* [PATCH for-next v5 01/12] rdma_rxe: Separat MEM into MR and MW objects.
2020-09-18 21:15 [PATCH for-next v5 00/12] rdma_rxe: API extensions Bob Pearson
@ 2020-09-18 21:15 ` Bob Pearson
2020-09-18 21:15 ` [PATCH for-next v5 02/12] rdma_rxe: Enable " Bob Pearson
` (11 subsequent siblings)
12 siblings, 0 replies; 23+ messages in thread
From: Bob Pearson @ 2020-09-18 21:15 UTC (permalink / raw)
To: jgg, zyjzyj2000, linux-rdma; +Cc: Bob Pearson
In the original rxe implementation it was intended to use a common
object to represent MRs and MWs but it became clear that they are
different enough to separate these into two objects.
This allows replacing the mem name with mr for MRs which is more
consistent with the style for the other objects and less likely
to be confusing. This is a long patch that mostly changes mem to
mr where it makes sense and adds a new rxe_mw struct.
Signed-off-by: Bob Pearson <rpearson@hpe.com>
---
drivers/infiniband/sw/rxe/rxe_comp.c | 4 +-
drivers/infiniband/sw/rxe/rxe_loc.h | 26 +--
drivers/infiniband/sw/rxe/rxe_mr.c | 264 +++++++++++++-------------
drivers/infiniband/sw/rxe/rxe_pool.c | 8 +-
drivers/infiniband/sw/rxe/rxe_req.c | 6 +-
drivers/infiniband/sw/rxe/rxe_resp.c | 30 +--
drivers/infiniband/sw/rxe/rxe_verbs.c | 18 +-
drivers/infiniband/sw/rxe/rxe_verbs.h | 51 ++---
8 files changed, 204 insertions(+), 203 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index 0a1e6393250b..5dc86c9e74c2 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -345,7 +345,7 @@ static inline enum comp_state do_read(struct rxe_qp *qp,
ret = copy_data(qp->pd, IB_ACCESS_LOCAL_WRITE,
&wqe->dma, payload_addr(pkt),
- payload_size(pkt), to_mem_obj, NULL);
+ payload_size(pkt), to_mr_obj, NULL);
if (ret)
return COMPST_ERROR;
@@ -365,7 +365,7 @@ static inline enum comp_state do_atomic(struct rxe_qp *qp,
ret = copy_data(qp->pd, IB_ACCESS_LOCAL_WRITE,
&wqe->dma, &atomic_orig,
- sizeof(u64), to_mem_obj, NULL);
+ sizeof(u64), to_mr_obj, NULL);
if (ret)
return COMPST_ERROR;
else
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index 0d758760b9ae..9ec6bff6863f 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -72,40 +72,40 @@ int rxe_mmap(struct ib_ucontext *context, struct vm_area_struct *vma);
/* rxe_mr.c */
enum copy_direction {
- to_mem_obj,
- from_mem_obj,
+ to_mr_obj,
+ from_mr_obj,
};
-void rxe_mem_init_dma(struct rxe_pd *pd,
- int access, struct rxe_mem *mem);
+void rxe_mr_init_dma(struct rxe_pd *pd,
+ int access, struct rxe_mr *mr);
-int rxe_mem_init_user(struct rxe_pd *pd, u64 start,
+int rxe_mr_init_user(struct rxe_pd *pd, u64 start,
u64 length, u64 iova, int access, struct ib_udata *udata,
- struct rxe_mem *mr);
+ struct rxe_mr *mr);
-int rxe_mem_init_fast(struct rxe_pd *pd,
- int max_pages, struct rxe_mem *mem);
+int rxe_mr_init_fast(struct rxe_pd *pd,
+ int max_pages, struct rxe_mr *mr);
-int rxe_mem_copy(struct rxe_mem *mem, u64 iova, void *addr,
+int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr,
int length, enum copy_direction dir, u32 *crcp);
int copy_data(struct rxe_pd *pd, int access,
struct rxe_dma_info *dma, void *addr, int length,
enum copy_direction dir, u32 *crcp);
-void *iova_to_vaddr(struct rxe_mem *mem, u64 iova, int length);
+void *iova_to_vaddr(struct rxe_mr *mr, u64 iova, int length);
enum lookup_type {
lookup_local,
lookup_remote,
};
-struct rxe_mem *lookup_mem(struct rxe_pd *pd, int access, u32 key,
+struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
enum lookup_type type);
-int mem_check_range(struct rxe_mem *mem, u64 iova, size_t length);
+int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length);
-void rxe_mem_cleanup(struct rxe_pool_entry *arg);
+void rxe_mr_cleanup(struct rxe_pool_entry *arg);
int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index 708e2dff5eaa..368012904879 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -24,17 +24,17 @@ static u8 rxe_get_key(void)
return key;
}
-int mem_check_range(struct rxe_mem *mem, u64 iova, size_t length)
+int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length)
{
- switch (mem->type) {
- case RXE_MEM_TYPE_DMA:
+ switch (mr->type) {
+ case RXE_MR_TYPE_DMA:
return 0;
- case RXE_MEM_TYPE_MR:
