#include "efa.h"
-#define EFA_MMAP_FLAG_SHIFT 56
-#define EFA_MMAP_PAGE_MASK GENMASK(EFA_MMAP_FLAG_SHIFT - 1, 0)
-#define EFA_MMAP_INVALID U64_MAX
-
enum {
EFA_MMAP_DMA_PAGE = 0,
EFA_MMAP_IO_WC,
(BIT(EFA_ADMIN_FATAL_ERROR) | BIT(EFA_ADMIN_WARNING) | \
BIT(EFA_ADMIN_NOTIFICATION) | BIT(EFA_ADMIN_KEEP_ALIVE))
-struct efa_mmap_entry {
- void *obj;
+struct efa_user_mmap_entry {
+ struct rdma_user_mmap_entry rdma_entry;
u64 address;
- u64 length;
- u32 mmap_page;
u8 mmap_flag;
};
-static inline u64 get_mmap_key(const struct efa_mmap_entry *efa)
-{
- return ((u64)efa->mmap_flag << EFA_MMAP_FLAG_SHIFT) |
- ((u64)efa->mmap_page << PAGE_SHIFT);
-}
-
#define EFA_DEFINE_STATS(op) \
op(EFA_TX_BYTES, "tx_bytes") \
op(EFA_TX_PKTS, "tx_pkts") \
return container_of(ibah, struct efa_ah, ibah);
}
+static inline struct efa_user_mmap_entry *
+to_emmap(struct rdma_user_mmap_entry *rdma_entry)
+{
+ return container_of(rdma_entry, struct efa_user_mmap_entry, rdma_entry);
+}
+
#define field_avail(x, fld, sz) (offsetof(typeof(x), fld) + \
FIELD_SIZEOF(typeof(x), fld) <= (sz))
return addr;
}
-/*
- * This is only called when the ucontext is destroyed and there can be no
- * concurrent query via mmap or allocate on the xarray, thus we can be sure no
- * other thread is using the entry pointer. We also know that all the BAR
- * pages have either been zap'd or munmaped at this point. Normal pages are
- * refcounted and will be freed at the proper time.
- */
-static void mmap_entries_remove_free(struct efa_dev *dev,
- struct efa_ucontext *ucontext)
-{
- struct efa_mmap_entry *entry;
- unsigned long mmap_page;
-
- xa_for_each(&ucontext->mmap_xa, mmap_page, entry) {
- xa_erase(&ucontext->mmap_xa, mmap_page);
-
- ibdev_dbg(
- &dev->ibdev,
- "mmap: obj[0x%p] key[%#llx] addr[%#llx] len[%#llx] removed\n",
- entry->obj, get_mmap_key(entry), entry->address,
- entry->length);
- if (entry->mmap_flag == EFA_MMAP_DMA_PAGE)
- /* DMA mapping is already gone, now free the pages */
- free_pages_exact(phys_to_virt(entry->address),
- entry->length);
- kfree(entry);
- }
-}
-
-static struct efa_mmap_entry *mmap_entry_get(struct efa_dev *dev,
- struct efa_ucontext *ucontext,
- u64 key, u64 len)
-{
- struct efa_mmap_entry *entry;
- u64 mmap_page;
-
- mmap_page = (key & EFA_MMAP_PAGE_MASK) >> PAGE_SHIFT;
- if (mmap_page > U32_MAX)
- return NULL;
-
- entry = xa_load(&ucontext->mmap_xa, mmap_page);
- if (!entry || get_mmap_key(entry) != key || entry->length != len)
- return NULL;
-
- ibdev_dbg(&dev->ibdev,
- "mmap: obj[0x%p] key[%#llx] addr[%#llx] len[%#llx] removed\n",
- entry->obj, key, entry->address, entry->length);
-
- return entry;
-}
-
-/*
- * Note this locking scheme cannot support removal of entries, except during
- * ucontext destruction when the core code guarentees no concurrency.
