exynos-linux-stable/include/linux/rculist_nulls.h

174 lines
6.1 KiB
C
Raw Permalink Normal View History

rcu: Introduce hlist_nulls variant of hlist hlist uses NULL value to finish a chain. hlist_nulls variant use the low order bit set to 1 to signal an end-of-list marker. This allows to store many different end markers, so that some RCU lockless algos (used in TCP/UDP stack for example) can save some memory barriers in fast paths. Two new files are added : include/linux/list_nulls.h - mimics hlist part of include/linux/list.h, derived to hlist_nulls variant include/linux/rculist_nulls.h - mimics hlist part of include/linux/rculist.h, derived to hlist_nulls variant Only four helpers are declared for the moment : hlist_nulls_del_init_rcu(), hlist_nulls_del_rcu(), hlist_nulls_add_head_rcu() and hlist_nulls_for_each_entry_rcu() prefetches() were removed, since an end of list is not anymore NULL value. prefetches() could trigger useless (and possibly dangerous) memory transactions. Example of use (extracted from __udp4_lib_lookup()) struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); unsigned int hash = udp_hashfn(net, hnum); struct udp_hslot *hslot = &udptable->hash[hash]; int score, badness; rcu_read_lock(); begin: result = NULL; badness = -1; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; } } /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (get_nulls_value(node) != hash) goto begin; if (result) { if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) result = NULL; else if (unlikely(compute_score(result, net, saddr, hnum, sport, daddr, dport, dif) < badness)) { sock_put(result); goto begin; } } rcu_read_unlock(); return result; Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-16 19:37:55 -08:00
#ifndef _LINUX_RCULIST_NULLS_H
#define _LINUX_RCULIST_NULLS_H
#ifdef __KERNEL__
/*
* RCU-protected list version
*/
#include <linux/list_nulls.h>
#include <linux/rcupdate.h>
/**
* hlist_nulls_del_init_rcu - deletes entry from hash list with re-initialization
* @n: the element to delete from the hash list.
*
* Note: hlist_nulls_unhashed() on the node return true after this. It is
* useful for RCU based read lockfree traversal if the writer side
* must know if the list entry is still hashed or already unhashed.
*
* In particular, it means that we can not poison the forward pointers
* that may still be used for walking the hash list and we can only
* zero the pprev pointer so list_unhashed() will return true after
* this.
*
* The caller must take whatever precautions are necessary (such as
* holding appropriate locks) to avoid racing with another
* list-mutation primitive, such as hlist_nulls_add_head_rcu() or
* hlist_nulls_del_rcu(), running on this same list. However, it is
* perfectly legal to run concurrently with the _rcu list-traversal
* primitives, such as hlist_nulls_for_each_entry_rcu().
*/
static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n)
{
if (!hlist_nulls_unhashed(n)) {
__hlist_nulls_del(n);
rcu: Use WRITE_ONCE() for assignments to ->pprev for hlist_nulls [ Upstream commit 860c8802ace14c646864795e057349c9fb2d60ad ] Eric Dumazet supplied a KCSAN report of a bug that forces use of hlist_unhashed_lockless() from sk_unhashed(): ------------------------------------------------------------------------ BUG: KCSAN: data-race in inet_unhash / inet_unhash write to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 1: __hlist_nulls_del include/linux/list_nulls.h:88 [inline] hlist_nulls_del_init_rcu include/linux/rculist_nulls.h:36 [inline] __sk_nulls_del_node_init_rcu include/net/sock.h:676 [inline] inet_unhash+0x38f/0x4a0 net/ipv4/inet_hashtables.c:612 tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249 tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854 tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56 tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619 call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71 arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571 default_idle_call+0x1e/0x40 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x1af/0x280 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355 start_secondary+0x208/0x260 arch/x86/kernel/smpboot.c:264 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241 read to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 0: sk_unhashed include/net/sock.h:607 [inline] inet_unhash+0x3d/0x4a0 net/ipv4/inet_hashtables.c:592 tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249 tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854 tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56 tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619 call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71 arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571 default_idle_call+0x1e/0x40 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x1af/0x280 