/*
 * linux/net/sunrpc/timer.c
 *
 * Estimate RPC request round trip time.
 *
 * Based on packet round-trip and variance estimator algorithms described
 * in appendix A of "Congestion Avoidance and Control" by Van Jacobson
 * and Michael J. Karels (ACM Computer Communication Review; Proceedings
 * of the Sigcomm '88 Symposium in Stanford, CA, August, 1988).
 *
 * This RTT estimator is used only for RPC over datagram protocols.
 *
 * Copyright (C) 2002 Trond Myklebust <trond.myklebust@fys.uio.no>
 */

#include <asm/param.h>

#include <linux/types.h>
#include <linux/unistd.h>
#include <linux/module.h>

#include <linux/sunrpc/clnt.h>

#define RPC_RTO_MAX (60*HZ)
#define RPC_RTO_INIT (HZ/5)
#define RPC_RTO_MIN (HZ/10)

/**
 * rpc_init_rtt - Initialize an RPC RTT estimator context
 * @rt: context to initialize
 * @timeo: initial timeout value, in jiffies
 *
 */
void rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo)
{
	unsigned long init = 0;
	unsigned int i;

	rt->timeo = timeo;

	if (timeo > RPC_RTO_INIT)
		init = (timeo - RPC_RTO_INIT) << 3;
	for (i = 0; i < 5; i++) {
		rt->srtt[i] = init;
		rt->sdrtt[i] = RPC_RTO_INIT;
		rt->ntimeouts[i] = 0;
	}
}
EXPORT_SYMBOL_GPL(rpc_init_rtt);

/**
 * rpc_update_rtt - Update an RPC RTT estimator context
 * @rt: context to update
 * @timer: timer array index (request type)
 * @m: recent actual RTT, in jiffies
 *
 * NB: When computing the smoothed RTT and standard deviation,
 *     be careful not to produce negative intermediate results.
 */
void rpc_update_rtt(struct rpc_rtt *rt, unsigned int timer, long m)
{
	long *srtt, *sdrtt;

	if (timer-- == 0)
		return;

	/* jiffies wrapped; ignore this one */
	if (m < 0)
		return;

	if (m == 0)
		m = 1L;

	srtt = (long *)&rt->srtt[timer];
	m -= *srtt >> 3;
	*srtt += m;

	if (m < 0)
		m = -m;

	sdrtt = (long *)&rt->sdrtt[timer];
	m -= *sdrtt >> 2;
	*sdrtt += m;

	/* Set lower bound on the variance */
	if (*sdrtt < RPC_RTO_MIN)
		*sdrtt = RPC_RTO_MIN;
}
EXPORT_SYMBOL_GPL(rpc_update_rtt);

/**
 * rpc_calc_rto - Provide an estimated timeout value
 * @rt: context to use for calculation
 * @timer: timer array index (request type)
 *
 * Estimate RTO for an NFS RPC sent via an unreliable datagram.  Use
 * the mean and mean deviation of RTT for the appropriate type of RPC
 * for frequently issued RPCs, and a fixed default for the others.
 *
 * The justification for doing "other" this way is that these RPCs
 * happen so infrequently that timer estimation would probably be
 * stale.  Also, since many of these RPCs are non-idempotent, a
 * conservative timeout is desired.
 *
 * getattr, lookup,
 * read, write, commit     - A+4D
 * other                   - timeo
 */
unsigned long rpc_calc_rto(struct rpc_rtt *rt, unsigned int timer)
{
	unsigned long res;

	if (timer-- == 0)
		return rt->timeo;

	res = ((rt->srtt[timer] + 7) >> 3) + rt->sdrtt[timer];
	if (res > RPC_RTO_MAX)
		res = RPC_RTO_MAX;