- */
-static u64 mmap_entry_insert(struct efa_dev *dev, struct efa_ucontext *ucontext,
- void *obj, u64 address, u64 length, u8 mmap_flag)
-{
- struct efa_mmap_entry *entry;
- u32 next_mmap_page;
- int err;
-
- entry = kmalloc(sizeof(*entry), GFP_KERNEL);
- if (!entry)
- return EFA_MMAP_INVALID;
-
- entry->obj = obj;
- entry->address = address;
- entry->length = length;
- entry->mmap_flag = mmap_flag;
-
- xa_lock(&ucontext->mmap_xa);
- if (check_add_overflow(ucontext->mmap_xa_page,
- (u32)(length >> PAGE_SHIFT),
- &next_mmap_page))
- goto err_unlock;
-
- entry->mmap_page = ucontext->mmap_xa_page;
- ucontext->mmap_xa_page = next_mmap_page;
- err = __xa_insert(&ucontext->mmap_xa, entry->mmap_page, entry,
- GFP_KERNEL);
- if (err)
- goto err_unlock;
-
- xa_unlock(&ucontext->mmap_xa);
-
- ibdev_dbg(
- &dev->ibdev,
- "mmap: obj[0x%p] addr[%#llx], len[%#llx], key[%#llx] inserted\n",
- entry->obj, entry->address, entry->length, get_mmap_key(entry));
-
- return get_mmap_key(entry);
-
-err_unlock:
- xa_unlock(&ucontext->mmap_xa);
- kfree(entry);
- return EFA_MMAP_INVALID;
-
-}
-
int efa_query_device(struct ib_device *ibdev,
struct ib_device_attr *props,
struct ib_udata *udata)
return efa_com_destroy_qp(&dev->edev, ¶ms);
}
+static void efa_qp_user_mmap_entries_remove(struct efa_ucontext *uctx,
+ struct efa_qp *qp)
+{
+ rdma_user_mmap_entry_remove(qp->rq_mmap_entry);
+ rdma_user_mmap_entry_remove(qp->rq_db_mmap_entry);
+ rdma_user_mmap_entry_remove(qp->llq_desc_mmap_entry);
+ rdma_user_mmap_entry_remove(qp->sq_db_mmap_entry);
+}
+
int efa_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
{
+ struct efa_ucontext *ucontext = rdma_udata_to_drv_context(udata,
+ struct efa_ucontext, ibucontext);
struct efa_dev *dev = to_edev(ibqp->pd->device);
struct efa_qp *qp = to_eqp(ibqp);
int err;
DMA_TO_DEVICE);
}
+ efa_qp_user_mmap_entries_remove(ucontext, qp);
kfree(qp);
return 0;
}
+static struct rdma_user_mmap_entry*
+efa_user_mmap_entry_insert(struct ib_ucontext *ucontext,
+ u64 address, size_t length,
+ u8 mmap_flag, u64 *offset)
+{
+ struct efa_user_mmap_entry *entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+ int err;
+
+ if (!entry)
+ return NULL;
+
+ entry->address = address;
+ entry->mmap_flag = mmap_flag;
+
+ err = rdma_user_mmap_entry_insert(ucontext, &entry->rdma_entry,
+ length);
+ if (err) {
+ kfree(entry);
+ return NULL;
+ }
+ *offset = rdma_user_mmap_get_offset(&entry->rdma_entry);
+
+ return &entry->rdma_entry;
+}
+
static int qp_mmap_entries_setup(struct efa_qp *qp,
struct efa_dev *dev,
struct efa_ucontext *ucontext,
struct efa_com_create_qp_params *params,
struct efa_ibv_create_qp_resp *resp)
{
- /*
- * Once an entry is inserted it might be mmapped, hence cannot be
- * cleaned up until dealloc_ucontext.
