linux/net/xdp/xdp_umem.c
Michel Lespinasse d8ed45c5dc mmap locking API: use coccinelle to convert mmap_sem rwsem call sites
This change converts the existing mmap_sem rwsem calls to use the new mmap
locking API instead.

The change is generated using coccinelle with the following rule:

// spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir .

@@
expression mm;
@@
(
-init_rwsem
+mmap_init_lock
|
-down_write
+mmap_write_lock
|
-down_write_killable
+mmap_write_lock_killable
|
-down_write_trylock
+mmap_write_trylock
|
-up_write
+mmap_write_unlock
|
-downgrade_write
+mmap_write_downgrade
|
-down_read
+mmap_read_lock
|
-down_read_killable
+mmap_read_lock_killable
|
-down_read_trylock
+mmap_read_trylock
|
-up_read
+mmap_read_unlock
)
-(&mm->mmap_sem)
+(mm)

Signed-off-by: Michel Lespinasse <walken@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Liam Howlett <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ying Han <yinghan@google.com>
Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 09:39:14 -07:00

421 lines
8.7 KiB
C

// SPDX-License-Identifier: GPL-2.0
/* XDP user-space packet buffer
* Copyright(c) 2018 Intel Corporation.
*/
#include <linux/init.h>
#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/uaccess.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/mm.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/idr.h>
#include <linux/vmalloc.h>
#include "xdp_umem.h"
#include "xsk_queue.h"
#define XDP_UMEM_MIN_CHUNK_SIZE 2048
static DEFINE_IDA(umem_ida);
void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
{
unsigned long flags;
if (!xs->tx)
return;
spin_lock_irqsave(&umem->xsk_tx_list_lock, flags);
list_add_rcu(&xs->list, &umem->xsk_tx_list);
spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags);
}
void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
{
unsigned long flags;
if (!xs->tx)
return;
spin_lock_irqsave(&umem->xsk_tx_list_lock, flags);
list_del_rcu(&xs->list);
spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags);
}
/* The umem is stored both in the _rx struct and the _tx struct as we do
* not know if the device has more tx queues than rx, or the opposite.
* This might also change during run time.
*/
static int xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem,
u16 queue_id)
{
if (queue_id >= max_t(unsigned int,
dev->real_num_rx_queues,
dev->real_num_tx_queues))
return -EINVAL;
if (queue_id < dev->real_num_rx_queues)
dev->_rx[queue_id].umem = umem;
if (queue_id < dev->real_num_tx_queues)
dev->_tx[queue_id].umem = umem;
return 0;
}
struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
u16 queue_id)
{
if (queue_id < dev->real_num_rx_queues)
return dev->_rx[queue_id].umem;
if (queue_id < dev->real_num_tx_queues)
return dev->_tx[queue_id].umem;
return NULL;
}
EXPORT_SYMBOL(xdp_get_umem_from_qid);
static void xdp_clear_umem_at_qid(struct net_device *dev, u16 queue_id)
{
if (queue_id < dev->real_num_rx_queues)
dev->_rx[queue_id].umem = NULL;
if (queue_id < dev->real_num_tx_queues)
dev->_tx[queue_id].umem = NULL;
}
int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
u16 queue_id, u16 flags)
{
bool force_zc, force_copy;
struct netdev_bpf bpf;
int err = 0;
ASSERT_RTNL();
force_zc = flags & XDP_ZEROCOPY;
force_copy = flags & XDP_COPY;
if (force_zc && force_copy)
return -EINVAL;
if (xdp_get_umem_from_qid(dev, queue_id))
return -EBUSY;
err = xdp_reg_umem_at_qid(dev, umem, queue_id);
if (err)
return err;
umem->dev = dev;
umem->queue_id = queue_id;
if (flags & XDP_USE_NEED_WAKEUP) {
umem->flags |= XDP_UMEM_USES_NEED_WAKEUP;
/* Tx needs to be explicitly woken up the first time.
* Also for supporting drivers that do not implement this
* feature. They will always have to call sendto().
*/
xsk_set_tx_need_wakeup(umem);
}
dev_hold(dev);
if (force_copy)
/* For copy-mode, we are done. */
return 0;
if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_wakeup) {
err = -EOPNOTSUPP;
goto err_unreg_umem;
}
bpf.command = XDP_SETUP_XSK_UMEM;
bpf.xsk.umem = umem;
bpf.xsk.queue_id = queue_id;
err = dev->netdev_ops->ndo_bpf(dev, &bpf);
if (err)
goto err_unreg_umem;
umem->zc = true;
return 0;
err_unreg_umem:
if (!force_zc)
err = 0; /* fallback to copy mode */
if (err)
xdp_clear_umem_at_qid(dev, queue_id);
return err;
}
void xdp_umem_clear_dev(struct xdp_umem *umem)
{
struct netdev_bpf bpf;
int err;
ASSERT_RTNL();
if (!umem->dev)
return;
if (umem->zc) {
bpf.command = XDP_SETUP_XSK_UMEM;
bpf.xsk.umem = NULL;
bpf.xsk.queue_id = umem->queue_id;
err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf);
if (err)
WARN(1, "failed to disable umem!\n");
}
xdp_clear_umem_at_qid(umem->dev, umem->queue_id);
dev_put(umem->dev);
umem->dev = NULL;