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355 rest_init+0xec/0xf6 init/main.c:452 arch_call_rest_init+0x17/0x37 start_kernel+0x838/0x85e init/main.c:786 x86_64_start_reservations+0x29/0x2b arch/x86/kernel/head64.c:490 x86_64_start_kernel+0x72/0x76 arch/x86/kernel/head64.c:471 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc6+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 ------------------------------------------------------------------------ This commit therefore replaces C-language assignments with WRITE_ONCE() in include/linux/list_nulls.h and include/linux/rculist_nulls.h. Reported-by: Eric Dumazet <edumazet@google.com> # For KCSAN Signed-off-by: Paul E. McKenney <paulmck@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
2019-11-09 09:42:13 -08:00
WRITE_ONCE(n->pprev, NULL);
rcu: Introduce hlist_nulls variant of hlist hlist uses NULL value to finish a chain. hlist_nulls variant use the low order bit set to 1 to signal an end-of-list marker. This allows to store many different end markers, so that some RCU lockless algos (used in TCP/UDP stack for example) can save some memory barriers in fast paths. Two new files are added : include/linux/list_nulls.h - mimics hlist part of include/linux/list.h, derived to hlist_nulls variant include/linux/rculist_nulls.h - mimics hlist part of include/linux/rculist.h, derived to hlist_nulls variant Only four helpers are declared for the moment : hlist_nulls_del_init_rcu(), hlist_nulls_del_rcu(), hlist_nulls_add_head_rcu() and hlist_nulls_for_each_entry_rcu() prefetches() were removed, since an end of list is not anymore NULL value. prefetches() could trigger useless (and possibly dangerous) memory transactions. Example of use (extracted from __udp4_lib_lookup()) struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); unsigned int hash = udp_hashfn(net, hnum); struct udp_hslot *hslot = &udptable->hash[hash]; int score, badness; rcu_read_lock(); begin: result = NULL; badness = -1; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; } } /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (get_nulls_value(node) != hash) goto begin; if (result) { if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) result = NULL; else if (unlikely(compute_score(result, net, saddr, hnum, sport, daddr, dport, dif) < badness)) { sock_put(result); goto begin; } } rcu_read_unlock(); return result; Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-16 19:37:55 -08:00
}
}
#define hlist_nulls_first_rcu(head) \
(*((struct hlist_nulls_node __rcu __force **)&(head)->first))
#define hlist_nulls_next_rcu(node) \
(*((struct hlist_nulls_node __rcu __force **)&(node)->next))
rcu: Introduce hlist_nulls variant of hlist hlist uses NULL value to finish a chain. hlist_nulls variant use the low order bit set to 1 to signal an end-of-list marker. This allows to store many different end markers, so that some RCU lockless algos (used in TCP/UDP stack for example) can save some memory barriers in fast paths. Two new files are added : include/linux/list_nulls.h - mimics hlist part of include/linux/list.h, derived to hlist_nulls variant include/linux/rculist_nulls.h - mimics hlist part of include/linux/rculist.h, derived to hlist_nulls variant Only four helpers are declared for the moment : hlist_nulls_del_init_rcu(), hlist_nulls_del_rcu(), hlist_nulls_add_head_rcu() and hlist_nulls_for_each_entry_rcu() prefetches() were removed, since an end of list is not anymore NULL value. prefetches() could trigger useless (and possibly dangerous) memory transactions. Example of use (extracted from __udp4_lib_lookup()) struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); unsigned int hash = udp_hashfn(net, hnum); struct udp_hslot *hslot = &udptable->hash[hash]; int score, badness; rcu_read_lock(); begin: result = NULL; badness = -1; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; } } /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (get_nulls_value(node) != hash) goto begin; if (result) { if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) result = NULL; else if (unlikely(compute_score(result, net, saddr, hnum, sport, daddr, dport, dif) < badness)) { sock_put(result); goto begin; } } rcu_read_unlock(); return result; Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-16 19:37:55 -08:00
/**
* hlist_nulls_del_rcu - deletes entry from hash list without re-initialization
* @n: the element to delete from the hash list.
*
* Note: hlist_nulls_unhashed() on entry does not return true after this,
* the entry is in an undefined state. It is useful for RCU based
* lockfree traversal.
*
* In particular, it means that we can not poison the forward
* pointers that may still be used for walking the hash list.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
* or hlist_nulls_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_nulls_for_each_entry().
