mirror of
https://github.com/torvalds/linux.git
synced 2024-11-26 14:12:06 +00:00
bd6c11bc43
Core ---- - Increase size limits for to-be-sent skb frag allocations. This allows tun, tap devices and packet sockets to better cope with large writes operations. - Store netdevs in an xarray, to simplify iterating over netdevs. - Refactor nexthop selection for multipath routes. - Improve sched class lifetime handling. - Add backup nexthop ID support for bridge. - Implement drop reasons support in openvswitch. - Several data races annotations and fixes. - Constify the sk parameter of routing functions. - Prepend kernel version to netconsole message. Protocols --------- - Implement support for TCP probing the peer being under memory pressure. - Remove hard coded limitation on IPv6 specific info placement inside the socket struct. - Get rid of sysctl_tcp_adv_win_scale and use an auto-estimated per socket scaling factor. - Scaling-up the IPv6 expired route GC via a separated list of expiring routes. - In-kernel support for the TLS alert protocol. - Better support for UDP reuseport with connected sockets. - Add NEXT-C-SID support for SRv6 End.X behavior, reducing the SR header size. - Get rid of additional ancillary per MPTCP connection struct socket. - Implement support for BPF-based MPTCP packet schedulers. - Format MPTCP subtests selftests results in TAP. - Several new SMC 2.1 features including unique experimental options, max connections per lgr negotiation, max links per lgr negotiation. BPF --- - Multi-buffer support in AF_XDP. - Add multi uprobe BPF links for attaching multiple uprobes and usdt probes, which is significantly faster and saves extra fds. - Implement an fd-based tc BPF attach API (TCX) and BPF link support on top of it. - Add SO_REUSEPORT support for TC bpf_sk_assign. - Support new instructions from cpu v4 to simplify the generated code and feature completeness, for x86, arm64, riscv64. - Support defragmenting IPv(4|6) packets in BPF. - Teach verifier actual bounds of bpf_get_smp_processor_id() and fix perf+libbpf issue related to custom section handling. - Introduce bpf map element count and enable it for all program types. - Add a BPF hook in sys_socket() to change the protocol ID from IPPROTO_TCP to IPPROTO_MPTCP to cover migration for legacy. - Introduce bpf_me_mcache_free_rcu() and fix OOM under stress. - Add uprobe support for the bpf_get_func_ip helper. - Check skb ownership against full socket. - Support for up to 12 arguments in BPF trampoline. - Extend link_info for kprobe_multi and perf_event links. Netfilter --------- - Speed-up process exit by aborting ruleset validation if a fatal signal is pending. - Allow NLA_POLICY_MASK to be used with BE16/BE32 types. Driver API ---------- - Page pool optimizations, to improve data locality and cache usage. - Introduce ndo_hwtstamp_get() and ndo_hwtstamp_set() to avoid the need for raw ioctl() handling in drivers. - Simplify genetlink dump operations (doit/dumpit) providing them the common information already populated in struct genl_info. - Extend and use the yaml devlink specs to [re]generate the split ops. - Introduce devlink selective dumps, to allow SF filtering SF based on handle and other attributes. - Add yaml netlink spec for netlink-raw families, allow route, link and address related queries via the ynl tool. - Remove phylink legacy mode support. - Support offload LED blinking to phy. - Add devlink port function attributes for IPsec. New hardware / drivers ---------------------- - Ethernet: - Broadcom ASP 2.0 (72165) ethernet controller - MediaTek MT7988 SoC - Texas Instruments AM654 SoC - Texas Instruments IEP driver - Atheros qca8081 phy - Marvell 88Q2110 phy - NXP TJA1120 phy - WiFi: - MediaTek mt7981 support - Can: - Kvaser SmartFusion2 PCI Express devices - Allwinner T113 controllers - Texas Instruments tcan4552/4553 chips - Bluetooth: - Intel Gale Peak - Qualcomm WCN3988 and WCN7850 - NXP AW693 and IW624 - Mediatek MT2925 Drivers ------- - Ethernet NICs: - nVidia/Mellanox: - mlx5: - support UDP encapsulation in packet offload mode - IPsec packet offload support in eswitch mode - improve aRFS observability by adding new set of counters - extends MACsec offload support to cover RoCE traffic - dynamic completion EQs - mlx4: - convert to use auxiliary bus instead of custom interface logic - Intel - ice: - implement switchdev bridge offload, even for LAG interfaces - implement SRIOV support for LAG interfaces - igc: - add support for multiple in-flight TX timestamps - Broadcom: - bnxt: - use the unified RX page pool buffers for XDP and non-XDP - use the NAPI skb allocation cache - OcteonTX2: - support Round Robin scheduling HTB offload - TC flower offload support for SPI field - Freescale: - add XDP_TX feature support - AMD: - ionic: add support for PCI FLR event - sfc: - basic conntrack offload - introduce eth, ipv4 and ipv6 pedit offloads - ST Microelectronics: - stmmac: maximze PTP timestamping resolution - Virtual NICs: - Microsoft vNIC: - batch ringing RX queue doorbell on receiving packets - add page pool for RX buffers - Virtio vNIC: - add per queue interrupt coalescing support - Google vNIC: - add queue-page-list mode