- */
- resp->sq_db_mmap_key =
- mmap_entry_insert(dev, ucontext, qp,
- dev->db_bar_addr + resp->sq_db_offset,
- PAGE_SIZE, EFA_MMAP_IO_NC);
- if (resp->sq_db_mmap_key == EFA_MMAP_INVALID)
+ size_t length;
+ u64 address;
+
+ address = dev->db_bar_addr + resp->sq_db_offset;
+ qp->sq_db_mmap_entry =
+ efa_user_mmap_entry_insert(&ucontext->ibucontext,
+ address,
+ PAGE_SIZE, EFA_MMAP_IO_NC,
+ &resp->sq_db_mmap_key);
+ if (!qp->sq_db_mmap_entry)
return -ENOMEM;
resp->sq_db_offset &= ~PAGE_MASK;
- resp->llq_desc_mmap_key =
- mmap_entry_insert(dev, ucontext, qp,
- dev->mem_bar_addr + resp->llq_desc_offset,
- PAGE_ALIGN(params->sq_ring_size_in_bytes +
- (resp->llq_desc_offset & ~PAGE_MASK)),
- EFA_MMAP_IO_WC);
- if (resp->llq_desc_mmap_key == EFA_MMAP_INVALID)
- return -ENOMEM;
+ address = dev->mem_bar_addr + resp->llq_desc_offset;
+ length = PAGE_ALIGN(params->sq_ring_size_in_bytes +
+ (resp->llq_desc_offset & ~PAGE_MASK));
+
+ qp->llq_desc_mmap_entry =
+ efa_user_mmap_entry_insert(&ucontext->ibucontext,
+ address, length,
+ EFA_MMAP_IO_WC,
+ &resp->llq_desc_mmap_key);
+ if (!qp->llq_desc_mmap_entry)
+ goto err_remove_mmap;
resp->llq_desc_offset &= ~PAGE_MASK;
if (qp->rq_size) {
- resp->rq_db_mmap_key =
- mmap_entry_insert(dev, ucontext, qp,
- dev->db_bar_addr + resp->rq_db_offset,
- PAGE_SIZE, EFA_MMAP_IO_NC);
- if (resp->rq_db_mmap_key == EFA_MMAP_INVALID)
- return -ENOMEM;
+ address = dev->db_bar_addr + resp->rq_db_offset;
+
+ qp->rq_db_mmap_entry =
+ efa_user_mmap_entry_insert(&ucontext->ibucontext,
+ address, PAGE_SIZE,
+ EFA_MMAP_IO_NC,
+ &resp->rq_db_mmap_key);
+ if (!qp->rq_db_mmap_entry)
+ goto err_remove_mmap;
resp->rq_db_offset &= ~PAGE_MASK;
- resp->rq_mmap_key =
- mmap_entry_insert(dev, ucontext, qp,
- virt_to_phys(qp->rq_cpu_addr),
- qp->rq_size, EFA_MMAP_DMA_PAGE);
- if (resp->rq_mmap_key == EFA_MMAP_INVALID)
- return -ENOMEM;
+ address = virt_to_phys(qp->rq_cpu_addr);
+ qp->rq_mmap_entry =
+ efa_user_mmap_entry_insert(&ucontext->ibucontext,
+ address, qp->rq_size,
+ EFA_MMAP_DMA_PAGE,
+ &resp->rq_mmap_key);
+ if (!qp->rq_mmap_entry)
+ goto err_remove_mmap;
resp->rq_mmap_size = qp->rq_size;
}
return 0;
+
+err_remove_mmap:
+ efa_qp_user_mmap_entries_remove(ucontext, qp);
+
+ return -ENOMEM;
}
static int efa_qp_validate_cap(struct efa_dev *dev,
struct efa_dev *dev = to_edev(ibpd->device);
struct efa_ibv_create_qp_resp resp = {};
struct efa_ibv_create_qp cmd = {};
- bool rq_entry_inserted = false;
struct efa_ucontext *ucontext;
struct efa_qp *qp;
int err;
if (err)
goto err_destroy_qp;
- rq_entry_inserted = true;
qp->qp_handle = create_qp_resp.qp_handle;
qp->ibqp.qp_num = create_qp_resp.qp_num;
qp->ibqp.qp_type = init_attr->qp_type;
ibdev_dbg(&dev->ibdev,
"Failed to copy udata for qp[%u]\n",
create_qp_resp.qp_num);
- goto err_destroy_qp;
+ goto err_remove_mmap_entries;
}
}