- case RXE_MEM_TYPE_FMR:
- if (iova < mem->iova ||
- length > mem->length ||
- iova > mem->iova + mem->length - length)
+ case RXE_MR_TYPE_MR:
+ case RXE_MR_TYPE_FMR:
+ if (iova < mr->iova ||
+ length > mr->length ||
+ iova > mr->iova + mr->length - length)
return -EFAULT;
return 0;
@@ -47,90 +47,90 @@ int mem_check_range(struct rxe_mem *mem, u64 iova, size_t length)
| IB_ACCESS_REMOTE_WRITE \
| IB_ACCESS_REMOTE_ATOMIC)
-static void rxe_mem_init(int access, struct rxe_mem *mem)
+static void rxe_mr_init(int access, struct rxe_mr *mr)
{
- u32 lkey = mem->pelem.index << 8 | rxe_get_key();
+ u32 lkey = mr->pelem.index << 8 | rxe_get_key();
u32 rkey = (access & IB_ACCESS_REMOTE) ? lkey : 0;
- if (mem->pelem.pool->type == RXE_TYPE_MR) {
- mem->ibmr.lkey = lkey;
- mem->ibmr.rkey = rkey;
+ if (mr->pelem.pool->type == RXE_TYPE_MR) {
+ mr->ibmr.lkey = lkey;
+ mr->ibmr.rkey = rkey;
}
- mem->lkey = lkey;
- mem->rkey = rkey;
- mem->state = RXE_MEM_STATE_INVALID;
- mem->type = RXE_MEM_TYPE_NONE;
- mem->map_shift = ilog2(RXE_BUF_PER_MAP);
+ mr->lkey = lkey;
+ mr->rkey = rkey;
+ mr->state = RXE_MEM_STATE_INVALID;
+ mr->type = RXE_MR_TYPE_NONE;
+ mr->map_shift = ilog2(RXE_BUF_PER_MAP);
}
-void rxe_mem_cleanup(struct rxe_pool_entry *arg)
+void rxe_mr_cleanup(struct rxe_pool_entry *arg)
{
- struct rxe_mem *mem = container_of(arg, typeof(*mem), pelem);
+ struct rxe_mr *mr = container_of(arg, typeof(*mr), pelem);
int i;
- ib_umem_release(mem->umem);
+ ib_umem_release(mr->umem);
- if (mem->map) {
- for (i = 0; i < mem->num_map; i++)
- kfree(mem->map[i]);
+ if (mr->map) {
+ for (i = 0; i < mr->num_map; i++)
+ kfree(mr->map[i]);
- kfree(mem->map);
+ kfree(mr->map);
}
}
-static int rxe_mem_alloc(struct rxe_mem *mem, int num_buf)
+static int rxe_mr_alloc(struct rxe_mr *mr, int num_buf)
{
int i;
int num_map;
- struct rxe_map **map = mem->map;
+ struct rxe_map **map = mr->map;
num_map = (num_buf + RXE_BUF_PER_MAP - 1) / RXE_BUF_PER_MAP;
- mem->map = kmalloc_array(num_map, sizeof(*map), GFP_KERNEL);
- if (!mem->map)
+ mr->map = kmalloc_array(num_map, sizeof(*map), GFP_KERNEL);
+ if (!mr->map)
goto err1;
for (i = 0; i < num_map; i++) {
- mem->map[i] = kmalloc(sizeof(**map), GFP_KERNEL);
- if (!mem->map[i])
+ mr->map[i] = kmalloc(sizeof(**map), GFP_KERNEL);
+ if (!mr->map[i])
goto err2;
}
BUILD_BUG_ON(!is_power_of_2(RXE_BUF_PER_MAP));
- mem->map_shift = ilog2(RXE_BUF_PER_MAP);
- mem->map_mask = RXE_BUF_PER_MAP - 1;
+ mr->map_shift = ilog2(RXE_BUF_PER_MAP);
+ mr->map_mask = RXE_BUF_PER_MAP - 1;
- mem->num_buf = num_buf;
- mem->num_map = num_map;
- mem->max_buf = num_map * RXE_BUF_PER_MAP;
+ mr->num_buf = num_buf;
+ mr->num_map = num_map;
+ mr->max_buf = num_map * RXE_BUF_PER_MAP;
return 0;
err2:
for (i--; i >= 0; i--)
- kfree(mem->map[i]);
+ kfree(mr->map[i]);
- kfree(mem->map);
+ kfree(mr->map);
err1:
return -ENOMEM;
}
-void rxe_mem_init_dma(struct rxe_pd *pd,
- int access, struct rxe_mem *mem)
+void rxe_mr_init_dma(struct rxe_pd *pd,
+ int access, struct rxe_mr *mr)
{
- rxe_mem_init(access, mem);
+ rxe_mr_init(access, mr);
- mem->pd = pd;
- mem->access = access;
- mem->state = RXE_MEM_STATE_VALID;
- mem->type = RXE_MEM_TYPE_DMA;
+ mr->pd = pd;
+ mr->access = access;
+ mr->state = RXE_MEM_STATE_VALID;
+ mr->type = RXE_MR_TYPE_DMA;
}
-int rxe_mem_init_user(struct rxe_pd *pd, u64 start,
+int rxe_mr_init_user(struct rxe_pd *pd, u64 start,
u64 length, u64 iova, int access, struct ib_udata *udata,
- struct rxe_mem *mem)
+ struct rxe_mr *mr)
{
struct rxe_map **map;
struct rxe_phys_buf *buf = NULL;
@@ -148,23 +148,23 @@ int rxe_mem_init_user(struct rxe_pd *pd, u64 start,
goto err1;
}
- mem->umem = umem;
+ mr->umem = umem;
num_buf = ib_umem_num_pages(umem);
- rxe_mem_init(access, mem);
+ rxe_mr_init(access, mr);
- err = rxe_mem_alloc(mem, num_buf);
+ err = rxe_mr_alloc(mr, num_buf);
if (err) {
- pr_warn("err %d from rxe_mem_alloc\n", err);
+ pr_warn("err %d from rxe_mr_alloc\n", err);
ib_umem_release(umem);
goto err1;
}
- mem->page_shift = PAGE_SHIFT;
- mem->page_mask = PAGE_SIZE - 1;
+ mr->page_shift = PAGE_SHIFT;
+ mr->page_mask = PAGE_SIZE - 1;
num_buf = 0;
- map = mem->map;
+ map = mr->map;
if (length > 0) {
buf = map[0]->buf;
