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() ...
cpu_rmap.c
/*
* cpu_rmap.c: CPU affinity reverse-map support
* Copyright 2011 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation, incorporated herein by reference.
*/
#include <linux/cpu_rmap.h>
#include <linux/interrupt.h>
#include <linux/export.h>
/*
* These functions maintain a mapping from CPUs to some ordered set of
* objects with CPU affinities. This can be seen as a reverse-map of
* CPU affinity. However, we do not assume that the object affinities
* cover all CPUs in the system. For those CPUs not directly covered
* by object affinities, we attempt to find a nearest object based on
* CPU topology.
*/
/**
* alloc_cpu_rmap - allocate CPU affinity reverse-map
* @size: Number of objects to be mapped
* @flags: Allocation flags e.g. %GFP_KERNEL
*/
struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
{
struct cpu_rmap *rmap;
unsigned int cpu;
size_t obj_offset;
/* This is a silly number of objects, and we use u16 indices. */
if (size > 0xffff)
return NULL;
/* Offset of object pointer array from base structure */
obj_offset = ALIGN(offsetof(struct cpu_rmap, near[nr_cpu_ids]),
sizeof(void *));
rmap = kzalloc(obj_offset + size * sizeof(rmap->obj[0]), flags);
if (!rmap)
return NULL;
kref_init(&rmap->refcount);
rmap->obj = (void **)((char *)rmap + obj_offset);
/* Initially assign CPUs to objects on a rota, since we have
* no idea where the objects are. Use infinite distance, so
* any object with known distance is preferable. Include the
* CPUs that are not present/online, since we definitely want
* any newly-hotplugged CPUs to have some object assigned.
*/
for_each_possible_cpu(cpu) {
rmap->near[cpu].index = cpu % size;
rmap->near[cpu].dist = CPU_RMAP_DIST_INF;
}
rmap->size = size;
return rmap;
}
EXPORT_SYMBOL(alloc_cpu_rmap);
/**
* cpu_rmap_release - internal reclaiming helper called from kref_put
* @ref: kref to struct cpu_rmap
*/
static void cpu_rmap_release(struct kref *ref)
{
struct cpu_rmap *rmap = container_of(ref, struct cpu_rmap, refcount);
kfree(rmap);
}
/**
* cpu_rmap_get - internal helper to get new ref on a cpu_rmap
* @rmap: reverse-map allocated with alloc_cpu_rmap()
*/
static inline void cpu_rmap_get(struct cpu_rmap *rmap)
{
kref_get(&rmap->refcount);
}
/**
* cpu_rmap_put - release ref on a cpu_rmap
* @rmap: reverse-map allocated with alloc_cpu_rmap()
*/
int cpu_rmap_put(struct cpu_rmap *rmap)
{
return kref_put(&rmap->refcount, cpu_rmap_release);
}
EXPORT_SYMBOL(cpu_rmap_put);
/* Reevaluate nearest object for given CPU, comparing with the given
* neighbours at the given distance.
*/
static bool cpu_rmap_copy_neigh(struct cpu_rmap *rmap, unsigned int cpu,
const struct cpumask *mask, u16 dist)
{
int neigh;
for_each_cpu(neigh, mask) {
if (rmap->near[cpu].dist > dist &&
rmap->near[neigh].dist <= dist) {
rmap->near[cpu].index = rmap->near[neigh].index;
rmap->near[cpu].dist = dist;
return true;
}
}
return false;
}
#ifdef DEBUG
static void debug_print_rmap(const struct cpu_rmap *rmap, const char *prefix)
{
unsigned index;
unsigned int cpu;
pr_info("cpu_rmap %p, %s:\n", rmap, prefix);
for_each_possible_cpu(cpu) {
index = rmap->near[cpu].index;
pr_info("cpu %d -> obj %u (distance %u)\n",
cpu, index, rmap->near[cpu].dist);
}
}
#else
static inline void
debug_print_rmap(const struct cpu_rmap *rmap, const char *prefix)
{
}
#endif
/**
* cpu_rmap_add - add object to a rmap
* @rmap: CPU rmap allocated with alloc_cpu_rmap()
* @obj: Object to add to rmap
*
* Return index of object.
*/
int cpu_rmap_add(struct cpu_rmap *rmap, void *obj)
{
u16 index;
BUG_ON(rmap->used >= rmap->size);
index = rmap->used++;
rmap->obj[index] = obj;
return index;
}
EXPORT_SYMBOL(cpu_rmap_add);
/**
* cpu_rmap_update - update CPU rmap following a change of object affinity
* @rmap: CPU rmap to update
* @index: Index of object whose affinity changed
* @affinity: New CPU affinity of object
*/
int cpu_rmap_update(struct cpu_rmap *rmap, u16 index,
const struct cpumask *affinity)
{
cpumask_var_t update_mask;
unsigned int cpu;
if (unlikely(!zalloc_cpumask_var(&update_mask, GFP_KERNEL)))
return -ENOMEM;
/* Invalidate distance for all CPUs for which this used to be
* the nearest object. Mark those CPUs for update.