*/
static inline void hlist_nulls_del_rcu(struct hlist_nulls_node *n)
{
__hlist_nulls_del(n);
rcu: Use WRITE_ONCE() for assignments to ->pprev for hlist_nulls [ Upstream commit 860c8802ace14c646864795e057349c9fb2d60ad ] Eric Dumazet supplied a KCSAN report of a bug that forces use of hlist_unhashed_lockless() from sk_unhashed(): ------------------------------------------------------------------------ BUG: KCSAN: data-race in inet_unhash / inet_unhash write to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 1: __hlist_nulls_del include/linux/list_nulls.h:88 [inline] hlist_nulls_del_init_rcu include/linux/rculist_nulls.h:36 [inline] __sk_nulls_del_node_init_rcu include/net/sock.h:676 [inline] inet_unhash+0x38f/0x4a0 net/ipv4/inet_hashtables.c:612 tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249 tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854 tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56 tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619 call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71 arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571 default_idle_call+0x1e/0x40 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x1af/0x280 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355 start_secondary+0x208/0x260 arch/x86/kernel/smpboot.c:264 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241 read to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 0: sk_unhashed include/net/sock.h:607 [inline] inet_unhash+0x3d/0x4a0 net/ipv4/inet_hashtables.c:592 tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249 tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854 tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56 tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619 call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71 arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571 default_idle_call+0x1e/0x40 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x1af/0x280 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355 rest_init+0xec/0xf6 init/main.c:452 arch_call_rest_init+0x17/0x37 start_kernel+0x838/0x85e init/main.c:786 x86_64_start_reservations+0x29/0x2b arch/x86/kernel/head64.c:490 x86_64_start_kernel+0x72/0x76 arch/x86/kernel/head64.c:471 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc6+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 ------------------------------------------------------------------------ This commit therefore replaces C-language assignments with WRITE_ONCE() in include/linux/list_nulls.h and include/linux/rculist_nulls.h. Reported-by: Eric Dumazet <edumazet@google.com> # For KCSAN Signed-off-by: Paul E. McKenney <paulmck@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
2019-11-09 09:42:13 -08:00
WRITE_ONCE(n->pprev, LIST_POISON2);
rcu: Introduce hlist_nulls variant of hlist hlist uses NULL value to finish a chain. hlist_nulls variant use the low order bit set to 1 to signal an end-of-list marker. This allows to store many different end markers, so that some RCU lockless algos (used in TCP/UDP stack for example) can save some memory barriers in fast paths. Two new files are added : include/linux/list_nulls.h - mimics hlist part of include/linux/list.h, derived to hlist_nulls variant include/linux/rculist_nulls.h - mimics hlist part of include/linux/rculist.h, derived to hlist_nulls variant Only four helpers are declared for the moment : hlist_nulls_del_init_rcu(), hlist_nulls_del_rcu(), hlist_nulls_add_head_rcu() and hlist_nulls_for_each_entry_rcu() prefetches() were removed, since an end of list is not anymore NULL value. prefetches() could trigger useless (and possibly dangerous) memory transactions. Example of use (extracted from __udp4_lib_lookup()) struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); unsigned int hash = udp_hashfn(net, hnum); struct udp_hslot *hslot = &udptable->hash[hash]; int score, badness; rcu_read_lock(); begin: result = NULL; badness = -1; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; } } /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (get_nulls_value(node) != hash) goto begin; if (result) { if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) result = NULL; else if (unlikely(compute_score(result, net, saddr, hnum, sport, daddr, dport, dif) < badness)) { sock_put(result); goto begin; } } rcu_read_unlock(); return result; Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-16 19:37:55 -08:00
}
/**
* hlist_nulls_add_head_rcu
* @n: the element to add to the hash list.
* @h: the list to add to.
*
* Description:
* Adds the specified element to the specified hlist_nulls,
* while permitting racing traversals.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
* or hlist_nulls_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
* problems on Alpha CPUs. Regardless of the type of CPU, the
* list-traversal primitive must be guarded by rcu_read_lock().