return &qp->ibqp;
+err_remove_mmap_entries:
+ efa_qp_user_mmap_entries_remove(ucontext, qp);
err_destroy_qp:
efa_destroy_qp_handle(dev, create_qp_resp.qp_handle);
err_free_mapped:
if (qp->rq_size) {
dma_unmap_single(&dev->pdev->dev, qp->rq_dma_addr, qp->rq_size,
DMA_TO_DEVICE);
- if (!rq_entry_inserted)
+
+ if (!qp->rq_mmap_entry)
free_pages_exact(qp->rq_cpu_addr, qp->rq_size);
}
err_free_qp:
efa_destroy_cq_idx(dev, cq->cq_idx);
dma_unmap_single(&dev->pdev->dev, cq->dma_addr, cq->size,
DMA_FROM_DEVICE);
+ rdma_user_mmap_entry_remove(cq->mmap_entry);
}
static int cq_mmap_entries_setup(struct efa_dev *dev, struct efa_cq *cq,
struct efa_ibv_create_cq_resp *resp)
{
resp->q_mmap_size = cq->size;
- resp->q_mmap_key = mmap_entry_insert(dev, cq->ucontext, cq,
- virt_to_phys(cq->cpu_addr),
- cq->size, EFA_MMAP_DMA_PAGE);
- if (resp->q_mmap_key == EFA_MMAP_INVALID)
+ cq->mmap_entry = efa_user_mmap_entry_insert(&cq->ucontext->ibucontext,
+ virt_to_phys(cq->cpu_addr),
+ cq->size, EFA_MMAP_DMA_PAGE,
+ &resp->q_mmap_key);
+ if (!cq->mmap_entry)
return -ENOMEM;
return 0;
struct efa_dev *dev = to_edev(ibdev);
struct efa_ibv_create_cq cmd = {};
struct efa_cq *cq = to_ecq(ibcq);
- bool cq_entry_inserted = false;
int entries = attr->cqe;
int err;
goto err_destroy_cq;
}
- cq_entry_inserted = true;
-
if (udata->outlen) {
err = ib_copy_to_udata(udata, &resp,
min(sizeof(resp), udata->outlen));
if (err) {
ibdev_dbg(ibdev,
"Failed to copy udata for create_cq\n");
- goto err_destroy_cq;
+ goto err_remove_mmap;
}
}
return 0;
+err_remove_mmap:
+ rdma_user_mmap_entry_remove(cq->mmap_entry);
err_destroy_cq:
efa_destroy_cq_idx(dev, cq->cq_idx);
err_free_mapped:
dma_unmap_single(&dev->pdev->dev, cq->dma_addr, cq->size,
DMA_FROM_DEVICE);
- if (!cq_entry_inserted)
+ if (!cq->mmap_entry)
free_pages_exact(cq->cpu_addr, cq->size);
+
err_out:
atomic64_inc(&dev->stats.sw_stats.create_cq_err);
return err;
goto err_out;
ucontext->uarn = result.uarn;
- xa_init(&ucontext->mmap_xa);
resp.cmds_supp_udata_mask |= EFA_USER_CMDS_SUPP_UDATA_QUERY_DEVICE;
resp.cmds_supp_udata_mask |= EFA_USER_CMDS_SUPP_UDATA_CREATE_AH;
struct efa_ucontext *ucontext = to_eucontext(ibucontext);
struct efa_dev *dev = to_edev(ibucontext->device);
- mmap_entries_remove_free(dev, ucontext);
efa_dealloc_uar(dev, ucontext->uarn);
}
+void efa_mmap_free(struct rdma_user_mmap_entry *rdma_entry)
+{
+ struct efa_user_mmap_entry *entry = to_emmap(rdma_entry);
+
+ /* DMA mapping is already gone, now free the pages */
+ if (entry->mmap_flag == EFA_MMAP_DMA_PAGE)
+ free_pages_exact(phys_to_virt(entry->address),
+ entry->rdma_entry.npages * PAGE_SIZE);
+ kfree(entry);
+}
+
static int __efa_mmap(struct efa_dev *dev, struct efa_ucontext *ucontext,
- struct vm_area_struct *vma, u64 key, u64 length)
+ struct vm_area_struct *vma)
{
- struct efa_mmap_entry *entry;