@@ -190,15 +190,15 @@ int rxe_mem_init_user(struct rxe_pd *pd, u64 start,
}
}
- mem->pd = pd;
- mem->umem = umem;
- mem->access = access;
- mem->length = length;
- mem->iova = iova;
- mem->va = start;
- mem->offset = ib_umem_offset(umem);
- mem->state = RXE_MEM_STATE_VALID;
- mem->type = RXE_MEM_TYPE_MR;
+ mr->pd = pd;
+ mr->umem = umem;
+ mr->access = access;
+ mr->length = length;
+ mr->iova = iova;
+ mr->va = start;
+ mr->offset = ib_umem_offset(umem);
+ mr->state = RXE_MEM_STATE_VALID;
+ mr->type = RXE_MR_TYPE_MR;
return 0;
@@ -206,24 +206,24 @@ int rxe_mem_init_user(struct rxe_pd *pd, u64 start,
return err;
}
-int rxe_mem_init_fast(struct rxe_pd *pd,
- int max_pages, struct rxe_mem *mem)
+int rxe_mr_init_fast(struct rxe_pd *pd,
+ int max_pages, struct rxe_mr *mr)
{
int err;
- rxe_mem_init(0, mem);
+ rxe_mr_init(0, mr);
/* In fastreg, we also set the rkey */
- mem->ibmr.rkey = mem->ibmr.lkey;
+ mr->ibmr.rkey = mr->ibmr.lkey;
- err = rxe_mem_alloc(mem, max_pages);
+ err = rxe_mr_alloc(mr, max_pages);
if (err)
goto err1;
- mem->pd = pd;
- mem->max_buf = max_pages;
- mem->state = RXE_MEM_STATE_FREE;
- mem->type = RXE_MEM_TYPE_MR;
+ mr->pd = pd;
+ mr->max_buf = max_pages;
+ mr->state = RXE_MEM_STATE_FREE;
+ mr->type = RXE_MR_TYPE_MR;
return 0;
@@ -232,27 +232,27 @@ int rxe_mem_init_fast(struct rxe_pd *pd,
}
static void lookup_iova(
- struct rxe_mem *mem,
+ struct rxe_mr *mr,
u64 iova,
int *m_out,
int *n_out,
size_t *offset_out)
{
- size_t offset = iova - mem->iova + mem->offset;
+ size_t offset = iova - mr->iova + mr->offset;
int map_index;
int buf_index;
u64 length;
- if (likely(mem->page_shift)) {
- *offset_out = offset & mem->page_mask;
- offset >>= mem->page_shift;
- *n_out = offset & mem->map_mask;
- *m_out = offset >> mem->map_shift;
+ if (likely(mr->page_shift)) {
+ *offset_out = offset & mr->page_mask;
+ offset >>= mr->page_shift;
+ *n_out = offset & mr->map_mask;
+ *m_out = offset >> mr->map_shift;
} else {
map_index = 0;
buf_index = 0;
- length = mem->map[map_index]->buf[buf_index].size;
+ length = mr->map[map_index]->buf[buf_index].size;
while (offset >= length) {
offset -= length;
@@ -262,7 +262,7 @@ static void lookup_iova(
map_index++;
buf_index = 0;
}
- length = mem->map[map_index]->buf[buf_index].size;
+ length = mr->map[map_index]->buf[buf_index].size;
}
*m_out = map_index;
@@ -271,48 +271,48 @@ static void lookup_iova(
}
}
-void *iova_to_vaddr(struct rxe_mem *mem, u64 iova, int length)
+void *iova_to_vaddr(struct rxe_mr *mr, u64 iova, int length)
{
size_t offset;
int m, n;
void *addr;
- if (mem->state != RXE_MEM_STATE_VALID) {
- pr_warn("mem not in valid state\n");
+ if (mr->state != RXE_MEM_STATE_VALID) {
+ pr_warn("mr not in valid state\n");
addr = NULL;
goto out;
}
- if (!mem->map) {
+ if (!mr->map) {
addr = (void *)(uintptr_t)iova;
goto out;
}
- if (mem_check_range(mem, iova, length)) {
+ if (mr_check_range(mr, iova, length)) {
pr_warn("range violation\n");
addr = NULL;
goto out;
}
- lookup_iova(mem, iova, &m, &n, &offset);
+ lookup_iova(mr, iova, &m, &n, &offset);
- if (offset + length > mem->map[m]->buf[n].size) {
+ if (offset + length > mr->map[m]->buf[n].size) {
pr_warn("crosses page boundary\n");
addr = NULL;
goto out;
}
- addr = (void *)(uintptr_t)mem->map[m]->buf[n].addr + offset;
+ addr = (void *)(uintptr_t)mr->map[m]->buf[n].addr + offset;
out:
return addr;
}
/* copy data from a range (vaddr, vaddr+length-1) to or from
- * a mem object starting at iova. Compute incremental value of
- * crc32 if crcp is not zero. caller must hold a reference to mem
+ * a mr object starting at iova. Compute incremental value of
+ * crc32 if crcp is not zero. caller must hold a reference to mr
*/
-int rxe_mem_copy(struct rxe_mem *mem, u64 iova, void *addr, int length,
+int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length,
enum copy_direction dir, u32 *crcp)
{
int err;
@@ -328,43 +328,43 @@ int rxe_mem_copy(struct rxe_mem *mem, u64 iova, void *addr, int length,
if (length == 0)
return 0;
- if (mem->type == RXE_MEM_TYPE_DMA) {
+ if (mr->type == RXE_MR_TYPE_DMA) {
u8 *src, *dest;
- src = (dir == to_mem_obj) ?
+ src = (dir == to_mr_obj) ?
addr : ((void *)(uintptr_t)iova);
- dest = (dir == to_mem_obj) ?
+ dest = (dir == to_mr_obj) ?