*/
static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
struct hlist_nulls_head *h)
{
struct hlist_nulls_node *first = h->first;
n->next = first;
rcu: Use WRITE_ONCE() for assignments to ->pprev for hlist_nulls [ Upstream commit 860c8802ace14c646864795e057349c9fb2d60ad ] Eric Dumazet supplied a KCSAN report of a bug that forces use of hlist_unhashed_lockless() from sk_unhashed(): ------------------------------------------------------------------------ BUG: KCSAN: data-race in inet_unhash / inet_unhash write to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 1: __hlist_nulls_del include/linux/list_nulls.h:88 [inline] hlist_nulls_del_init_rcu include/linux/rculist_nulls.h:36 [inline] __sk_nulls_del_node_init_rcu include/net/sock.h:676 [inline] inet_unhash+0x38f/0x4a0 net/ipv4/inet_hashtables.c:612 tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249 tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854 tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56 tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619 call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71 arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571 default_idle_call+0x1e/0x40 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x1af/0x280 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355 start_secondary+0x208/0x260 arch/x86/kernel/smpboot.c:264 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241 read to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 0: sk_unhashed include/net/sock.h:607 [inline] inet_unhash+0x3d/0x4a0 net/ipv4/inet_hashtables.c:592 tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249 tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854 tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56 tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619 call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71 arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571 default_idle_call+0x1e/0x40 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x1af/0x280 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355 rest_init+0xec/0xf6 init/main.c:452 arch_call_rest_init+0x17/0x37 start_kernel+0x838/0x85e init/main.c:786 x86_64_start_reservations+0x29/0x2b arch/x86/kernel/head64.c:490 x86_64_start_kernel+0x72/0x76 arch/x86/kernel/head64.c:471 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc6+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 ------------------------------------------------------------------------ This commit therefore replaces C-language assignments with WRITE_ONCE() in include/linux/list_nulls.h and include/linux/rculist_nulls.h. Reported-by: Eric Dumazet <edumazet@google.com> # For KCSAN Signed-off-by: Paul E. McKenney <paulmck@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
2019-11-09 09:42:13 -08:00
WRITE_ONCE(n->pprev, &h->first);
rcu_assign_pointer(hlist_nulls_first_rcu(h), n);
rcu: Introduce hlist_nulls variant of hlist hlist uses NULL value to finish a chain. hlist_nulls variant use the low order bit set to 1 to signal an end-of-list marker. This allows to store many different end markers, so that some RCU lockless algos (used in TCP/UDP stack for example) can save some memory barriers in fast paths. Two new files are added : include/linux/list_nulls.h - mimics hlist part of include/linux/list.h, derived to hlist_nulls variant include/linux/rculist_nulls.h - mimics hlist part of include/linux/rculist.h, derived to hlist_nulls variant Only four helpers are declared for the moment : hlist_nulls_del_init_rcu(), hlist_nulls_del_rcu(), hlist_nulls_add_head_rcu() and hlist_nulls_for_each_entry_rcu() prefetches() were removed, since an end of list is not anymore NULL value. prefetches() could trigger useless (and possibly dangerous) memory transactions. Example of use (extracted from __udp4_lib_lookup()) struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); unsigned int hash = udp_hashfn(net, hnum); struct udp_hslot *hslot = &udptable->hash[hash]; int score, badness; rcu_read_lock(); begin: result = NULL; badness = -1; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; } } /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (get_nulls_value(node) != hash) goto begin; if (result) { if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) result = NULL; else if (unlikely(compute_score(result, net, saddr, hnum, sport, daddr, dport, dif) < badness)) { sock_put(result); goto begin; } } rcu_read_unlock(); return result; Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-16 19:37:55 -08:00
if (!is_a_nulls(first))
rcu: Use WRITE_ONCE() for assignments to ->pprev for hlist_nulls [ Upstream commit 860c8802ace14c646864795e057349c9fb2d60ad ] Eric Dumazet supplied a KCSAN report of a bug that forces use of hlist_unhashed_lockless() from sk_unhashed(): ------------------------------------------------------------------------ BUG: KCSAN: data-race in inet_unhash / inet_unhash write to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 1: __hlist_nulls_del include/linux/list_nulls.h:88 [inline] hlist_nulls_del_init_rcu include/linux/rculist_nulls.h:36 [inline] __sk_nulls_del_node_init_rcu include/net/sock.h:676 [inline] inet_unhash+0x38f/0x4a0 net/ipv4/inet_hashtables.c:612 tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249 tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854 tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56 tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619 call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71 arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571 default_idle_call+0x1e/0x40 