+ struct rdma_user_mmap_entry *rdma_entry;
+ struct efa_user_mmap_entry *entry;
unsigned long va;
+ int err = 0;
u64 pfn;
- int err;
- entry = mmap_entry_get(dev, ucontext, key, length);
- if (!entry) {
- ibdev_dbg(&dev->ibdev, "key[%#llx] does not have valid entry\n",
- key);
+ rdma_entry = rdma_user_mmap_entry_get(&ucontext->ibucontext, vma);
+ if (!rdma_entry) {
+ ibdev_dbg(&dev->ibdev,
+ "pgoff[%#lx] does not have valid entry\n",
+ vma->vm_pgoff);
return -EINVAL;
}
+ entry = to_emmap(rdma_entry);
ibdev_dbg(&dev->ibdev,
- "Mapping address[%#llx], length[%#llx], mmap_flag[%d]\n",
- entry->address, length, entry->mmap_flag);
+ "Mapping address[%#llx], length[%#zx], mmap_flag[%d]\n",
+ entry->address, rdma_entry->npages * PAGE_SIZE,
+ entry->mmap_flag);
pfn = entry->address >> PAGE_SHIFT;
switch (entry->mmap_flag) {
case EFA_MMAP_IO_NC:
- err = rdma_user_mmap_io(&ucontext->ibucontext, vma, pfn, length,
+ err = rdma_user_mmap_io(&ucontext->ibucontext, vma, pfn,
+ entry->rdma_entry.npages * PAGE_SIZE,
pgprot_noncached(vma->vm_page_prot),
- NULL);
+ rdma_entry);
break;
case EFA_MMAP_IO_WC:
- err = rdma_user_mmap_io(&ucontext->ibucontext, vma, pfn, length,
+ err = rdma_user_mmap_io(&ucontext->ibucontext, vma, pfn,
+ entry->rdma_entry.npages * PAGE_SIZE,
pgprot_writecombine(vma->vm_page_prot),
- NULL);
+ rdma_entry);
break;
case EFA_MMAP_DMA_PAGE:
for (va = vma->vm_start; va < vma->vm_end;
if (err) {
ibdev_dbg(
&dev->ibdev,
- "Couldn't mmap address[%#llx] length[%#llx] mmap_flag[%d] err[%d]\n",
- entry->address, length, entry->mmap_flag, err);
- return err;
+ "Couldn't mmap address[%#llx] length[%#zx] mmap_flag[%d] err[%d]\n",
+ entry->address, rdma_entry->npages * PAGE_SIZE,
+ entry->mmap_flag, err);
}
- return 0;
+ rdma_user_mmap_entry_put(rdma_entry);
+ return err;
}
int efa_mmap(struct ib_ucontext *ibucontext,
{
struct efa_ucontext *ucontext = to_eucontext(ibucontext);
struct efa_dev *dev = to_edev(ibucontext->device);
- u64 length = vma->vm_end - vma->vm_start;
- u64 key = vma->vm_pgoff << PAGE_SHIFT;
+ size_t length = vma->vm_end - vma->vm_start;
ibdev_dbg(&dev->ibdev,
- "start %#lx, end %#lx, length = %#llx, key = %#llx\n",
- vma->vm_start, vma->vm_end, length, key);
-
- if (length % PAGE_SIZE != 0 || !(vma->vm_flags & VM_SHARED)) {
- ibdev_dbg(&dev->ibdev,
- "length[%#llx] is not page size aligned[%#lx] or VM_SHARED is not set [%#lx]\n",
- length, PAGE_SIZE, vma->vm_flags);
- return -EINVAL;
- }
-
- if (vma->vm_flags & VM_EXEC) {
- ibdev_dbg(&dev->ibdev, "Mapping executable pages is not permitted\n");
- return -EPERM;
- }
+ "start %#lx, end %#lx, length = %#zx, pgoff = %#lx\n",
+ vma->vm_start, vma->vm_end, length, vma->vm_pgoff);
- return __efa_mmap(dev, ucontext, vma, key, length);
+ return __efa_mmap(dev, ucontext, vma);
}
static int efa_ah_destroy(struct efa_dev *dev, struct efa_ah *ah)