((void *)(uintptr_t)iova) : addr;
memcpy(dest, src, length);
if (crcp)
- *crcp = rxe_crc32(to_rdev(mem->pd->ibpd.device),
+ *crcp = rxe_crc32(to_rdev(mr->pd->ibpd.device),
*crcp, dest, length);
return 0;
}
- WARN_ON_ONCE(!mem->map);
+ WARN_ON_ONCE(!mr->map);
- err = mem_check_range(mem, iova, length);
+ err = mr_check_range(mr, iova, length);
if (err) {
err = -EFAULT;
goto err1;
}
- lookup_iova(mem, iova, &m, &i, &offset);
+ lookup_iova(mr, iova, &m, &i, &offset);
- map = mem->map + m;
+ map = mr->map + m;
buf = map[0]->buf + i;
while (length > 0) {
u8 *src, *dest;
va = (u8 *)(uintptr_t)buf->addr + offset;
- src = (dir == to_mem_obj) ? addr : va;
- dest = (dir == to_mem_obj) ? va : addr;
+ src = (dir == to_mr_obj) ? addr : va;
+ dest = (dir == to_mr_obj) ? va : addr;
bytes = buf->size - offset;
@@ -374,7 +374,7 @@ int rxe_mem_copy(struct rxe_mem *mem, u64 iova, void *addr, int length,
memcpy(dest, src, bytes);
if (crcp)
- crc = rxe_crc32(to_rdev(mem->pd->ibpd.device),
+ crc = rxe_crc32(to_rdev(mr->pd->ibpd.device),
crc, dest, bytes);
length -= bytes;
@@ -416,7 +416,7 @@ int copy_data(
struct rxe_sge *sge = &dma->sge[dma->cur_sge];
int offset = dma->sge_offset;
int resid = dma->resid;
- struct rxe_mem *mem = NULL;
+ struct rxe_mr *mr = NULL;
u64 iova;
int err;
@@ -429,8 +429,8 @@ int copy_data(
}
if (sge->length && (offset < sge->length)) {
- mem = lookup_mem(pd, access, sge->lkey, lookup_local);
- if (!mem) {
+ mr = lookup_mr(pd, access, sge->lkey, lookup_local);
+ if (!mr) {
err = -EINVAL;
goto err1;
}
@@ -440,9 +440,9 @@ int copy_data(
bytes = length;
if (offset >= sge->length) {
- if (mem) {
- rxe_drop_ref(mem);
- mem = NULL;
+ if (mr) {
+ rxe_drop_ref(mr);
+ mr = NULL;
}
sge++;
dma->cur_sge++;
@@ -454,9 +454,9 @@ int copy_data(
}
if (sge->length) {
- mem = lookup_mem(pd, access, sge->lkey,
+ mr = lookup_mr(pd, access, sge->lkey,
lookup_local);
- if (!mem) {
+ if (!mr) {
err = -EINVAL;
goto err1;
}
@@ -471,7 +471,7 @@ int copy_data(
if (bytes > 0) {
iova = sge->addr + offset;
- err = rxe_mem_copy(mem, iova, addr, bytes, dir, crcp);
+ err = rxe_mr_copy(mr, iova, addr, bytes, dir, crcp);
if (err)
goto err2;
@@ -485,14 +485,14 @@ int copy_data(
dma->sge_offset = offset;
dma->resid = resid;
- if (mem)
- rxe_drop_ref(mem);
+ if (mr)
+ rxe_drop_ref(mr);
return 0;
err2:
- if (mem)
- rxe_drop_ref(mem);
+ if (mr)
+ rxe_drop_ref(mr);
err1:
return err;
}
@@ -530,31 +530,31 @@ int advance_dma_data(struct rxe_dma_info *dma, unsigned int length)
return 0;
}
-/* (1) find the mem (mr or mw) corresponding to lkey/rkey
+/* (1) find the mr corresponding to lkey/rkey
* depending on lookup_type
- * (2) verify that the (qp) pd matches the mem pd
- * (3) verify that the mem can support the requested access
- * (4) verify that mem state is valid
+ * (2) verify that the (qp) pd matches the mr pd
+ * (3) verify that the mr can support the requested access
+ * (4) verify that mr state is valid
*/
-struct rxe_mem *lookup_mem(struct rxe_pd *pd, int access, u32 key,
+struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
enum lookup_type type)
{
- struct rxe_mem *mem;
+ struct rxe_mr *mr;
struct rxe_dev *rxe = to_rdev(pd->ibpd.device);
int index = key >> 8;
- mem = rxe_pool_get_index(&rxe->mr_pool, index);
- if (!mem)
+ mr = rxe_pool_get_index(&rxe->mr_pool, index);
+ if (!mr)
return NULL;
- if (unlikely((type == lookup_local && mem->lkey != key) ||
- (type == lookup_remote && mem->rkey != key) ||
- mem->pd != pd ||
- (access && !(access & mem->access)) ||
- mem->state != RXE_MEM_STATE_VALID)) {
- rxe_drop_ref(mem);
- mem = NULL;
+ if (unlikely((type == lookup_local && mr->lkey != key) ||
+ (type == lookup_remote && mr->rkey != key) ||
+ mr->pd != pd ||
+ (access && !(access & mr->access)) ||
+ mr->state != RXE_MEM_STATE_VALID)) {
+ rxe_drop_ref(mr);
+ mr = NULL;
}
- return mem;
+ return mr;
}
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c
index b374eb53e2fe..32ba47d143f3 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.c
+++ b/drivers/infiniband/sw/rxe/rxe_pool.c
@@ -8,8 +8,6 @@
#include "rxe_loc.h"
/* info about object pools
- * note that mr and mw share a single index space
- * so that one can map an lkey to the correct type of object
*/
struct rxe_type_info rxe_type_info[RXE_NUM_TYPES] = {
[RXE_TYPE_UC] = {
@@ -50,15 +48,15 @@ struct rxe_type_info rxe_type_info[RXE_NUM_TYPES] = {
},
[RXE_TYPE_MR] = {
.name = "rxe-mr",
- .size = sizeof(struct rxe_mem),
- .cleanup = rxe_mem_cleanup,
+ .size = sizeof(struct rxe_mr),
+ .cleanup = rxe_mr_cleanup,
.flags = RXE_POOL_INDEX,
.max_index = RXE_MAX_MR_INDEX,
.min_index = RXE_MIN_MR_INDEX,
},
[RXE_TYPE_MW] = {
.name = "rxe-mw",
- .size = sizeof(struct rxe_mem),
+ .size = sizeof(struct rxe_mw),