*/
for_each_online_cpu(cpu) {
if (rmap->near[cpu].index == index) {
rmap->near[cpu].dist = CPU_RMAP_DIST_INF;
cpumask_set_cpu(cpu, update_mask);
}
}
debug_print_rmap(rmap, "after invalidating old distances");
/* Set distance to 0 for all CPUs in the new affinity mask.
* Mark all CPUs within their NUMA nodes for update.
*/
for_each_cpu(cpu, affinity) {
rmap->near[cpu].index = index;
rmap->near[cpu].dist = 0;
cpumask_or(update_mask, update_mask,
cpumask_of_node(cpu_to_node(cpu)));
}
debug_print_rmap(rmap, "after updating neighbours");
/* Update distances based on topology */
for_each_cpu(cpu, update_mask) {
if (cpu_rmap_copy_neigh(rmap, cpu,
topology_sibling_cpumask(cpu), 1))
continue;
if (cpu_rmap_copy_neigh(rmap, cpu,
topology_core_cpumask(cpu), 2))
continue;
if (cpu_rmap_copy_neigh(rmap, cpu,
cpumask_of_node(cpu_to_node(cpu)), 3))
continue;
/* We could continue into NUMA node distances, but for now
* we give up.
*/
}
debug_print_rmap(rmap, "after copying neighbours");
free_cpumask_var(update_mask);
return 0;
}
EXPORT_SYMBOL(cpu_rmap_update);
/* Glue between IRQ affinity notifiers and CPU rmaps */
struct irq_glue {
struct irq_affinity_notify notify;
struct cpu_rmap *rmap;
u16 index;
};
/**
* free_irq_cpu_rmap - free a CPU affinity reverse-map used for IRQs
* @rmap: Reverse-map allocated with alloc_irq_cpu_map(), or %NULL
*
* Must be called in process context, before freeing the IRQs.
*/
void free_irq_cpu_rmap(struct cpu_rmap *rmap)
{
struct irq_glue *glue;
u16 index;
if (!rmap)
return;
for (index = 0; index < rmap->used; index++) {
glue = rmap->obj[index];
irq_set_affinity_notifier(glue->notify.irq, NULL);
}
cpu_rmap_put(rmap);
}
EXPORT_SYMBOL(free_irq_cpu_rmap);
/**
* irq_cpu_rmap_notify - callback for IRQ subsystem when IRQ affinity updated
* @notify: struct irq_affinity_notify passed by irq/manage.c
* @mask: cpu mask for new SMP affinity
*
* This is executed in workqueue context.
*/
static void
irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
{
struct irq_glue *glue =
container_of(notify, struct irq_glue, notify);
int rc;
rc = cpu_rmap_update(glue->rmap, glue->index, mask);
if (rc)
pr_warning("irq_cpu_rmap_notify: update failed: %d\n", rc);
}
/**
* irq_cpu_rmap_release - reclaiming callback for IRQ subsystem
* @ref: kref to struct irq_affinity_notify passed by irq/manage.c
*/
static void irq_cpu_rmap_release(struct kref *ref)
{
struct irq_glue *glue =
container_of(ref, struct irq_glue, notify.kref);
cpu_rmap_put(glue->rmap);
kfree(glue);
}
/**
* irq_cpu_rmap_add - add an IRQ to a CPU affinity reverse-map
* @rmap: The reverse-map
* @irq: The IRQ number
*
* This adds an IRQ affinity notifier that will update the reverse-map
* automatically.
*
* Must be called in process context, after the IRQ is allocated but
* before it is bound with request_irq().
*/
int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq)
{
struct irq_glue *glue = kzalloc(sizeof(*glue), GFP_KERNEL);
int rc;
if (!glue)
return -ENOMEM;
glue->notify.notify = irq_cpu_rmap_notify;
glue->notify.release = irq_cpu_rmap_release;
glue->rmap = rmap;
cpu_rmap_get(rmap);
glue->index = cpu_rmap_add(rmap, glue);
rc = irq_set_affinity_notifier(irq, &glue->notify);
if (rc) {
cpu_rmap_put(glue->rmap);
kfree(glue);
}
return rc;
}
EXPORT_SYMBOL(irq_cpu_rmap_add);
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...