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x1af/0x280 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355 start_secondary+0x208/0x260 arch/x86/kernel/smpboot.c:264 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241 read to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 0: sk_unhashed include/net/sock.h:607 [inline] inet_unhash+0x3d/0x4a0 net/ipv4/inet_hashtables.c:592 tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249 tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854 tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56 tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619 call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71 arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571 default_idle_call+0x1e/0x40 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x1af/0x280 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355 rest_init+0xec/0xf6 init/main.c:452 arch_call_rest_init+0x17/0x37 start_kernel+0x838/0x85e init/main.c:786 x86_64_start_reservations+0x29/0x2b arch/x86/kernel/head64.c:490 x86_64_start_kernel+0x72/0x76 arch/x86/kernel/head64.c:471 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc6+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 ------------------------------------------------------------------------ This commit therefore replaces C-language assignments with WRITE_ONCE() in include/linux/list_nulls.h and include/linux/rculist_nulls.h. Reported-by: Eric Dumazet <edumazet@google.com> # For KCSAN Signed-off-by: Paul E. McKenney <paulmck@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
2019-11-09 09:42:13 -08:00
WRITE_ONCE(first->pprev, &n->next);
rcu: Introduce hlist_nulls variant of hlist hlist uses NULL value to finish a chain. hlist_nulls variant use the low order bit set to 1 to signal an end-of-list marker. This allows to store many different end markers, so that some RCU lockless algos (used in TCP/UDP stack for example) can save some memory barriers in fast paths. Two new files are added : include/linux/list_nulls.h - mimics hlist part of include/linux/list.h, derived to hlist_nulls variant include/linux/rculist_nulls.h - mimics hlist part of include/linux/rculist.h, derived to hlist_nulls variant Only four helpers are declared for the moment : hlist_nulls_del_init_rcu(), hlist_nulls_del_rcu(), hlist_nulls_add_head_rcu() and hlist_nulls_for_each_entry_rcu() prefetches() were removed, since an end of list is not anymore NULL value. prefetches() could trigger useless (and possibly dangerous) memory transactions. Example of use (extracted from __udp4_lib_lookup()) struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); unsigned int hash = udp_hashfn(net, hnum); struct udp_hslot *hslot = &udptable->hash[hash]; int score, badness; rcu_read_lock(); begin: result = NULL; badness = -1; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; } } /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (get_nulls_value(node) != hash) goto begin; if (result) { if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) result = NULL; else if (unlikely(compute_score(result, net, saddr, hnum, sport, daddr, dport, dif) < badness)) { sock_put(result); goto begin; } } rcu_read_unlock(); return result; Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-16 19:37:55 -08:00
}
soreuseport: fix ordering for mixed v4/v6 sockets With the SO_REUSEPORT socket option, it is possible to create sockets in the AF_INET and AF_INET6 domains which are bound to the same IPv4 address. This is only possible with SO_REUSEPORT and when not using IPV6_V6ONLY on the AF_INET6 sockets. Prior to the commits referenced below, an incoming IPv4 packet would always be routed to a socket of type AF_INET when this mixed-mode was used. After those changes, the same packet would be routed to the most recently bound socket (if this happened to be an AF_INET6 socket, it would have an IPv4 mapped IPv6 address). The change in behavior occurred because the recent SO_REUSEPORT optimizations short-circuit the socket scoring logic as soon as they find a match. They did not take into account the scoring logic that favors AF_INET sockets over AF_INET6 sockets in the event of a tie. To fix this problem, this patch changes the insertion order of AF_INET and AF_INET6 addresses in the TCP and UDP socket lists when the sockets have SO_REUSEPORT set. AF_INET sockets will be inserted at the head of the list and AF_INET6 sockets with SO_REUSEPORT set will always be inserted at the tail of the list. This will force AF_INET sockets to always be considered first. Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection") Fixes: 125e80b88687 ("soreuseport: fast reuseport TCP socket selection") Reported-by: Maciej Żenczykowski <maze@google.com> Signed-off-by: Craig Gallek <kraig@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-12 13:11:25 -04:00
/**
* hlist_nulls_add_tail_rcu
* @n: the element to add to the hash list.
* @h: the list to add to.
*
* Description:
* Adds the specified element to the specified hlist_nulls,
* while permitting racing traversals.
*
* The caller must take whatever precautions are necessary
* (such as holding appropriate locks) to avoid racing
* with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
* or hlist_nulls_del_rcu(), running on this same list.
* However, it is perfectly legal to run concurrently with
* the _rcu list-traversal primitives, such as
* hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
* problems on Alpha CPUs. Regardless of the type of CPU, the
* list-traversal primitive must be guarded by rcu_read_lock().