support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add port range matching tc-flower offload - permit enslavement to netdevices with uppers - Ethernet embedded switches: - Marvell (mv88e6xxx): - convert to phylink_pcs - Renesas: - r8A779fx: add speed change support - rzn1: enables vlan support - Ethernet PHYs: - convert mv88e6xxx to phylink_pcs - WiFi: - Qualcomm Wi-Fi 7 (ath12k): - extremely High Throughput (EHT) PHY support - RealTek (rtl8xxxu): - enable AP mode for: RTL8192FU, RTL8710BU (RTL8188GU), RTL8192EU and RTL8723BU - RealTek (rtw89): - Introduce Time Averaged SAR (TAS) support - Connector: - support for event filtering Signed-off-by: Paolo Abeni <pabeni@redhat.com> -----BEGIN PGP SIGNATURE----- iQJGBAABCAAwFiEEg1AjqC77wbdLX2LbKSR5jcyPE6QFAmTt1ZoSHHBhYmVuaUBy ZWRoYXQuY29tAAoJECkkeY3MjxOkgFUP/REFaYWdWUvAzmWeezyx9dqgZMfSOjWq 9QvySiA94OAOcjIYkb7wfzQ5BBAZqaBQ/f8XqWwS1EDDDEBs8sP1cxmABKwW7Hsr qFRu2sOqLzKBk223d0jIgEocfQaFpGbF71gXoTlDivBjBi5UxWm9bF0XnbYWcKgO /QEvzNosi9uNdi85Fzmv62J6YzAdidEpwGsM7X2CfejwNRmStxAEg/NwvRR0Hyiq OJCo97omEgTRaUle8nc64PDx33u4h5kQ1BkaeHEv0rbE3hftFC2YPKn/InmqSFGz 6ew2xnrGPR37LCuAiCcIIv6yR7K0eu0iYJ7jXwZxBDqxGavEPuwWGBoCP6qFiitH ZLWhIrAUrdmSbySkTOCONhJ475qFAuQoYHYpZnX/bJZUHlSsb/9lwDJYJQGpVfd1 /daqJVSb7lhaifmNO1iNd/ibCIXq9zapwtkRwA897M8GkZBTsnVvazFld1Em+Se3 Bx6DSDUVBqVQ9fpZG2IAGD6odDwOzC1lF2IoceFvK9Ff6oE0psI+A0qNLMkHxZbW Qlo7LsNe53hpoCC+yHTfXX7e/X8eNt0EnCGOQJDusZ0Nr3K7H4LKFA0i8UBUK05n 4lKnnaSQW7GQgdofLWt103OMDR9GoDxpFsm7b1X9+AEk6Fz6tq50wWYeMZETUKYP DCW8VGFOZjZM =9CsR -----END PGP SIGNATURE----- Merge tag 'net-next-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Paolo Abeni: "Core: - Increase size limits for to-be-sent skb frag allocations. This allows tun, tap devices and packet sockets to better cope with large writes operations - Store netdevs in an xarray, to simplify iterating over netdevs - Refactor nexthop selection for multipath routes - Improve sched class lifetime handling - Add backup nexthop ID support for bridge - Implement drop reasons support in openvswitch - Several data races annotations and fixes - Constify the sk parameter of routing functions - Prepend kernel version to netconsole message Protocols: - Implement support for TCP probing the peer being under memory pressure - Remove hard coded limitation on IPv6 specific info placement inside the socket struct - Get rid of sysctl_tcp_adv_win_scale and use an auto-estimated per socket scaling factor - Scaling-up the IPv6 expired route GC via a separated list of expiring routes - In-kernel support for the TLS alert protocol - Better support for UDP reuseport with connected sockets - Add NEXT-C-SID support for SRv6 End.X behavior, reducing the SR header size - Get rid of additional ancillary per MPTCP connection struct socket - Implement support for BPF-based MPTCP packet schedulers - Format MPTCP subtests selftests results in TAP - Several new SMC 2.1 features including unique experimental options, max connections per lgr negotiation, max links per lgr negotiation BPF: - Multi-buffer support in AF_XDP - Add multi uprobe BPF links for attaching multiple uprobes and usdt probes, which is significantly faster and saves extra fds - Implement an fd-based tc BPF attach API (TCX) and BPF link support on top of it - Add SO_REUSEPORT support for TC bpf_sk_assign - Support new instructions from cpu v4 to simplify the generated code and feature completeness, for x86, arm64, riscv64 - Support defragmenting IPv(4|6) packets in BPF - Teach verifier actual bounds of bpf_get_smp_processor_id() and fix perf+libbpf issue related to custom section handling - Introduce bpf map element count and enable it for all program types - Add a BPF hook in sys_socket() to change the protocol ID from IPPROTO_TCP to IPPROTO_MPTCP to cover migration for legacy - Introduce bpf_me_mcache_free_rcu() and fix OOM under stress - Add uprobe support for the bpf_get_func_ip helper - Check skb ownership against full socket - Support for up to 12 arguments in BPF trampoline - Extend link_info for kprobe_multi and perf_event links Netfilter: - Speed-up process exit by aborting ruleset validation if a fatal signal is pending - Allow NLA_POLICY_MASK to be used with BE16/BE32 types Driver API: - Page pool optimizations, to improve data locality and cache usage - Introduce ndo_hwtstamp_get() and ndo_hwtstamp_set() to avoid the need for raw ioctl() handling in drivers - Simplify genetlink dump operations (doit/dumpit) providing them the common information already populated in struct genl_info - Extend and use the yaml devlink specs to [re]generate the split ops - Introduce devlink selective dumps, to allow SF filtering SF based on handle and other attributes - Add yaml netlink spec for netlink-raw families, allow route, link and address related queries via the ynl tool - Remove phylink legacy mode support - Support offload LED blinking to phy - Add devlink port function attributes for IPsec New hardware / drivers: - Ethernet: - Broadcom ASP 2.0 (72165) ethernet controller - MediaTek MT7988 SoC - Texas Instruments AM654 SoC - Texas Instruments IEP driver - Atheros qca8081 phy - Marvell 88Q2110 phy - NXP TJA1120 phy - WiFi: - MediaTek mt7981 support - Can: - Kvaser SmartFusion2 PCI Express devices - Allwinner T113 controllers - Texas Instruments tcan4552/4553 chips - Bluetooth: - Intel Gale Peak - Qualcomm WCN3988 and WCN7850 - NXP AW693 and IW624 - Mediatek MT2925 Drivers: - Ethernet NICs: - nVidia/Mellanox: - mlx5: - support UDP encapsulation in packet offload mode - IPsec packet offload support in eswitch mode - improve aRFS observability by adding new set of counters - extends MACsec offload support to cover RoCE traffic - dynamic completion EQs - mlx4: - convert to use auxiliary bus instead of custom interface logic - Intel - ice: - implement switchdev bridge offload, even for LAG interfaces - implement SRIOV support for LAG interfaces - igc: - add support for multiple in-flight TX timestamps - Broadcom: - bnxt: - use the unified RX page pool buffers for XDP and non-XDP - use the NAPI skb allocation cache - OcteonTX2: - support Round Robin scheduling HTB offload - TC flower offload support for SPI field - Freescale: - add XDP_TX feature support - AMD: - ionic: add support for PCI FLR event - sfc: - basic conntrack offload - introduce eth, ipv4 and ipv6 pedit offloads - ST Microelectronics: - stmmac: maximze PTP timestamping resolution - Virtual NICs: - Microsoft vNIC: - batch ringing RX queue doorbell on receiving packets - add page pool for RX buffers - Virtio vNIC: - add per queue interrupt coalescing support - Google vNIC: - add queue-page-list mode support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add port range matching tc-flower offload - permit enslavement to netdevices with uppers - Ethernet embedded switches: - Marvell (mv88e6xxx): - convert to phylink_pcs - Renesas: - r8A779fx: add speed change support - rzn1: enables vlan support - Ethernet PHYs: - convert mv88e6xxx to phylink_pcs - WiFi: - Qualcomm Wi-Fi 7 (ath12k): - extremely High Throughput (EHT) PHY support - RealTek (rtl8xxxu): - enable AP mode for: RTL8192FU, RTL8710BU (RTL8188GU), RTL8192EU and RTL8723BU - RealTek (rtw89): - Introduce Time Averaged SAR (TAS) support - Connector: - support for event filtering" * tag 'net-next-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1806 commits) net: ethernet: mtk_wed: minor change in wed_{tx,rx}info_show net: ethernet: mtk_wed: add some more info in wed_txinfo_show handler net: stmmac: clarify difference between "interface" and "phy_interface" r8152: add vendor/device ID pair for D-Link DUB-E250 devlink: move devlink_notify_register/unregister() to dev.c devlink: move small_ops definition into netlink.c devlink: move tracepoint definitions into core.c devlink: push linecard related code into separate file devlink: push rate related code into separate file devlink: push trap related code into separate file devlink: use tracepoint_enabled() helper devlink: push region related code into separate file devlink: push param related code into separate file devlink: push resource related code into separate file devlink: push dpipe related code into separate file devlink: move and rename devlink_dpipe_send_and_alloc_skb() helper devlink: push shared buffer related code into separate file devlink: push port related code into separate file devlink: push object register/unregister notifications into separate helpers inet: fix IP_TRANSPARENT error handling ...
658 lines
20 KiB
C
658 lines
20 KiB
C
/* SPDX-License-Identifier: GPL-2.0+ */
|
|
/*
|
|
* Read-Copy Update definitions shared among RCU implementations.
|
|
*
|
|
* Copyright IBM Corporation, 2011
|
|
*
|
|
* Author: Paul E. McKenney <paulmck@linux.ibm.com>
|
|
*/
|
|
|
|
#ifndef __LINUX_RCU_H
|
|
#define __LINUX_RCU_H
|
|
|
|
#include <trace/events/rcu.h>
|
|
|
|
/*
|
|
* Grace-period counter management.
|
|
*
|
|
* The two least significant bits contain the control flags.
|
|
* The most significant bits contain the grace-period sequence counter.
|
|
*
|
|
* When both control flags are zero, no grace period is in progress.
|
|
* When either bit is non-zero, a grace period has started and is in
|
|
* progress. When the grace period completes, the control flags are reset
|
|
* to 0 and the grace-period sequence counter is incremented.
|
|
*
|
|
* However some specific RCU usages make use of custom values.
|
|
*
|
|
* SRCU special control values:
|
|
*
|
|
* SRCU_SNP_INIT_SEQ : Invalid/init value set when SRCU node
|
|
* is initialized.
|
|
*
|
|
* SRCU_STATE_IDLE : No SRCU gp is in progress
|
|
*
|
|
* SRCU_STATE_SCAN1 : State set by rcu_seq_start(). Indicates
|
|
* we are scanning the readers on the slot
|
|
* defined as inactive (there might well
|
|
* be pending readers that will use that
|
|
* index, but their number is bounded).
|
|
*
|
|
* SRCU_STATE_SCAN2 : State set manually via rcu_seq_set_state()
|
|
* Indicates we are flipping the readers
|
|
* index and then scanning the readers on the
|
|
* slot newly designated as inactive (again,
|
|
* the number of pending readers that will use
|
|
* this inactive index is bounded).
|
|
*
|
|
* RCU polled GP special control value:
|
|
*
|
|
* RCU_GET_STATE_COMPLETED : State value indicating an already-completed
|
|
* polled GP has completed. This value covers
|
|
* both the state and the counter of the
|
|
* grace-period sequence number.