umem->zc = false;
}
static void xdp_umem_unpin_pages(struct xdp_umem *umem)
{
unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
kfree(umem->pgs);
umem->pgs = NULL;
}
static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
{
if (umem->user) {
atomic_long_sub(umem->npgs, &umem->user->locked_vm);
free_uid(umem->user);
}
}
static void xdp_umem_release(struct xdp_umem *umem)
{
rtnl_lock();
xdp_umem_clear_dev(umem);
rtnl_unlock();
ida_simple_remove(&umem_ida, umem->id);
if (umem->fq) {
xskq_destroy(umem->fq);
umem->fq = NULL;
}
if (umem->cq) {
xskq_destroy(umem->cq);
umem->cq = NULL;
}
xp_destroy(umem->pool);
xdp_umem_unpin_pages(umem);
xdp_umem_unaccount_pages(umem);
kfree(umem);
}
static void xdp_umem_release_deferred(struct work_struct *work)
{
struct xdp_umem *umem = container_of(work, struct xdp_umem, work);
xdp_umem_release(umem);
}
void xdp_get_umem(struct xdp_umem *umem)
{
refcount_inc(&umem->users);
}
void xdp_put_umem(struct xdp_umem *umem)
{
if (!umem)
return;
if (refcount_dec_and_test(&umem->users)) {
INIT_WORK(&umem->work, xdp_umem_release_deferred);
schedule_work(&umem->work);
}
}
static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address)
{
unsigned int gup_flags = FOLL_WRITE;
long npgs;
int err;
umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs),
GFP_KERNEL | __GFP_NOWARN);
if (!umem->pgs)
return -ENOMEM;
mmap_read_lock(current->mm);
npgs = pin_user_pages(address, umem->npgs,
gup_flags | FOLL_LONGTERM, &umem->pgs[0], NULL);
mmap_read_unlock(current->mm);
if (npgs != umem->npgs) {
if (npgs >= 0) {
umem->npgs = npgs;
err = -ENOMEM;
goto out_pin;
}
err = npgs;
goto out_pgs;
}
return 0;
out_pin:
xdp_umem_unpin_pages(umem);
out_pgs:
kfree(umem->pgs);
umem->pgs = NULL;
return err;
}
static int xdp_umem_account_pages(struct xdp_umem *umem)
{
unsigned long lock_limit, new_npgs, old_npgs;
if (capable(CAP_IPC_LOCK))
return 0;
lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
umem->user = get_uid(current_user());
do {
old_npgs = atomic_long_read(&umem->user->locked_vm);
new_npgs = old_npgs + umem->npgs;
if (new_npgs > lock_limit) {
free_uid(umem->user);
umem->user = NULL;
return -ENOBUFS;
}
} while (atomic_long_cmpxchg(&umem->user->locked_vm, old_npgs,
new_npgs) != old_npgs);
return 0;
}
static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
{
bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
u32 chunk_size = mr->chunk_size, headroom = mr->headroom;
u64 npgs, addr = mr->addr, size = mr->len;
unsigned int chunks, chunks_per_page;
int err;
if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) {
/* Strictly speaking we could support this, if:
* - huge pages, or*
* - using an IOMMU, or
* - making sure the memory area is consecutive
* but for now, we simply say "computer says no".
*/
return -EINVAL;
}
if (mr->flags & ~(XDP_UMEM_UNALIGNED_CHUNK_FLAG |
XDP_UMEM_USES_NEED_WAKEUP))
return -EINVAL;
if (!unaligned_chunks && !is_power_of_2(chunk_size))
return -EINVAL;
if (!PAGE_ALIGNED(addr)) {
/* Memory area has to be page size aligned. For
* simplicity, this might change.
*/
return -EINVAL;
}
if ((addr + size) < addr)
return -EINVAL;
npgs = size >> PAGE_SHIFT;
if (npgs > U32_MAX)
return -EINVAL;
chunks = (unsigned int)div_u64(size, chunk_size);
if (chunks == 0)
return -EINVAL;
if (!unaligned_chunks) {
chunks_per_page = PAGE_SIZE / chunk_size;
if (chunks < chunks_per_page || chunks % chunks_per_page)
return -EINVAL;
}
if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
return -EINVAL;
umem->size = size;
umem->headroom = headroom;
umem->chunk_size = chunk_size;
umem->npgs = (u32)npgs;
umem->pgs = NULL;
umem->user = NULL;
umem->flags = mr->flags;
INIT_LIST_HEAD(&umem->xsk_tx_list);
spin_lock_init(&umem->xsk_tx_list_lock);
refcount_set(&umem->users, 1);
err = xdp_umem_account_pages(umem);
if (err)
return err;
err = xdp_umem_pin_pages(umem, (unsigned long)addr);
if (err)
goto out_account;
umem->pool = xp_create(umem->pgs, umem->npgs, chunks, chunk_size,
headroom, size, unaligned_chunks);
if (!umem->pool) {
err = -ENOMEM;
goto out_pin;
}
return 0;
out_pin:
xdp_umem_unpin_pages(umem);
out_account:
xdp_umem_unaccount_pages(umem);
return err;
}
struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr)
{
struct xdp_umem *umem;
int err;
umem = kzalloc(sizeof(*umem), GFP_KERNEL);
if (!umem)
return ERR_PTR(-ENOMEM);
err = ida_simple_get(&umem_ida, 0, 0, GFP_KERNEL);
if (err < 0) {
kfree(umem);
return ERR_PTR(err);
}
umem->id = err;
err = xdp_umem_reg(umem, mr);
if (err) {
ida_simple_remove(&umem_ida, umem->id);
kfree(umem);
return ERR_PTR(err);
}
return umem;
}
bool xdp_umem_validate_queues(struct xdp_umem *umem)
{
return umem->fq && umem->cq;
}