Revision c4a86165d1ec70c8e592fa7b7cc7070971533021 authored by Linus Torvalds on 14 October 2016, 04:28:20 UTC, committed by Linus Torvalds on 14 October 2016, 04:28:20 UTC
Pull NFS client updates from Anna Schumaker: "Highlights include: Stable bugfixes: - sunrpc: fix writ espace race causing stalls - NFS: Fix inode corruption in nfs_prime_dcache() - NFSv4: Don't report revoked delegations as valid in nfs_have_delegation() - NFSv4: nfs4_copy_delegation_stateid() must fail if the delegation is invalid - NFSv4: Open state recovery must account for file permission changes - NFSv4.2: Fix a reference leak in nfs42_proc_layoutstats_generic Features: - Add support for tracking multiple layout types with an ordered list - Add support for using multiple backchannel threads on the client - Add support for pNFS file layout session trunking - Delay xprtrdma use of DMA API (for device driver removal) - Add support for xprtrdma remote invalidation - Add support for larger xprtrdma inline thresholds - Use a scatter/gather list for sending xprtrdma RPC calls - Add support for the CB_NOTIFY_LOCK callback - Improve hashing sunrpc auth_creds by using both uid and gid Bugfixes: - Fix xprtrdma use of DMA API - Validate filenames before adding to the dcache - Fix corruption of xdr->nwords in xdr_copy_to_scratch - Fix setting buffer length in xdr_set_next_buffer() - Don't deadlock the state manager on the SEQUENCE status flags - Various delegation and stateid related fixes - Retry operations if an interrupted slot receives EREMOTEIO - Make nfs boot time y2038 safe" * tag 'nfs-for-4.9-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (100 commits) NFSv4.2: Fix a reference leak in nfs42_proc_layoutstats_generic fs: nfs: Make nfs boot time y2038 safe sunrpc: replace generic auth_cred hash with auth-specific function sunrpc: add RPCSEC_GSS hash_cred() function sunrpc: add auth_unix hash_cred() function sunrpc: add generic_auth hash_cred() function sunrpc: add hash_cred() function to rpc_authops struct Retry operation on EREMOTEIO on an interrupted slot pNFS: Fix atime updates on pNFS clients sunrpc: queue work on system_power_efficient_wq NFSv4.1: Even if the stateid is OK, we may need to recover the open modes NFSv4: If recovery failed for a specific open stateid, then don't retry NFSv4: Fix retry issues with nfs41_test/free_stateid NFSv4: Open state recovery must account for file permission changes NFSv4: Mark the lock and open stateids as invalid after freeing them NFSv4: Don't test open_stateid unless it is set NFSv4: nfs4_do_handle_exception() handle revoke/expiry of a single stateid NFS: Always call nfs_inode_find_state_and_recover() when revoking a delegation NFSv4: Fix a race when updating an open_stateid NFSv4: Fix a race in nfs_inode_reclaim_delegation() ...
flex_proportions.c
/*
* Floating proportions with flexible aging period
*
* Copyright (C) 2011, SUSE, Jan Kara <jack@suse.cz>
*
* The goal of this code is: Given different types of event, measure proportion
* of each type of event over time. The proportions are measured with
* exponentially decaying history to give smooth transitions. A formula
* expressing proportion of event of type 'j' is:
*
* p_{j} = (\Sum_{i>=0} x_{i,j}/2^{i+1})/(\Sum_{i>=0} x_i/2^{i+1})
*
* Where x_{i,j} is j's number of events in i-th last time period and x_i is
* total number of events in i-th last time period.
*
* Note that p_{j}'s are normalised, i.e.
*
* \Sum_{j} p_{j} = 1,
*
* This formula can be straightforwardly computed by maintaining denominator
* (let's call it 'd') and for each event type its numerator (let's call it
* 'n_j'). When an event of type 'j' happens, we simply need to do:
* n_j++; d++;
*
* When a new period is declared, we could do:
* d /= 2
* for each j
* n_j /= 2
*
* To avoid iteration over all event types, we instead shift numerator of event
* j lazily when someone asks for a proportion of event j or when event j
* occurs. This can bit trivially implemented by remembering last period in
* which something happened with proportion of type j.
*/
#include <linux/flex_proportions.h>
int fprop_global_init(struct fprop_global *p, gfp_t gfp)
{
int err;
p->period = 0;
/* Use 1 to avoid dealing with periods with 0 events... */
err = percpu_counter_init(&p->events, 1, gfp);
if (err)
return err;
seqcount_init(&p->sequence);
return 0;
}
void fprop_global_destroy(struct fprop_global *p)
{
percpu_counter_destroy(&p->events);
}
/*
* Declare @periods new periods. It is upto the caller to make sure period
* transitions cannot happen in parallel.
*
* The function returns true if the proportions are still defined and false
* if aging zeroed out all events. This can be used to detect whether declaring
* further periods has any effect.
*/
bool fprop_new_period(struct fprop_global *p, int periods)
{
s64 events;
unsigned long flags;
local_irq_save(flags);
events = percpu_counter_sum(&p->events);
/*
* Don't do anything if there are no events.