|
|
*/
|
|
|
|
#define RCU_SEQ_CTR_SHIFT 2
|
|
#define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1)
|
|
|
|
/* Low-order bit definition for polled grace-period APIs. */
|
|
#define RCU_GET_STATE_COMPLETED 0x1
|
|
|
|
extern int sysctl_sched_rt_runtime;
|
|
|
|
/*
|
|
* Return the counter portion of a sequence number previously returned
|
|
* by rcu_seq_snap() or rcu_seq_current().
|
|
*/
|
|
static inline unsigned long rcu_seq_ctr(unsigned long s)
|
|
{
|
|
return s >> RCU_SEQ_CTR_SHIFT;
|
|
}
|
|
|
|
/*
|
|
* Return the state portion of a sequence number previously returned
|
|
* by rcu_seq_snap() or rcu_seq_current().
|
|
*/
|
|
static inline int rcu_seq_state(unsigned long s)
|
|
{
|
|
return s & RCU_SEQ_STATE_MASK;
|
|
}
|
|
|
|
/*
|
|
* Set the state portion of the pointed-to sequence number.
|
|
* The caller is responsible for preventing conflicting updates.
|
|
*/
|
|
static inline void rcu_seq_set_state(unsigned long *sp, int newstate)
|
|
{
|
|
WARN_ON_ONCE(newstate & ~RCU_SEQ_STATE_MASK);
|
|
WRITE_ONCE(*sp, (*sp & ~RCU_SEQ_STATE_MASK) + newstate);
|
|
}
|
|
|
|
/* Adjust sequence number for start of update-side operation. */
|
|
static inline void rcu_seq_start(unsigned long *sp)
|
|
{
|
|
WRITE_ONCE(*sp, *sp + 1);
|
|
smp_mb(); /* Ensure update-side operation after counter increment. */
|
|
WARN_ON_ONCE(rcu_seq_state(*sp) != 1);
|
|
}
|
|
|
|
/* Compute the end-of-grace-period value for the specified sequence number. */
|
|
static inline unsigned long rcu_seq_endval(unsigned long *sp)
|
|
{
|
|
return (*sp | RCU_SEQ_STATE_MASK) + 1;
|
|
}
|
|
|
|
/* Adjust sequence number for end of update-side operation. */
|
|
static inline void rcu_seq_end(unsigned long *sp)
|
|
{
|
|
smp_mb(); /* Ensure update-side operation before counter increment. */
|
|
WARN_ON_ONCE(!rcu_seq_state(*sp));
|
|
WRITE_ONCE(*sp, rcu_seq_endval(sp));
|
|
}
|
|
|
|
/*
|
|
* rcu_seq_snap - Take a snapshot of the update side's sequence number.
|
|
*
|
|
* This function returns the earliest value of the grace-period sequence number
|
|
* that will indicate that a full grace period has elapsed since the current
|
|
* time. Once the grace-period sequence number has reached this value, it will
|
|
* be safe to invoke all callbacks that have been registered prior to the
|
|
* current time. This value is the current grace-period number plus two to the
|
|
* power of the number of low-order bits reserved for state, then rounded up to
|
|
* the next value in which the state bits are all zero.
|
|
*/
|
|
static inline unsigned long rcu_seq_snap(unsigned long *sp)
|
|
{
|
|
unsigned long s;
|
|
|
|
s = (READ_ONCE(*sp) + 2 * RCU_SEQ_STATE_MASK + 1) & ~RCU_SEQ_STATE_MASK;
|
|
smp_mb(); /* Above access must not bleed into critical section. */
|
|
return s;
|
|
}
|
|
|
|
/* Return the current value the update side's sequence number, no ordering. */
|
|
static inline unsigned long rcu_seq_current(unsigned long *sp)
|
|
{
|
|
return READ_ONCE(*sp);
|
|
}
|
|
|
|
/*
|
|
* Given a snapshot from rcu_seq_snap(), determine whether or not the
|
|
* corresponding update-side operation has started.
|
|
*/
|
|
static inline bool rcu_seq_started(unsigned long *sp, unsigned long s)
|
|
{
|
|
return ULONG_CMP_LT((s - 1) & ~RCU_SEQ_STATE_MASK, READ_ONCE(*sp));
|
|
}
|
|
|
|
/*
|
|
* Given a snapshot from rcu_seq_snap(), determine whether or not a
|
|
* full update-side operation has occurred.
|
|
*/
|
|
static inline bool rcu_seq_done(unsigned long *sp, unsigned long s)
|
|
{
|
|
return ULONG_CMP_GE(READ_ONCE(*sp), s);
|
|
}
|
|
|
|
/*
|
|
* Given a snapshot from rcu_seq_snap(), determine whether or not a
|
|
* full update-side operation has occurred, but do not allow the
|
|
* (ULONG_MAX / 2) safety-factor/guard-band.
|
|
*/
|
|
static inline bool rcu_seq_done_exact(unsigned long *sp, unsigned long s)
|
|
{
|
|
unsigned long cur_s = READ_ONCE(*sp);
|
|
|
|
return ULONG_CMP_GE(cur_s, s) || ULONG_CMP_LT(cur_s, s - (2 * RCU_SEQ_STATE_MASK + 1));
|
|
}
|
|
|
|
/*
|
|
* Has a grace period completed since the time the old gp_seq was collected?
|
|
*/
|
|
static inline bool rcu_seq_completed_gp(unsigned long old, unsigned long new)
|
|
{
|
|
return ULONG_CMP_LT(old, new & ~RCU_SEQ_STATE_MASK);
|
|
}
|
|
|
|
/*
|
|
* Has a grace period started since the time the old gp_seq was collected?