	return res;
}
EXPORT_SYMBOL_GPL(rpc_calc_rto);
</a></div><div class='content'><div class='cgit-panel'><b>diff options</b><form method='get'><input type='hidden' name='id' value='966d2b04e070bc040319aaebfec09e0144dc3341'/><table><tr><td colspan='2'/></tr><tr><td class='label'>context:</td><td class='ctrl'><select name='context' onchange='this.form.submit();'><option value='1'>1</option><option value='2'>2</option><option value='3' selected='selected'>3</option><option value='4'>4</option><option value='5'>5</option><option value='6'>6</option><option value='7'>7</option><option value='8'>8</option><option value='9'>9</option><option value='10'>10</option><option value='15'>15</option><option value='20'>20</option><option value='25'>25</option><option value='30'>30</option><option value='35'>35</option><option value='40'>40</option></select></td></tr><tr><td class='label'>space:</td><td class='ctrl'><select name='ignorews' onchange='this.form.submit();'><option value='0' selected='selected'>include</option><option value='1'>ignore</option></select></td></tr><tr><td class='label'>mode:</td><td class='ctrl'><select name='dt' onchange='this.form.submit();'><option value='0' selected='selected'>unified</option><option value='1'>ssdiff</option><option value='2'>stat only</option></select></td></tr><tr><td/><td class='ctrl'><noscript><input type='submit' value='reload'/></noscript></td></tr></table></form></div><table summary='commit info' class='commit-info'>
<tr><th>author</th><td>Douglas Miller &lt;dougmill@linux.vnet.ibm.com&gt;</td><td class='right'>2017-01-28 06:42:20 -0600</td></tr>
<tr><th>committer</th><td>Tejun Heo &lt;tj@kernel.org&gt;</td><td class='right'>2017-01-28 07:49:42 -0500</td></tr>
<tr><th>commit</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/commit/net/strparser?id=966d2b04e070bc040319aaebfec09e0144dc3341'>966d2b04e070bc040319aaebfec09e0144dc3341</a> (<a href='/cgit.cgi/linux/net-next.git/patch/net/strparser?id=966d2b04e070bc040319aaebfec09e0144dc3341'>patch</a>)</td></tr>
<tr><th>tree</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/tree/?id=966d2b04e070bc040319aaebfec09e0144dc3341'>4b96156e3d1dd4dfd6039b7c219c9dc4616da52d</a> /<a href='/cgit.cgi/linux/net-next.git/tree/net/strparser?id=966d2b04e070bc040319aaebfec09e0144dc3341'>net/strparser</a></td></tr>
<tr><th>parent</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/commit/net/strparser?id=1b1bc42c1692e9b62756323c675a44cb1a1f9dbd'>1b1bc42c1692e9b62756323c675a44cb1a1f9dbd</a> (<a href='/cgit.cgi/linux/net-next.git/diff/net/strparser?id=966d2b04e070bc040319aaebfec09e0144dc3341&amp;id2=1b1bc42c1692e9b62756323c675a44cb1a1f9dbd'>diff</a>)</td></tr></table>
<div class='commit-subject'>percpu-refcount: fix reference leak during percpu-atomic transition</div><div class='commit-msg'>percpu_ref_tryget() and percpu_ref_tryget_live() should return
"true" IFF they acquire a reference. But the return value from
atomic_long_inc_not_zero() is a long and may have high bits set,
e.g. PERCPU_COUNT_BIAS, and the return value of the tryget routines
is bool so the reference may actually be acquired but the routines
return "false" which results in a reference leak since the caller
assumes it does not need to do a corresponding percpu_ref_put().

This was seen when performing CPU hotplug during I/O, as hangs in
blk_mq_freeze_queue_wait where percpu_ref_kill (blk_mq_freeze_queue_start)
raced with percpu_ref_tryget (blk_mq_timeout_work).
Sample stack trace:

__switch_to+0x2c0/0x450
__schedule+0x2f8/0x970
schedule+0x48/0xc0
blk_mq_freeze_queue_wait+0x94/0x120
blk_mq_queue_reinit_work+0xb8/0x180
blk_mq_queue_reinit_prepare+0x84/0xa0
cpuhp_invoke_callback+0x17c/0x600
cpuhp_up_callbacks+0x58/0x150
_cpu_up+0xf0/0x1c0
do_cpu_up+0x120/0x150
cpu_subsys_online+0x64/0xe0
device_online+0xb4/0x120
online_store+0xb4/0xc0
dev_attr_store+0x68/0xa0
sysfs_kf_write+0x80/0xb0
kernfs_fop_write+0x17c/0x250
__vfs_write+0x6c/0x1e0
vfs_write+0xd0/0x270
SyS_write+0x6c/0x110
system_call+0x38/0xe0

Examination of the queue showed a single reference (no PERCPU_COUNT_BIAS,
and __PERCPU_REF_DEAD, __PERCPU_REF_ATOMIC set) and no requests.
However, conditions at the time of the race are count of PERCPU_COUNT_BIAS + 0
and __PERCPU_REF_DEAD and __PERCPU_REF_ATOMIC set.

The fix is to make the tryget routines use an actual boolean internally instead
of the atomic long result truncated to a int.

Fixes: e625305b3907 percpu-refcount: make percpu_ref based on longs instead of ints
Link: https://bugzilla.kernel.org/show_bug.cgi?id=190751
Signed-off-by: Douglas Miller &lt;dougmill@linux.vnet.ibm.com&gt;
Reviewed-by: Jens Axboe &lt;axboe@fb.com&gt;
Signed-off-by: Tejun Heo &lt;tj@kernel.org&gt;
Fixes: e625305b3907 ("percpu-refcount: make percpu_ref based on longs instead of ints")
Cc: stable@vger.kernel.org # v3.18+
</div><div class='diffstat-header'><a href='/cgit.cgi/linux/net-next.git/diff/?id=966d2b04e070bc040319aaebfec09e0144dc3341'>Diffstat</a> (limited to 'net/strparser')</div><table summary='diffstat' class='diffstat'>