.flags = RXE_POOL_INDEX,
.max_index = RXE_MAX_MW_INDEX,
.min_index = RXE_MIN_MW_INDEX,
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index e27585ce9eb7..57236d8c2146 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -465,7 +465,7 @@ static int fill_packet(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
} else {
err = copy_data(qp->pd, 0, &wqe->dma,
payload_addr(pkt), paylen,
- from_mem_obj,
+ from_mr_obj,
&crc);
if (err)
return err;
@@ -597,7 +597,7 @@ int rxe_requester(void *arg)
if (wqe->mask & WR_REG_MASK) {
if (wqe->wr.opcode == IB_WR_LOCAL_INV) {
struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
- struct rxe_mem *rmr;
+ struct rxe_mr *rmr;
rmr = rxe_pool_get_index(&rxe->mr_pool,
wqe->wr.ex.invalidate_rkey >> 8);
@@ -613,7 +613,7 @@ int rxe_requester(void *arg)
wqe->state = wqe_state_done;
wqe->status = IB_WC_SUCCESS;
} else if (wqe->wr.opcode == IB_WR_REG_MR) {
- struct rxe_mem *rmr = to_rmr(wqe->wr.wr.reg.mr);
+ struct rxe_mr *rmr = to_rmr(wqe->wr.wr.reg.mr);
rmr->state = RXE_MEM_STATE_VALID;
rmr->access = wqe->wr.wr.reg.access;
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index c7e3b6a4af38..69867bf39cfb 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -390,7 +390,7 @@ static enum resp_states check_length(struct rxe_qp *qp,
static enum resp_states check_rkey(struct rxe_qp *qp,
struct rxe_pkt_info *pkt)
{
- struct rxe_mem *mem = NULL;
+ struct rxe_mr *mr = NULL;
u64 va;
u32 rkey;
u32 resid;
@@ -429,18 +429,18 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
resid = qp->resp.resid;
pktlen = payload_size(pkt);
- mem = lookup_mem(qp->pd, access, rkey, lookup_remote);
- if (!mem) {
+ mr = lookup_mr(qp->pd, access, rkey, lookup_remote);
+ if (!mr) {
state = RESPST_ERR_RKEY_VIOLATION;
goto err;
}
- if (unlikely(mem->state == RXE_MEM_STATE_FREE)) {
+ if (unlikely(mr->state == RXE_MEM_STATE_FREE)) {
state = RESPST_ERR_RKEY_VIOLATION;
goto err;
}
- if (mem_check_range(mem, va, resid)) {
+ if (mr_check_range(mr, va, resid)) {
state = RESPST_ERR_RKEY_VIOLATION;
goto err;
}
@@ -468,12 +468,12 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
WARN_ON_ONCE(qp->resp.mr);
- qp->resp.mr = mem;
+ qp->resp.mr = mr;
return RESPST_EXECUTE;
err:
- if (mem)
- rxe_drop_ref(mem);
+ if (mr)
+ rxe_drop_ref(mr);
return state;
}
@@ -483,7 +483,7 @@ static enum resp_states send_data_in(struct rxe_qp *qp, void *data_addr,
int err;
err = copy_data(qp->pd, IB_ACCESS_LOCAL_WRITE, &qp->resp.wqe->dma,
- data_addr, data_len, to_mem_obj, NULL);
+ data_addr, data_len, to_mr_obj, NULL);
if (unlikely(err))
return (err == -ENOSPC) ? RESPST_ERR_LENGTH
: RESPST_ERR_MALFORMED_WQE;
@@ -498,8 +498,8 @@ static enum resp_states write_data_in(struct rxe_qp *qp,
int err;
int data_len = payload_size(pkt);
- err = rxe_mem_copy(qp->resp.mr, qp->resp.va, payload_addr(pkt),
- data_len, to_mem_obj, NULL);
+ err = rxe_mr_copy(qp->resp.mr, qp->resp.va, payload_addr(pkt),
+ data_len, to_mr_obj, NULL);
if (err) {
rc = RESPST_ERR_RKEY_VIOLATION;
goto out;
@@ -521,7 +521,7 @@ static enum resp_states process_atomic(struct rxe_qp *qp,
u64 iova = atmeth_va(pkt);
u64 *vaddr;
enum resp_states ret;
- struct rxe_mem *mr = qp->resp.mr;
+ struct rxe_mr *mr = qp->resp.mr;
if (mr->state != RXE_MEM_STATE_VALID) {
ret = RESPST_ERR_RKEY_VIOLATION;
@@ -700,8 +700,8 @@ static enum resp_states read_reply(struct rxe_qp *qp,
if (!skb)
return RESPST_ERR_RNR;
- err = rxe_mem_copy(res->read.mr, res->read.va, payload_addr(&ack_pkt),
- payload, from_mem_obj, &icrc);
+ err = rxe_mr_copy(res->read.mr, res->read.va, payload_addr(&ack_pkt),
+ payload, from_mr_obj, &icrc);
if (err)
pr_err("Failed copying memory\n");
@@ -883,7 +883,7 @@ static enum resp_states do_complete(struct rxe_qp *qp,
}
if (pkt->mask & RXE_IETH_MASK) {
- struct rxe_mem *rmr;
+ struct rxe_mr *rmr;
wc->wc_flags |= IB_WC_WITH_INVALIDATE;
wc->ex.invalidate_rkey = ieth_rkey(pkt);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 5a4087b01757..626706f25efc 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -867,7 +867,7 @@ static struct ib_mr *rxe_get_dma_mr(struct ib_pd *ibpd, int access)
{
struct rxe_dev *rxe = to_rdev(ibpd->device);
struct rxe_pd *pd = to_rpd(ibpd);
- struct rxe_mem *mr;
+ struct rxe_mr *mr;
mr = rxe_alloc(&rxe->mr_pool);
if (!mr)
@@ -875,7 +875,7 @@ static struct ib_mr *rxe_get_dma_mr(struct ib_pd *ibpd, int access)
rxe_add_index(mr);
rxe_add_ref(pd);
- rxe_mem_init_dma(pd, access, mr);
+ rxe_mr_init_dma(pd, access, mr);
return &mr->ibmr;
}
@@ -889,7 +889,7 @@ static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd,
int err;
struct rxe_dev *rxe = to_rdev(ibpd->device);
struct rxe_pd *pd = to_rpd(ibpd);
- struct rxe_mem *mr;
+ struct rxe_mr *mr;