*/
static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
struct hlist_nulls_head *h)
{
struct hlist_nulls_node *i, *last = NULL;
/* Note: write side code, so rcu accessors are not needed. */
for (i = h->first; !is_a_nulls(i); i = i->next)
last = i;
if (last) {
n->next = last->next;
n->pprev = &last->next;
rcu_assign_pointer(hlist_next_rcu(last), n);
} else {
hlist_nulls_add_head_rcu(n, h);
}
}
rcu: Introduce hlist_nulls variant of hlist hlist uses NULL value to finish a chain. hlist_nulls variant use the low order bit set to 1 to signal an end-of-list marker. This allows to store many different end markers, so that some RCU lockless algos (used in TCP/UDP stack for example) can save some memory barriers in fast paths. Two new files are added : include/linux/list_nulls.h - mimics hlist part of include/linux/list.h, derived to hlist_nulls variant include/linux/rculist_nulls.h - mimics hlist part of include/linux/rculist.h, derived to hlist_nulls variant Only four helpers are declared for the moment : hlist_nulls_del_init_rcu(), hlist_nulls_del_rcu(), hlist_nulls_add_head_rcu() and hlist_nulls_for_each_entry_rcu() prefetches() were removed, since an end of list is not anymore NULL value. prefetches() could trigger useless (and possibly dangerous) memory transactions. Example of use (extracted from __udp4_lib_lookup()) struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); unsigned int hash = udp_hashfn(net, hnum); struct udp_hslot *hslot = &udptable->hash[hash]; int score, badness; rcu_read_lock(); begin: result = NULL; badness = -1; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; } } /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (get_nulls_value(node) != hash) goto begin; if (result) { if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) result = NULL; else if (unlikely(compute_score(result, net, saddr, hnum, sport, daddr, dport, dif) < badness)) { sock_put(result); goto begin; } } rcu_read_unlock(); return result; Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-16 19:37:55 -08:00
/**
* hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
* @tpos: the type * to use as a loop cursor.
* @pos: the &struct hlist_nulls_node to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the hlist_nulls_node within the struct.
*
* The barrier() is needed to make sure compiler doesn't cache first element [1],
* as this loop can be restarted [2]
* [1] Documentation/atomic_ops.txt around line 114
* [2] Documentation/RCU/rculist_nulls.txt around line 146
rcu: Introduce hlist_nulls variant of hlist hlist uses NULL value to finish a chain. hlist_nulls variant use the low order bit set to 1 to signal an end-of-list marker. This allows to store many different end markers, so that some RCU lockless algos (used in TCP/UDP stack for example) can save some memory barriers in fast paths. Two new files are added : include/linux/list_nulls.h - mimics hlist part of include/linux/list.h, derived to hlist_nulls variant include/linux/rculist_nulls.h - mimics hlist part of include/linux/rculist.h, derived to hlist_nulls variant Only four helpers are declared for the moment : hlist_nulls_del_init_rcu(), hlist_nulls_del_rcu(), hlist_nulls_add_head_rcu() and hlist_nulls_for_each_entry_rcu() prefetches() were removed, since an end of list is not anymore NULL value. prefetches() could trigger useless (and possibly dangerous) memory transactions. Example of use (extracted from __udp4_lib_lookup()) struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); unsigned int hash = udp_hashfn(net, hnum); struct udp_hslot *hslot = &udptable->hash[hash]; int score, badness; rcu_read_lock(); begin: result = NULL; badness = -1; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; } } /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (get_nulls_value(node) != hash) goto begin; if (result) { if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) result = NULL; else if (unlikely(compute_score(result, net, saddr, hnum, sport, daddr, dport, dif) < badness)) { sock_put(result); goto begin; } } rcu_read_unlock(); return result; Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-16 19:37:55 -08:00
*/
#define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \
for (({barrier();}), \
pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \
(!is_a_nulls(pos)) && \