|
|
*/
|
|
static inline bool rcu_seq_new_gp(unsigned long old, unsigned long new)
|
|
{
|
|
return ULONG_CMP_LT((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK,
|
|
new);
|
|
}
|
|
|
|
/*
|
|
* Roughly how many full grace periods have elapsed between the collection
|
|
* of the two specified grace periods?
|
|
*/
|
|
static inline unsigned long rcu_seq_diff(unsigned long new, unsigned long old)
|
|
{
|
|
unsigned long rnd_diff;
|
|
|
|
if (old == new)
|
|
return 0;
|
|
/*
|
|
* Compute the number of grace periods (still shifted up), plus
|
|
* one if either of new and old is not an exact grace period.
|
|
*/
|
|
rnd_diff = (new & ~RCU_SEQ_STATE_MASK) -
|
|
((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK) +
|
|
((new & RCU_SEQ_STATE_MASK) || (old & RCU_SEQ_STATE_MASK));
|
|
if (ULONG_CMP_GE(RCU_SEQ_STATE_MASK, rnd_diff))
|
|
return 1; /* Definitely no grace period has elapsed. */
|
|
return ((rnd_diff - RCU_SEQ_STATE_MASK - 1) >> RCU_SEQ_CTR_SHIFT) + 2;
|
|
}
|
|
|
|
/*
|
|
* debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
|
|
* by call_rcu() and rcu callback execution, and are therefore not part
|
|
* of the RCU API. These are in rcupdate.h because they are used by all
|
|
* RCU implementations.
|
|
*/
|
|
|
|
#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
|
|
# define STATE_RCU_HEAD_READY 0
|
|
# define STATE_RCU_HEAD_QUEUED 1
|
|
|
|
extern const struct debug_obj_descr rcuhead_debug_descr;
|
|
|
|
static inline int debug_rcu_head_queue(struct rcu_head *head)
|
|
{
|
|
int r1;
|
|
|
|
r1 = debug_object_activate(head, &rcuhead_debug_descr);
|
|
debug_object_active_state(head, &rcuhead_debug_descr,
|
|
STATE_RCU_HEAD_READY,
|
|
STATE_RCU_HEAD_QUEUED);
|
|
return r1;
|
|
}
|
|
|
|
static inline void debug_rcu_head_unqueue(struct rcu_head *head)
|
|
{
|
|
debug_object_active_state(head, &rcuhead_debug_descr,
|
|
STATE_RCU_HEAD_QUEUED,
|
|
STATE_RCU_HEAD_READY);
|
|
debug_object_deactivate(head, &rcuhead_debug_descr);
|
|
}
|
|
#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
|
|
static inline int debug_rcu_head_queue(struct rcu_head *head)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void debug_rcu_head_unqueue(struct rcu_head *head)
|
|
{
|
|
}
|
|
#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
|
|
|
|
extern int rcu_cpu_stall_suppress_at_boot;
|
|
|
|
static inline bool rcu_stall_is_suppressed_at_boot(void)
|
|
{
|
|
return rcu_cpu_stall_suppress_at_boot && !rcu_inkernel_boot_has_ended();
|
|
}
|
|
|
|
#ifdef CONFIG_RCU_STALL_COMMON
|
|
|
|
extern int rcu_cpu_stall_ftrace_dump;
|
|
extern int rcu_cpu_stall_suppress;
|
|
extern int rcu_cpu_stall_timeout;
|
|
extern int rcu_exp_cpu_stall_timeout;
|
|
extern int rcu_cpu_stall_cputime;
|
|
extern bool rcu_exp_stall_task_details __read_mostly;
|
|
int rcu_jiffies_till_stall_check(void);
|
|
int rcu_exp_jiffies_till_stall_check(void);
|
|
|
|
static inline bool rcu_stall_is_suppressed(void)
|
|
{
|
|
return rcu_stall_is_suppressed_at_boot() || rcu_cpu_stall_suppress;
|
|
}
|
|
|
|
#define rcu_ftrace_dump_stall_suppress() \
|
|
do { \
|
|
if (!rcu_cpu_stall_suppress) \
|
|
rcu_cpu_stall_suppress = 3; \
|
|
} while (0)
|
|
|
|
#define rcu_ftrace_dump_stall_unsuppress() \
|
|
do { \
|
|
if (rcu_cpu_stall_suppress == 3) \
|
|
rcu_cpu_stall_suppress = 0; \
|
|
} while (0)
|
|
|
|
#else /* #endif #ifdef CONFIG_RCU_STALL_COMMON */
|
|
|
|
static inline bool rcu_stall_is_suppressed(void)
|
|
{
|
|
return rcu_stall_is_suppressed_at_boot();
|
|
}
|
|
#define rcu_ftrace_dump_stall_suppress()
|
|
#define rcu_ftrace_dump_stall_unsuppress()
|
|
#endif /* #ifdef CONFIG_RCU_STALL_COMMON */
|
|
|
|
/*
|
|
* Strings used in tracepoints need to be exported via the
|
|
* tracing system such that tools like perf and trace-cmd can
|
|
* translate the string address pointers to actual text.
|
|
*/
|
|
#define TPS(x) tracepoint_string(x)
|
|
|
|
/*
|
|
* Dump the ftrace buffer, but only one time per callsite per boot.