mr = rxe_alloc(&rxe->mr_pool);
if (!mr) {
@@ -901,7 +901,7 @@ static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd,
rxe_add_ref(pd);
- err = rxe_mem_init_user(pd, start, length, iova,
+ err = rxe_mr_init_user(pd, start, length, iova,
access, udata, mr);
if (err)
goto err3;
@@ -918,7 +918,7 @@ static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd,
static int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
{
- struct rxe_mem *mr = to_rmr(ibmr);
+ struct rxe_mr *mr = to_rmr(ibmr);
mr->state = RXE_MEM_STATE_ZOMBIE;
rxe_drop_ref(mr->pd);
@@ -932,7 +932,7 @@ static struct ib_mr *rxe_alloc_mr(struct ib_pd *ibpd, enum ib_mr_type mr_type,
{
struct rxe_dev *rxe = to_rdev(ibpd->device);
struct rxe_pd *pd = to_rpd(ibpd);
- struct rxe_mem *mr;
+ struct rxe_mr *mr;
int err;
if (mr_type != IB_MR_TYPE_MEM_REG)
@@ -948,7 +948,7 @@ static struct ib_mr *rxe_alloc_mr(struct ib_pd *ibpd, enum ib_mr_type mr_type,
rxe_add_ref(pd);
- err = rxe_mem_init_fast(pd, max_num_sg, mr);
+ err = rxe_mr_init_fast(pd, max_num_sg, mr);
if (err)
goto err2;
@@ -964,7 +964,7 @@ static struct ib_mr *rxe_alloc_mr(struct ib_pd *ibpd, enum ib_mr_type mr_type,
static int rxe_set_page(struct ib_mr *ibmr, u64 addr)
{
- struct rxe_mem *mr = to_rmr(ibmr);
+ struct rxe_mr *mr = to_rmr(ibmr);
struct rxe_map *map;
struct rxe_phys_buf *buf;
@@ -984,7 +984,7 @@ static int rxe_set_page(struct ib_mr *ibmr, u64 addr)
static int rxe_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg,
int sg_nents, unsigned int *sg_offset)
{
- struct rxe_mem *mr = to_rmr(ibmr);
+ struct rxe_mr *mr = to_rmr(ibmr);
int n;
mr->nbuf = 0;
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index 560a610bb0aa..dbc649c9c43f 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -39,7 +39,7 @@ struct rxe_ucontext {
};
struct rxe_pd {
- struct ib_pd ibpd;
+ struct ib_pd ibpd;
struct rxe_pool_entry pelem;
};
@@ -156,7 +156,7 @@ struct resp_res {
struct sk_buff *skb;
} atomic;
struct {
- struct rxe_mem *mr;
+ struct rxe_mr *mr;
u64 va_org;
u32 rkey;
u32 length;
@@ -183,7 +183,7 @@ struct rxe_resp_info {
/* RDMA read / atomic only */
u64 va;
- struct rxe_mem *mr;
+ struct rxe_mr *mr;
u32 resid;
u32 rkey;
u32 length;
@@ -269,31 +269,27 @@ enum rxe_mem_state {
RXE_MEM_STATE_VALID,
};
-enum rxe_mem_type {
- RXE_MEM_TYPE_NONE,
- RXE_MEM_TYPE_DMA,
- RXE_MEM_TYPE_MR,
- RXE_MEM_TYPE_FMR,
- RXE_MEM_TYPE_MW,
+enum rxe_mr_type {
+ RXE_MR_TYPE_NONE,
+ RXE_MR_TYPE_DMA,
+ RXE_MR_TYPE_MR,
+ RXE_MR_TYPE_FMR,
};
#define RXE_BUF_PER_MAP (PAGE_SIZE / sizeof(struct rxe_phys_buf))
struct rxe_phys_buf {
- u64 addr;
- u64 size;
+ u64 addr;
+ u64 size;
};
struct rxe_map {
struct rxe_phys_buf buf[RXE_BUF_PER_MAP];
};
-struct rxe_mem {
+struct rxe_mr {
struct rxe_pool_entry pelem;
- union {
- struct ib_mr ibmr;
- struct ib_mw ibmw;
- };
+ struct ib_mr ibmr;
struct rxe_pd *pd;
struct ib_umem *umem;
@@ -302,7 +298,7 @@ struct rxe_mem {
u32 rkey;
enum rxe_mem_state state;
- enum rxe_mem_type type;
+ enum rxe_mr_type type;
u64 va;
u64 iova;
size_t length;
@@ -323,6 +319,18 @@ struct rxe_mem {
struct rxe_map **map;
};
+struct rxe_mw {
+ struct rxe_pool_entry pelem;
+ struct ib_mw ibmw;
+ struct rxe_qp *qp; /* type 2B only */
+ struct rxe_mr *mr;
+ spinlock_t lock;
+ enum rxe_mem_state state;
+ u32 access;
+ u64 addr;
+ u64 length;
+};
+
struct rxe_mc_grp {
struct rxe_pool_entry pelem;
spinlock_t mcg_lock; /* guard group */
@@ -428,14 +436,9 @@ static inline struct rxe_cq *to_rcq(struct ib_cq *cq)
return cq ? container_of(cq, struct rxe_cq, ibcq) : NULL;
}
-static inline struct rxe_mem *to_rmr(struct ib_mr *mr)
-{
- return mr ? container_of(mr, struct rxe_mem, ibmr) : NULL;
-}
-
-static inline struct rxe_mem *to_rmw(struct ib_mw *mw)
+static inline struct rxe_mr *to_rmr(struct ib_mr *mr)
{
- return mw ? container_of(mw, struct rxe_mem, ibmw) : NULL;
+ return mr ? container_of(mr, struct rxe_mr, ibmr) : NULL;
}
int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name);
--
2.25.1
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH for-next v5 02/12] rdma_rxe: Enable MW objects
2020-09-18 21:15 [PATCH for-next v5 00/12] rdma_rxe: API extensions Bob Pearson
2020-09-18 21:15 ` [PATCH for-next v5 01/12] rdma_rxe: Separat MEM into MR and MW objects Bob Pearson
@ 2020-09-18 21:15 ` Bob Pearson
2020-09-18 21:15 ` [PATCH for-next v5 03/12] rdma_rxe: Let pools support both keys and indices Bob Pearson
` (10 subsequent siblings)
12 siblings, 0 replies; 23+ messages in thread
From: Bob Pearson @ 2020-09-18 21:15 UTC (permalink / raw)
To: jgg, zyjzyj2000, linux-rdma; +Cc: Bob Pearson
Change parameters in rxe_param.h so that MAX_MW is the same as MAX_MR.
Set device attribute in rxe.c so max_mw = MAX_MW.