rcu: Introduce hlist_nulls variant of hlist hlist uses NULL value to finish a chain. hlist_nulls variant use the low order bit set to 1 to signal an end-of-list marker. This allows to store many different end markers, so that some RCU lockless algos (used in TCP/UDP stack for example) can save some memory barriers in fast paths. Two new files are added : include/linux/list_nulls.h - mimics hlist part of include/linux/list.h, derived to hlist_nulls variant include/linux/rculist_nulls.h - mimics hlist part of include/linux/rculist.h, derived to hlist_nulls variant Only four helpers are declared for the moment : hlist_nulls_del_init_rcu(), hlist_nulls_del_rcu(), hlist_nulls_add_head_rcu() and hlist_nulls_for_each_entry_rcu() prefetches() were removed, since an end of list is not anymore NULL value. prefetches() could trigger useless (and possibly dangerous) memory transactions. Example of use (extracted from __udp4_lib_lookup()) struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); unsigned int hash = udp_hashfn(net, hnum); struct udp_hslot *hslot = &udptable->hash[hash]; int score, badness; rcu_read_lock(); begin: result = NULL; badness = -1; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; } } /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (get_nulls_value(node) != hash) goto begin; if (result) { if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) result = NULL; else if (unlikely(compute_score(result, net, saddr, hnum, sport, daddr, dport, dif) < badness)) { sock_put(result); goto begin; } } rcu_read_unlock(); return result; Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-16 19:37:55 -08:00
({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \
pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)))
rcu: Introduce hlist_nulls variant of hlist hlist uses NULL value to finish a chain. hlist_nulls variant use the low order bit set to 1 to signal an end-of-list marker. This allows to store many different end markers, so that some RCU lockless algos (used in TCP/UDP stack for example) can save some memory barriers in fast paths. Two new files are added : include/linux/list_nulls.h - mimics hlist part of include/linux/list.h, derived to hlist_nulls variant include/linux/rculist_nulls.h - mimics hlist part of include/linux/rculist.h, derived to hlist_nulls variant Only four helpers are declared for the moment : hlist_nulls_del_init_rcu(), hlist_nulls_del_rcu(), hlist_nulls_add_head_rcu() and hlist_nulls_for_each_entry_rcu() prefetches() were removed, since an end of list is not anymore NULL value. prefetches() could trigger useless (and possibly dangerous) memory transactions. Example of use (extracted from __udp4_lib_lookup()) struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); unsigned int hash = udp_hashfn(net, hnum); struct udp_hslot *hslot = &udptable->hash[hash]; int score, badness; rcu_read_lock(); begin: result = NULL; badness = -1; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; } } /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (get_nulls_value(node) != hash) goto begin; if (result) { if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) result = NULL; else if (unlikely(compute_score(result, net, saddr, hnum, sport, daddr, dport, dif) < badness)) { sock_put(result); goto begin; } } rcu_read_unlock(); return result; Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-16 19:37:55 -08:00
/**
* hlist_nulls_for_each_entry_safe -
* iterate over list of given type safe against removal of list entry
* @tpos: the type * to use as a loop cursor.
* @pos: the &struct hlist_nulls_node to use as a loop cursor.
* @head: the head for your list.
* @member: the name of the hlist_nulls_node within the struct.
*/
#define hlist_nulls_for_each_entry_safe(tpos, pos, head, member) \
for (({barrier();}), \
pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \
(!is_a_nulls(pos)) && \
({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); \
pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)); 1; });)
rcu: Introduce hlist_nulls variant of hlist hlist uses NULL value to finish a chain. hlist_nulls variant use the low order bit set to 1 to signal an end-of-list marker. This allows to store many different end markers, so that some RCU lockless algos (used in TCP/UDP stack for example) can save some memory barriers in fast paths. Two new files are added : include/linux/list_nulls.h - mimics hlist part of include/linux/list.h, derived to hlist_nulls variant include/linux/rculist_nulls.h - mimics hlist part of include/linux/rculist.h, derived to hlist_nulls variant Only four helpers are declared for the moment : hlist_nulls_del_init_rcu(), hlist_nulls_del_rcu(), hlist_nulls_add_head_rcu() and hlist_nulls_for_each_entry_rcu() prefetches() were removed, since an end of list is not anymore NULL value. prefetches() could trigger useless (and possibly dangerous) memory transactions. Example of use (extracted from __udp4_lib_lookup()) struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); unsigned int hash = udp_hashfn(net, hnum); struct udp_hslot *hslot = &udptable->hash[hash]; int score, badness; rcu_read_lock(); begin: result = NULL; badness = -1; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; } } /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (get_nulls_value(node) != hash) goto begin; if (result) { if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) result = NULL; else if (unlikely(compute_score(result, net, saddr, hnum, sport, daddr, dport, dif) < badness)) { sock_put(result); goto begin; } } rcu_read_unlock(); return result; Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-16 19:37:55 -08:00
#endif
#endif