|
|
*/
|
|
#define rcu_ftrace_dump(oops_dump_mode) \
|
|
do { \
|
|
static atomic_t ___rfd_beenhere = ATOMIC_INIT(0); \
|
|
\
|
|
if (!atomic_read(&___rfd_beenhere) && \
|
|
!atomic_xchg(&___rfd_beenhere, 1)) { \
|
|
tracing_off(); \
|
|
rcu_ftrace_dump_stall_suppress(); \
|
|
ftrace_dump(oops_dump_mode); \
|
|
rcu_ftrace_dump_stall_unsuppress(); \
|
|
} \
|
|
} while (0)
|
|
|
|
void rcu_early_boot_tests(void);
|
|
void rcu_test_sync_prims(void);
|
|
|
|
/*
|
|
* This function really isn't for public consumption, but RCU is special in
|
|
* that context switches can allow the state machine to make progress.
|
|
*/
|
|
extern void resched_cpu(int cpu);
|
|
|
|
#if !defined(CONFIG_TINY_RCU)
|
|
|
|
#include <linux/rcu_node_tree.h>
|
|
|
|
extern int rcu_num_lvls;
|
|
extern int num_rcu_lvl[];
|
|
extern int rcu_num_nodes;
|
|
static bool rcu_fanout_exact;
|
|
static int rcu_fanout_leaf;
|
|
|
|
/*
|
|
* Compute the per-level fanout, either using the exact fanout specified
|
|
* or balancing the tree, depending on the rcu_fanout_exact boot parameter.
|
|
*/
|
|
static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < RCU_NUM_LVLS; i++)
|
|
levelspread[i] = INT_MIN;
|
|
if (rcu_fanout_exact) {
|
|
levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
|
|
for (i = rcu_num_lvls - 2; i >= 0; i--)
|
|
levelspread[i] = RCU_FANOUT;
|
|
} else {
|
|
int ccur;
|
|
int cprv;
|
|
|
|
cprv = nr_cpu_ids;
|
|
for (i = rcu_num_lvls - 1; i >= 0; i--) {
|
|
ccur = levelcnt[i];
|
|
levelspread[i] = (cprv + ccur - 1) / ccur;
|
|
cprv = ccur;
|
|
}
|
|
}
|
|
}
|
|
|
|
extern void rcu_init_geometry(void);
|
|
|
|
/* Returns a pointer to the first leaf rcu_node structure. */
|
|
#define rcu_first_leaf_node() (rcu_state.level[rcu_num_lvls - 1])
|
|
|
|
/* Is this rcu_node a leaf? */
|
|
#define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1)
|
|
|
|
/* Is this rcu_node the last leaf? */
|
|
#define rcu_is_last_leaf_node(rnp) ((rnp) == &rcu_state.node[rcu_num_nodes - 1])
|
|
|
|
/*
|
|
* Do a full breadth-first scan of the {s,}rcu_node structures for the
|
|
* specified state structure (for SRCU) or the only rcu_state structure
|
|
* (for RCU).
|
|
*/
|
|
#define _rcu_for_each_node_breadth_first(sp, rnp) \
|
|
for ((rnp) = &(sp)->node[0]; \
|
|
(rnp) < &(sp)->node[rcu_num_nodes]; (rnp)++)
|
|
#define rcu_for_each_node_breadth_first(rnp) \
|
|
_rcu_for_each_node_breadth_first(&rcu_state, rnp)
|
|
#define srcu_for_each_node_breadth_first(ssp, rnp) \
|
|
_rcu_for_each_node_breadth_first(ssp->srcu_sup, rnp)
|
|
|
|
/*
|
|
* Scan the leaves of the rcu_node hierarchy for the rcu_state structure.
|
|
* Note that if there is a singleton rcu_node tree with but one rcu_node
|
|
* structure, this loop -will- visit the rcu_node structure. It is still
|
|
* a leaf node, even if it is also the root node.
|
|
*/
|
|
#define rcu_for_each_leaf_node(rnp) \
|
|
for ((rnp) = rcu_first_leaf_node(); \
|
|
(rnp) < &rcu_state.node[rcu_num_nodes]; (rnp)++)
|
|
|
|
/*
|
|
* Iterate over all possible CPUs in a leaf RCU node.
|
|
*/
|
|
#define for_each_leaf_node_possible_cpu(rnp, cpu) \
|
|
for (WARN_ON_ONCE(!rcu_is_leaf_node(rnp)), \
|
|
(cpu) = cpumask_next((rnp)->grplo - 1, cpu_possible_mask); \
|
|
(cpu) <= rnp->grphi; \
|
|
(cpu) = cpumask_next((cpu), cpu_possible_mask))
|
|
|
|
/*
|
|
* Iterate over all CPUs in a leaf RCU node's specified mask.
|
|
*/
|
|
#define rcu_find_next_bit(rnp, cpu, mask) \
|
|
((rnp)->grplo + find_next_bit(&(mask), BITS_PER_LONG, (cpu)))
|
|
#define for_each_leaf_node_cpu_mask(rnp, cpu, mask) \
|
|
for (WARN_ON_ONCE(!rcu_is_leaf_node(rnp)), \
|
|
(cpu) = rcu_find_next_bit((rnp), 0, (mask)); \
|
|
(cpu) <= rnp->grphi; \
|
|
(cpu) = rcu_find_next_bit((rnp), (cpu) + 1 - (rnp->grplo), (mask)))
|
|
|
|
#endif /* !defined(CONFIG_TINY_RCU) */
|
|
|
|
#if !defined(CONFIG_TINY_RCU) || defined(CONFIG_TASKS_RCU_GENERIC)
|
|
|
|
/*
|
|
* Wrappers for the rcu_node::lock acquire and release.
|
|
*
|
|
* Because the rcu_nodes form a tree, the tree traversal locking will observe
|
|
* different lock values, this in turn means that an UNLOCK of one level
|
|
* followed by a LOCK of another level does not imply a full memory barrier;
|
|
* and most importantly transitivity is lost.
