Revision 1cbe06c3cf542d48eb22180163e00f91760ef8cd authored by Linus Torvalds on 28 May 2016, 18:04:16 UTC, committed by Linus Torvalds on 28 May 2016, 18:04:16 UTC
Pull more rdma updates from Doug Ledford: "This is the second group of code for the 4.7 merge window. It looks large, but only in one sense. I'll get to that in a minute. The list of changes here breaks down as follows: - Dynamic counter infrastructure in the IB drivers This is a sysfs based code to allow free form access to the hardware counters RDMA devices might support so drivers don't need to code this up repeatedly themselves - SendOnlyFullMember multicast support - IB router support - A couple misc fixes - The big item on the list: hfi1 driver updates, plus moving the hfi1 driver out of staging There was a group of 15 patches in the hfi1 list that I thought I had in the first pull request but they weren't. So that added to the length of the hfi1 section here. As far as these go, everything but the hfi1 is pretty straight forward. The hfi1 is, if you recall, the driver that Al had complaints about how it used the write/writev interfaces in an overloaded fashion. The write portion of their interface behaved like the write handler in the IB stack proper and did bi-directional communications. The writev interface, on the other hand, only accepts SDMA request structures. The completions for those structures are sent back via an entirely different event mechanism. With the security patch, we put security checks on the write interface, however, we also knew they would be going away soon. Now, we've converted the write handler in the hfi1 driver to use ioctls from the IB reserved magic area for its bidirectional communications. With that change, Intel has addressed all of the items originally on their TODO when they went into staging (as well as many items added to the list later). As such, I moved them out, and since they were the last item in the staging/rdma directory, and I don't have immediate plans to use the staging area again, I removed the staging/rdma area. Because of the move out of staging, as well as a series of 5 patches in the hfi1 driver that removed code people thought should be done in a different way and was optional to begin with (a snoop debug interface, an eeprom driver for an eeprom connected directory to their hfi1 chip and not via an i2c bus, and a few other things like that), the line count, especially the removal count, is high" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (56 commits) staging/rdma: Remove the entire rdma subdirectory of staging IB/core: Make device counter infrastructure dynamic IB/hfi1: Fix pio map initialization IB/hfi1: Correct 8051 link parameter settings IB/hfi1: Update pkey table properly after link down or FM start IB/rdamvt: Fix rdmavt s_ack_queue sizing IB/rdmavt: Max atomic value should be a u8 IB/hfi1: Fix hard lockup due to not using save/restore spin lock IB/hfi1: Add tracing support for send with invalidate opcode IB/hfi1, qib: Add ieth to the packet header definitions IB/hfi1: Move driver out of staging IB/hfi1: Do not free hfi1 cdev parent structure early IB/hfi1: Add trace message in user IOCTL handling IB/hfi1: Remove write(), use ioctl() for user cmds IB/hfi1: Add ioctl() interface for user commands IB/hfi1: Remove unused user command IB/hfi1: Remove snoop/diag interface IB/hfi1: Remove EPROM functionality from data device IB/hfi1: Remove UI char device IB/hfi1: Remove multiple device cdev ...
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 ...