Revision 8700aff089843399f95bc7701ae87b642b35a716 authored by Edward Cree on 20 December 2019, 16:26:40 UTC, committed by David S. Miller on 21 December 2019, 05:56:48 UTC
It was possible for channel allocation logic to get confused between what
 it had and what it wanted, and end up trying to use the same channel for
 both PTP and regular TX.  This led to a kernel panic:
    BUG: unable to handle page fault for address: 0000000000047635
    #PF: supervisor write access in kernel mode
    #PF: error_code(0x0002) - not-present page
    PGD 0 P4D 0
    Oops: 0002 [#1] SMP PTI
    CPU: 0 PID: 0 Comm: swapper/0 Tainted: G        W         5.4.0-rc3-ehc14+ #900
    Hardware name: Dell Inc. PowerEdge R710/0M233H, BIOS 6.4.0 07/23/2013
    RIP: 0010:native_queued_spin_lock_slowpath+0x188/0x1e0
    Code: f3 90 48 8b 32 48 85 f6 74 f6 eb e8 c1 ee 12 83 e0 03 83 ee 01 48 c1 e0 05 48 63 f6 48 05 c0 98 02 00 48 03 04 f5 a0 c6 ed 81 <48> 89 10 8b 42 08 85 c0 75 09 f3 90 8b 42 08 85 c0 74 f7 48 8b 32
    RSP: 0018:ffffc90000003d28 EFLAGS: 00010006
    RAX: 0000000000047635 RBX: 0000000000000246 RCX: 0000000000040000
    RDX: ffff888627a298c0 RSI: 0000000000003ffe RDI: ffff88861f6b8dd4
    RBP: ffff8886225c6e00 R08: 0000000000040000 R09: 0000000000000000
    R10: 0000000616f080c6 R11: 00000000000000c0 R12: ffff88861f6b8dd4
    R13: ffffc90000003dc8 R14: ffff88861942bf00 R15: ffff8886150f2000
    FS:  0000000000000000(0000) GS:ffff888627a00000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: 0000000000047635 CR3: 000000000200a000 CR4: 00000000000006f0
    Call Trace:
     <IRQ>
     _raw_spin_lock_irqsave+0x22/0x30
     skb_queue_tail+0x1b/0x50
     sock_queue_err_skb+0x9d/0xf0
     __skb_complete_tx_timestamp+0x9d/0xc0
     efx_dequeue_buffer+0x126/0x180 [sfc]
     efx_xmit_done+0x73/0x1c0 [sfc]
     efx_ef10_ev_process+0x56a/0xfe0 [sfc]
     ? tick_sched_do_timer+0x60/0x60
     ? timerqueue_add+0x5d/0x70
     ? enqueue_hrtimer+0x39/0x90
     efx_poll+0x111/0x380 [sfc]
     ? rcu_accelerate_cbs+0x50/0x160
     net_rx_action+0x14a/0x400
     __do_softirq+0xdd/0x2d0
     irq_exit+0xa0/0xb0
     do_IRQ+0x53/0xe0
     common_interrupt+0xf/0xf
     </IRQ>

In the long run we intend to rewrite the channel allocation code, but for
 'net' fix this by allocating extra_channels, and giving them TX queues,
 even if we do not in fact need them (e.g. on NICs without MAC TX
 timestamping), and thereby using simpler logic to assign the channels
 once they're allocated.

Fixes: 3990a8fffbda ("sfc: allocate channels for XDP tx queues")
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent 258a980
Raw File
blk-cgroup-rwstat.h
/* SPDX-License-Identifier: GPL-2.0
 *
 * Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT.
 * Do not use in new code.
 */
#ifndef _BLK_CGROUP_RWSTAT_H
#define _BLK_CGROUP_RWSTAT_H

#include <linux/blk-cgroup.h>

enum blkg_rwstat_type {
	BLKG_RWSTAT_READ,
	BLKG_RWSTAT_WRITE,
	BLKG_RWSTAT_SYNC,
	BLKG_RWSTAT_ASYNC,
	BLKG_RWSTAT_DISCARD,

	BLKG_RWSTAT_NR,
	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
};

/*
 * blkg_[rw]stat->aux_cnt is excluded for local stats but included for
 * recursive.  Used to carry stats of dead children.
 */
struct blkg_rwstat {
	struct percpu_counter		cpu_cnt[BLKG_RWSTAT_NR];
	atomic64_t			aux_cnt[BLKG_RWSTAT_NR];
};

struct blkg_rwstat_sample {
	u64				cnt[BLKG_RWSTAT_NR];
};

static inline u64 blkg_rwstat_read_counter(struct blkg_rwstat *rwstat,
		unsigned int idx)
{
	return atomic64_read(&rwstat->aux_cnt[idx]) +
		percpu_counter_sum_positive(&rwstat->cpu_cnt[idx]);
}

int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp);
void blkg_rwstat_exit(struct blkg_rwstat *rwstat);
u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
			 const struct blkg_rwstat_sample *rwstat);
u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
		       int off);
void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
		int off, struct blkg_rwstat_sample *sum);


/**
 * blkg_rwstat_add - add a value to a blkg_rwstat
 * @rwstat: target blkg_rwstat
 * @op: REQ_OP and flags
 * @val: value to add
 *
 * Add @val to @rwstat.  The counters are chosen according to @rw.  The
 * caller is responsible for synchronizing calls to this function.
 */
static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
				   unsigned int op, uint64_t val)
{
	struct percpu_counter *cnt;

	if (op_is_discard(op))
		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD];
	else if (op_is_write(op))
		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE];
	else
		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];

	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);

	if (op_is_sync(op))
		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC];
	else
		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC];

	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
}

/**
 * blkg_rwstat_read - read the current values of a blkg_rwstat
 * @rwstat: blkg_rwstat to read
 *
 * Read the current snapshot of @rwstat and return it in the aux counts.
 */
static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat,
		struct blkg_rwstat_sample *result)
{
	int i;

	for (i = 0; i < BLKG_RWSTAT_NR; i++)
		result->cnt[i] =
			percpu_counter_sum_positive(&rwstat->cpu_cnt[i]);
}

/**
 * blkg_rwstat_total - read the total count of a blkg_rwstat
 * @rwstat: blkg_rwstat to read
 *
 * Return the total count of @rwstat regardless of the IO direction.  This
 * function can be called without synchronization and takes care of u64
 * atomicity.
 */
static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat)
{
	struct blkg_rwstat_sample tmp = { };

	blkg_rwstat_read(rwstat, &tmp);
	return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE];
}

/**
 * blkg_rwstat_reset - reset a blkg_rwstat
 * @rwstat: blkg_rwstat to reset
 */
static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat)
{
	int i;

	for (i = 0; i < BLKG_RWSTAT_NR; i++) {
		percpu_counter_set(&rwstat->cpu_cnt[i], 0);
		atomic64_set(&rwstat->aux_cnt[i], 0);
	}
}

/**
 * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count
 * @to: the destination blkg_rwstat
 * @from: the source
 *
 * Add @from's count including the aux one to @to's aux count.
 */
static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to,
				       struct blkg_rwstat *from)
{
	u64 sum[BLKG_RWSTAT_NR];
	int i;

	for (i = 0; i < BLKG_RWSTAT_NR; i++)
		sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]);

	for (i = 0; i < BLKG_RWSTAT_NR; i++)
		atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]),
			     &to->aux_cnt[i]);
}
#endif	/* _BLK_CGROUP_RWSTAT_H */
back to top