|
|
*
|
|
* In order to restore full ordering between tree levels, augment the regular
|
|
* lock acquire functions with smp_mb__after_unlock_lock().
|
|
*
|
|
* As ->lock of struct rcu_node is a __private field, therefore one should use
|
|
* these wrappers rather than directly call raw_spin_{lock,unlock}* on ->lock.
|
|
*/
|
|
#define raw_spin_lock_rcu_node(p) \
|
|
do { \
|
|
raw_spin_lock(&ACCESS_PRIVATE(p, lock)); \
|
|
smp_mb__after_unlock_lock(); \
|
|
} while (0)
|
|
|
|
#define raw_spin_unlock_rcu_node(p) \
|
|
do { \
|
|
lockdep_assert_irqs_disabled(); \
|
|
raw_spin_unlock(&ACCESS_PRIVATE(p, lock)); \
|
|
} while (0)
|
|
|
|
#define raw_spin_lock_irq_rcu_node(p) \
|
|
do { \
|
|
raw_spin_lock_irq(&ACCESS_PRIVATE(p, lock)); \
|
|
smp_mb__after_unlock_lock(); \
|
|
} while (0)
|
|
|
|
#define raw_spin_unlock_irq_rcu_node(p) \
|
|
do { \
|
|
lockdep_assert_irqs_disabled(); \
|
|
raw_spin_unlock_irq(&ACCESS_PRIVATE(p, lock)); \
|
|
} while (0)
|
|
|
|
#define raw_spin_lock_irqsave_rcu_node(p, flags) \
|
|
do { \
|
|
raw_spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \
|
|
smp_mb__after_unlock_lock(); \
|
|
} while (0)
|
|
|
|
#define raw_spin_unlock_irqrestore_rcu_node(p, flags) \
|
|
do { \
|
|
lockdep_assert_irqs_disabled(); \
|
|
raw_spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags); \
|
|
} while (0)
|
|
|
|
#define raw_spin_trylock_rcu_node(p) \
|
|
({ \
|
|
bool ___locked = raw_spin_trylock(&ACCESS_PRIVATE(p, lock)); \
|
|
\
|
|
if (___locked) \
|
|
smp_mb__after_unlock_lock(); \
|
|
___locked; \
|
|
})
|
|
|
|
#define raw_lockdep_assert_held_rcu_node(p) \
|
|
lockdep_assert_held(&ACCESS_PRIVATE(p, lock))
|
|
|
|
#endif // #if !defined(CONFIG_TINY_RCU) || defined(CONFIG_TASKS_RCU_GENERIC)
|
|
|
|
#ifdef CONFIG_TINY_RCU
|
|
/* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */
|
|
static inline bool rcu_gp_is_normal(void) { return true; }
|
|
static inline bool rcu_gp_is_expedited(void) { return false; }
|
|
static inline bool rcu_async_should_hurry(void) { return false; }
|
|
static inline void rcu_expedite_gp(void) { }
|
|
static inline void rcu_unexpedite_gp(void) { }
|
|
static inline void rcu_async_hurry(void) { }
|
|
static inline void rcu_async_relax(void) { }
|
|
#else /* #ifdef CONFIG_TINY_RCU */
|
|
bool rcu_gp_is_normal(void); /* Internal RCU use. */
|
|
bool rcu_gp_is_expedited(void); /* Internal RCU use. */
|
|
bool rcu_async_should_hurry(void); /* Internal RCU use. */
|
|
void rcu_expedite_gp(void);
|
|
void rcu_unexpedite_gp(void);
|
|
void rcu_async_hurry(void);
|
|
void rcu_async_relax(void);
|
|
void rcupdate_announce_bootup_oddness(void);
|
|
#ifdef CONFIG_TASKS_RCU_GENERIC
|
|
void show_rcu_tasks_gp_kthreads(void);
|
|
#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
|
|
static inline void show_rcu_tasks_gp_kthreads(void) {}
|
|
#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
|
|
#endif /* #else #ifdef CONFIG_TINY_RCU */
|
|
|
|
#ifdef CONFIG_TASKS_RCU
|
|
struct task_struct *get_rcu_tasks_gp_kthread(void);
|
|
#endif // # ifdef CONFIG_TASKS_RCU
|
|
|
|
#ifdef CONFIG_TASKS_RUDE_RCU
|
|
struct task_struct *get_rcu_tasks_rude_gp_kthread(void);
|
|
#endif // # ifdef CONFIG_TASKS_RUDE_RCU
|
|
|
|
#define RCU_SCHEDULER_INACTIVE 0
|
|
#define RCU_SCHEDULER_INIT 1
|
|
#define RCU_SCHEDULER_RUNNING 2
|
|
|
|
enum rcutorture_type {
|
|
RCU_FLAVOR,
|
|
RCU_TASKS_FLAVOR,
|
|
RCU_TASKS_RUDE_FLAVOR,
|
|
RCU_TASKS_TRACING_FLAVOR,
|
|
RCU_TRIVIAL_FLAVOR,
|
|
SRCU_FLAVOR,
|
|
INVALID_RCU_FLAVOR
|
|
};
|
|
|
|
#if defined(CONFIG_RCU_LAZY)
|
|
unsigned long rcu_lazy_get_jiffies_till_flush(void);
|
|
void rcu_lazy_set_jiffies_till_flush(unsigned long j);
|
|
#else
|
|
static inline unsigned long rcu_lazy_get_jiffies_till_flush(void) { return 0; }
|
|
static inline void rcu_lazy_set_jiffies_till_flush(unsigned long j) { }
|
|
#endif
|
|
|
|
#if defined(CONFIG_TREE_RCU)
|
|
void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
|
|
unsigned long *gp_seq);
|
|
void do_trace_rcu_torture_read(const char *rcutorturename,