Signed-off-by: Bob Pearson <rpearson@hpe.com>
---
drivers/infiniband/sw/rxe/rxe.c | 1 +
drivers/infiniband/sw/rxe/rxe_param.h | 10 ++++++----
2 files changed, 7 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index 43b327b53e26..fab291245366 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -52,6 +52,7 @@ static void rxe_init_device_param(struct rxe_dev *rxe)
rxe->attr.max_cq = RXE_MAX_CQ;
rxe->attr.max_cqe = (1 << RXE_MAX_LOG_CQE) - 1;
rxe->attr.max_mr = RXE_MAX_MR;
+ rxe->attr.max_mw = RXE_MAX_MW;
rxe->attr.max_pd = RXE_MAX_PD;
rxe->attr.max_qp_rd_atom = RXE_MAX_QP_RD_ATOM;
rxe->attr.max_res_rd_atom = RXE_MAX_RES_RD_ATOM;
diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h
index 25ab50d9b7c2..4ebb3da8c07d 100644
--- a/drivers/infiniband/sw/rxe/rxe_param.h
+++ b/drivers/infiniband/sw/rxe/rxe_param.h
@@ -58,7 +58,8 @@ enum rxe_device_param {
RXE_MAX_SGE_RD = 32,
RXE_MAX_CQ = 16384,
RXE_MAX_LOG_CQE = 15,
- RXE_MAX_MR = 256 * 1024,
+ RXE_MAX_MR = 0x40000,
+ RXE_MAX_MW = 0x40000,
RXE_MAX_PD = 0x7ffc,
RXE_MAX_QP_RD_ATOM = 128,
RXE_MAX_RES_RD_ATOM = 0x3f000,
@@ -87,9 +88,10 @@ enum rxe_device_param {
RXE_MAX_SRQ_INDEX = 0x00040000,
RXE_MIN_MR_INDEX = 0x00000001,
- RXE_MAX_MR_INDEX = 0x00040000,
- RXE_MIN_MW_INDEX = 0x00040001,
- RXE_MAX_MW_INDEX = 0x00060000,
+ RXE_MAX_MR_INDEX = RXE_MIN_MR_INDEX + RXE_MAX_MR - 1,
+ RXE_MIN_MW_INDEX = RXE_MIN_MR_INDEX + RXE_MAX_MR,
+ RXE_MAX_MW_INDEX = RXE_MIN_MW_INDEX + RXE_MAX_MW - 1,
+
RXE_MAX_PKT_PER_ACK = 64,
RXE_MAX_UNACKED_PSNS = 128,
--
2.25.1
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH for-next v5 03/12] rdma_rxe: Let pools support both keys and indices
2020-09-18 21:15 [PATCH for-next v5 00/12] rdma_rxe: API extensions Bob Pearson
2020-09-18 21:15 ` [PATCH for-next v5 01/12] rdma_rxe: Separat MEM into MR and MW objects Bob Pearson
2020-09-18 21:15 ` [PATCH for-next v5 02/12] rdma_rxe: Enable " Bob Pearson
@ 2020-09-18 21:15 ` Bob Pearson
2020-09-18 21:15 ` [PATCH for-next v5 04/12] rdma_rxe: Add alloc_mw and dealloc_mw verbs Bob Pearson
` (9 subsequent siblings)
12 siblings, 0 replies; 23+ messages in thread
From: Bob Pearson @ 2020-09-18 21:15 UTC (permalink / raw)
To: jgg, zyjzyj2000, linux-rdma; +Cc: Bob Pearson
Allow both indices and keys to exist for objects in pools.
Previously you were limited to one or the other. This will support
allowing the keys on MWs to change.
Signed-off-by: Bob Pearson <rpearson@hpe.com>
---
drivers/infiniband/sw/rxe/rxe_pool.c | 73 ++++++++++++++--------------
drivers/infiniband/sw/rxe/rxe_pool.h | 32 +++++++-----
2 files changed, 58 insertions(+), 47 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c
index 32ba47d143f3..30b8f037ee20 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.c
+++ b/drivers/infiniband/sw/rxe/rxe_pool.c
@@ -92,18 +92,18 @@ static int rxe_pool_init_index(struct rxe_pool *pool, u32 max, u32 min)
goto out;
}
- pool->max_index = max;
- pool->min_index = min;
+ pool->index.max_index = max;
+ pool->index.min_index = min;
size = BITS_TO_LONGS(max - min + 1) * sizeof(long);
- pool->table = kmalloc(size, GFP_KERNEL);
- if (!pool->table) {
+ pool->index.table = kmalloc(size, GFP_KERNEL);
+ if (!pool->index.table) {
err = -ENOMEM;
goto out;
}
- pool->table_size = size;
- bitmap_zero(pool->table, max - min + 1);
+ pool->index.table_size = size;
+ bitmap_zero(pool->index.table, max - min + 1);
out:
return err;
@@ -125,7 +125,8 @@ int rxe_pool_init(
pool->max_elem = max_elem;
pool->elem_size = ALIGN(size, RXE_POOL_ALIGN);
pool->flags = rxe_type_info[type].flags;
- pool->tree = RB_ROOT;
+ pool->index.tree = RB_ROOT;
+ pool->key.tree = RB_ROOT;
pool->cleanup = rxe_type_info[type].cleanup;
atomic_set(&pool->num_elem, 0);
@@ -143,8 +144,8 @@ int rxe_pool_init(
}
if (rxe_type_info[type].flags & RXE_POOL_KEY) {
- pool->key_offset = rxe_type_info[type].key_offset;
- pool->key_size = rxe_type_info[type].key_size;
+ pool->key.key_offset = rxe_type_info[type].key_offset;
+ pool->key.key_size = rxe_type_info[type].key_size;
}
pool->state = RXE_POOL_STATE_VALID;
@@ -158,7 +159,7 @@ static void rxe_pool_release(struct kref *kref)
struct rxe_pool *pool = container_of(kref, struct rxe_pool, ref_cnt);
pool->state = RXE_POOL_STATE_INVALID;
- kfree(pool->table);
+ kfree(pool->index.table);
}
static void rxe_pool_put(struct rxe_pool *pool)
@@ -183,27 +184,27 @@ void rxe_pool_cleanup(struct rxe_pool *pool)
static u32 alloc_index(struct rxe_pool *pool)
{
u32 index;
- u32 range = pool->max_index - pool->min_index + 1;
+ u32 range = pool->index.max_index - pool->index.min_index + 1;
- index = find_next_zero_bit(pool->table, range, pool->last);
+ index = find_next_zero_bit(pool->index.table, range, pool->index.last);
if (index >= range)
- index = find_first_zero_bit(pool->table, range);
+ index = find_first_zero_bit(pool->index.table, range);
WARN_ON_ONCE(index >= range);