*/
if (events <= 1) {
local_irq_restore(flags);
return false;
}
write_seqcount_begin(&p->sequence);
if (periods < 64)
events -= events >> periods;
/* Use addition to avoid losing events happening between sum and set */
percpu_counter_add(&p->events, -events);
p->period += periods;
write_seqcount_end(&p->sequence);
local_irq_restore(flags);
return true;
}
/*
* ---- SINGLE ----
*/
int fprop_local_init_single(struct fprop_local_single *pl)
{
pl->events = 0;
pl->period = 0;
raw_spin_lock_init(&pl->lock);
return 0;
}
void fprop_local_destroy_single(struct fprop_local_single *pl)
{
}
static void fprop_reflect_period_single(struct fprop_global *p,
struct fprop_local_single *pl)
{
unsigned int period = p->period;
unsigned long flags;
/* Fast path - period didn't change */
if (pl->period == period)
return;
raw_spin_lock_irqsave(&pl->lock, flags);
/* Someone updated pl->period while we were spinning? */
if (pl->period >= period) {
raw_spin_unlock_irqrestore(&pl->lock, flags);
return;
}
/* Aging zeroed our fraction? */
if (period - pl->period < BITS_PER_LONG)
pl->events >>= period - pl->period;
else
pl->events = 0;
pl->period = period;
raw_spin_unlock_irqrestore(&pl->lock, flags);
}
/* Event of type pl happened */
void __fprop_inc_single(struct fprop_global *p, struct fprop_local_single *pl)
{
fprop_reflect_period_single(p, pl);
pl->events++;
percpu_counter_add(&p->events, 1);
}
/* Return fraction of events of type pl */
void fprop_fraction_single(struct fprop_global *p,
struct fprop_local_single *pl,
unsigned long *numerator, unsigned long *denominator)
{
unsigned int seq;
s64 num, den;
do {
seq = read_seqcount_begin(&p->sequence);
fprop_reflect_period_single(p, pl);
num = pl->events;
den = percpu_counter_read_positive(&p->events);
} while (read_seqcount_retry(&p->sequence, seq));
/*
* Make fraction <= 1 and denominator > 0 even in presence of percpu
* counter errors
*/
if (den <= num) {
if (num)
den = num;
else
den = 1;
}
*denominator = den;
*numerator = num;
}
/*
* ---- PERCPU ----
*/
#define PROP_BATCH (8*(1+ilog2(nr_cpu_ids)))
int fprop_local_init_percpu(struct fprop_local_percpu *pl, gfp_t gfp)
{
int err;
err = percpu_counter_init(&pl->events, 0, gfp);
if (err)
return err;
pl->period = 0;
raw_spin_lock_init(&pl->lock);
return 0;
}
void fprop_local_destroy_percpu(struct fprop_local_percpu *pl)
{
percpu_counter_destroy(&pl->events);
}
static void fprop_reflect_period_percpu(struct fprop_global *p,
struct fprop_local_percpu *pl)
{
unsigned int period = p->period;
unsigned long flags;
/* Fast path - period didn't change */
if (pl->period == period)
return;
raw_spin_lock_irqsave(&pl->lock, flags);
/* Someone updated pl->period while we were spinning? */
if (pl->period >= period) {
raw_spin_unlock_irqrestore(&pl->lock, flags);
return;
}
/* Aging zeroed our fraction? */
if (period - pl->period < BITS_PER_LONG) {
s64 val = percpu_counter_read(&pl->events);
if (val < (nr_cpu_ids * PROP_BATCH))
val = percpu_counter_sum(&pl->events);
__percpu_counter_add(&pl->events,
-val + (val >> (period-pl->period)), PROP_BATCH);
} else
percpu_counter_set(&pl->events, 0);
pl->period = period;
raw_spin_unlock_irqrestore(&pl->lock, flags);
}
/* Event of type pl happened */
void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl)
{
fprop_reflect_period_percpu(p, pl);
__percpu_counter_add(&pl->events, 1, PROP_BATCH);
percpu_counter_add(&p->events, 1);
}
void fprop_fraction_percpu(struct fprop_global *p,
struct fprop_local_percpu *pl,
unsigned long *numerator, unsigned long *denominator)
{
unsigned int seq;
s64 num, den;
do {
seq = read_seqcount_begin(&p->sequence);
fprop_reflect_period_percpu(p, pl);
num = percpu_counter_read_positive(&pl->events);
den = percpu_counter_read_positive(&p->events);
} while (read_seqcount_retry(&p->sequence, seq));
/*
* Make fraction <= 1 and denominator > 0 even in presence of percpu
* counter errors
*/
if (den <= num) {
if (num)
den = num;
else
den = 1;
}
*denominator = den;
*numerator = num;
}
/*
* Like __fprop_inc_percpu() except that event is counted only if the given
* type has fraction smaller than @max_frac/FPROP_FRAC_BASE
*/
void __fprop_inc_percpu_max(struct fprop_global *p,
struct fprop_local_percpu *pl, int max_frac)
{
if (unlikely(max_frac < FPROP_FRAC_BASE)) {
unsigned long numerator, denominator;
fprop_fraction_percpu(p, pl, &numerator, &denominator);
if (numerator >
(((u64)denominator) * max_frac) >> FPROP_FRAC_SHIFT)
return;
} else
fprop_reflect_period_percpu(p, pl);
__percpu_counter_add(&pl->events, 1, PROP_BATCH);
percpu_counter_add(&p->events, 1);
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...