|
|
struct rcu_head *rhp,
|
|
unsigned long secs,
|
|
unsigned long c_old,
|
|
unsigned long c);
|
|
void rcu_gp_set_torture_wait(int duration);
|
|
#else
|
|
static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
|
|
int *flags, unsigned long *gp_seq)
|
|
{
|
|
*flags = 0;
|
|
*gp_seq = 0;
|
|
}
|
|
#ifdef CONFIG_RCU_TRACE
|
|
void do_trace_rcu_torture_read(const char *rcutorturename,
|
|
struct rcu_head *rhp,
|
|
unsigned long secs,
|
|
unsigned long c_old,
|
|
unsigned long c);
|
|
#else
|
|
#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
|
|
do { } while (0)
|
|
#endif
|
|
static inline void rcu_gp_set_torture_wait(int duration) { }
|
|
#endif
|
|
|
|
#if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST)
|
|
long rcutorture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask);
|
|
#endif
|
|
|
|
#ifdef CONFIG_TINY_SRCU
|
|
|
|
static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
|
|
struct srcu_struct *sp, int *flags,
|
|
unsigned long *gp_seq)
|
|
{
|
|
if (test_type != SRCU_FLAVOR)
|
|
return;
|
|
*flags = 0;
|
|
*gp_seq = sp->srcu_idx;
|
|
}
|
|
|
|
#elif defined(CONFIG_TREE_SRCU)
|
|
|
|
void srcutorture_get_gp_data(enum rcutorture_type test_type,
|
|
struct srcu_struct *sp, int *flags,
|
|
unsigned long *gp_seq);
|
|
|
|
#endif
|
|
|
|
#ifdef CONFIG_TINY_RCU
|
|
static inline bool rcu_dynticks_zero_in_eqs(int cpu, int *vp) { return false; }
|
|
static inline unsigned long rcu_get_gp_seq(void) { return 0; }
|
|
static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
|
|
static inline unsigned long
|
|
srcu_batches_completed(struct srcu_struct *sp) { return 0; }
|
|
static inline void rcu_force_quiescent_state(void) { }
|
|
static inline bool rcu_check_boost_fail(unsigned long gp_state, int *cpup) { return true; }
|
|
static inline void show_rcu_gp_kthreads(void) { }
|
|
static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
|
|
static inline void rcu_fwd_progress_check(unsigned long j) { }
|
|
static inline void rcu_gp_slow_register(atomic_t *rgssp) { }
|
|
static inline void rcu_gp_slow_unregister(atomic_t *rgssp) { }
|
|
#else /* #ifdef CONFIG_TINY_RCU */
|
|
bool rcu_dynticks_zero_in_eqs(int cpu, int *vp);
|
|
unsigned long rcu_get_gp_seq(void);
|
|
unsigned long rcu_exp_batches_completed(void);
|
|
unsigned long srcu_batches_completed(struct srcu_struct *sp);
|
|
bool rcu_check_boost_fail(unsigned long gp_state, int *cpup);
|
|
void show_rcu_gp_kthreads(void);
|
|
int rcu_get_gp_kthreads_prio(void);
|
|
void rcu_fwd_progress_check(unsigned long j);
|
|
void rcu_force_quiescent_state(void);
|
|
extern struct workqueue_struct *rcu_gp_wq;
|
|
#ifdef CONFIG_RCU_EXP_KTHREAD
|
|
extern struct kthread_worker *rcu_exp_gp_kworker;
|
|
extern struct kthread_worker *rcu_exp_par_gp_kworker;
|
|
#else /* !CONFIG_RCU_EXP_KTHREAD */
|
|
extern struct workqueue_struct *rcu_par_gp_wq;
|
|
#endif /* CONFIG_RCU_EXP_KTHREAD */
|
|
void rcu_gp_slow_register(atomic_t *rgssp);
|
|
void rcu_gp_slow_unregister(atomic_t *rgssp);
|
|
#endif /* #else #ifdef CONFIG_TINY_RCU */
|
|
|
|
#ifdef CONFIG_RCU_NOCB_CPU
|
|
void rcu_bind_current_to_nocb(void);
|
|
#else
|
|
static inline void rcu_bind_current_to_nocb(void) { }
|
|
#endif
|
|
|
|
#if !defined(CONFIG_TINY_RCU) && defined(CONFIG_TASKS_RCU)
|
|
void show_rcu_tasks_classic_gp_kthread(void);
|
|
#else
|
|
static inline void show_rcu_tasks_classic_gp_kthread(void) {}
|
|
#endif
|
|
#if !defined(CONFIG_TINY_RCU) && defined(CONFIG_TASKS_RUDE_RCU)
|
|
void show_rcu_tasks_rude_gp_kthread(void);
|
|
#else
|
|
static inline void show_rcu_tasks_rude_gp_kthread(void) {}
|
|
#endif
|
|
#if !defined(CONFIG_TINY_RCU) && defined(CONFIG_TASKS_TRACE_RCU)
|
|
void show_rcu_tasks_trace_gp_kthread(void);
|
|
#else
|
|
static inline void show_rcu_tasks_trace_gp_kthread(void) {}
|
|
#endif
|
|
|
|
#ifdef CONFIG_TINY_RCU
|
|
static inline bool rcu_cpu_beenfullyonline(int cpu) { return true; }
|
|
#else
|
|
bool rcu_cpu_beenfullyonline(int cpu);
|
|
#endif
|
|
|
|
#endif /* __LINUX_RCU_H */
|