- set_bit(index, pool->table);
- pool->last = index;
- return index + pool->min_index;
+ set_bit(index, pool->index.table);
+ pool->index.last = index;
+ return index + pool->index.min_index;
}
static void insert_index(struct rxe_pool *pool, struct rxe_pool_entry *new)
{
- struct rb_node **link = &pool->tree.rb_node;
+ struct rb_node **link = &pool->index.tree.rb_node;
struct rb_node *parent = NULL;
struct rxe_pool_entry *elem;
while (*link) {
parent = *link;
- elem = rb_entry(parent, struct rxe_pool_entry, node);
+ elem = rb_entry(parent, struct rxe_pool_entry, index_node);
if (elem->index == new->index) {
pr_warn("element already exists!\n");
@@ -216,25 +217,25 @@ static void insert_index(struct rxe_pool *pool, struct rxe_pool_entry *new)
link = &(*link)->rb_right;
}
- rb_link_node(&new->node, parent, link);
- rb_insert_color(&new->node, &pool->tree);
+ rb_link_node(&new->index_node, parent, link);
+ rb_insert_color(&new->index_node, &pool->index.tree);
out:
return;
}
static void insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new)
{
- struct rb_node **link = &pool->tree.rb_node;
+ struct rb_node **link = &pool->key.tree.rb_node;
struct rb_node *parent = NULL;
struct rxe_pool_entry *elem;
int cmp;
while (*link) {
parent = *link;
- elem = rb_entry(parent, struct rxe_pool_entry, node);
+ elem = rb_entry(parent, struct rxe_pool_entry, key_node);
- cmp = memcmp((u8 *)elem + pool->key_offset,
- (u8 *)new + pool->key_offset, pool->key_size);
+ cmp = memcmp((u8 *)elem + pool->key.key_offset,
+ (u8 *)new + pool->key.key_offset, pool->key.key_size);
if (cmp == 0) {
pr_warn("key already exists!\n");
@@ -247,8 +248,8 @@ static void insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new)
link = &(*link)->rb_right;
}
- rb_link_node(&new->node, parent, link);
- rb_insert_color(&new->node, &pool->tree);
+ rb_link_node(&new->key_node, parent, link);
+ rb_insert_color(&new->key_node, &pool->key.tree);
out:
return;
}
@@ -260,7 +261,7 @@ void rxe_add_key(void *arg, void *key)
unsigned long flags;
write_lock_irqsave(&pool->pool_lock, flags);
- memcpy((u8 *)elem + pool->key_offset, key, pool->key_size);
+ memcpy((u8 *)elem + pool->key.key_offset, key, pool->key.key_size);
insert_key(pool, elem);
write_unlock_irqrestore(&pool->pool_lock, flags);
}
@@ -272,7 +273,7 @@ void rxe_drop_key(void *arg)
unsigned long flags;
write_lock_irqsave(&pool->pool_lock, flags);
- rb_erase(&elem->node, &pool->tree);
+ rb_erase(&elem->key_node, &pool->key.tree);
write_unlock_irqrestore(&pool->pool_lock, flags);
}
@@ -295,8 +296,8 @@ void rxe_drop_index(void *arg)
unsigned long flags;
write_lock_irqsave(&pool->pool_lock, flags);
- clear_bit(elem->index - pool->min_index, pool->table);
- rb_erase(&elem->node, &pool->tree);
+ clear_bit(elem->index - pool->index.min_index, pool->index.table);
+ rb_erase(&elem->index_node, &pool->index.tree);
write_unlock_irqrestore(&pool->pool_lock, flags);
}
@@ -400,10 +401,10 @@ void *rxe_pool_get_index(struct rxe_pool *pool, u32 index)
if (pool->state != RXE_POOL_STATE_VALID)
goto out;
- node = pool->tree.rb_node;
+ node = pool->index.tree.rb_node;
while (node) {
- elem = rb_entry(node, struct rxe_pool_entry, node);
+ elem = rb_entry(node, struct rxe_pool_entry, index_node);
if (elem->index > index)
node = node->rb_left;
@@ -432,13 +433,13 @@ void *rxe_pool_get_key(struct rxe_pool *pool, void *key)
if (pool->state != RXE_POOL_STATE_VALID)
goto out;
- node = pool->tree.rb_node;
+ node = pool->key.tree.rb_node;
while (node) {
- elem = rb_entry(node, struct rxe_pool_entry, node);
+ elem = rb_entry(node, struct rxe_pool_entry, key_node);
- cmp = memcmp((u8 *)elem + pool->key_offset,
- key, pool->key_size);
+ cmp = memcmp((u8 *)elem + pool->key.key_offset,
+ key, pool->key.key_size);
if (cmp > 0)
node = node->rb_left;
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.h b/drivers/infiniband/sw/rxe/rxe_pool.h
index 432745ffc8d4..3d722aae5f15 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.h
+++ b/drivers/infiniband/sw/rxe/rxe_pool.h
@@ -56,8 +56,11 @@ struct rxe_pool_entry {
struct kref ref_cnt;
struct list_head list;
- /* only used if indexed or keyed */
- struct rb_node node;
+ /* only used if keyed */
+ struct rb_node key_node;
+
+ /* only used if indexed */
+ struct rb_node index_node;
u32 index;
};
@@ -74,15 +77,22 @@ struct rxe_pool {
unsigned int max_elem;
atomic_t num_elem;
- /* only used if indexed or keyed */
- struct rb_root tree;
- unsigned long *table;
- size_t table_size;
- u32 max_index;
- u32 min_index;
- u32 last;
- size_t key_offset;
- size_t key_size;
+ /* only used if indexed */
+ struct {
+ struct rb_root tree;
+ unsigned long *table;
+ size_t table_size;
+ u32 last;
+ u32 max_index;
+ u32 min_index;
+ } index;
+
+ /* only used if keyed */
+ struct {
+ struct rb_root tree;
+ size_t key_offset;
+ size_t key_size;
+ } key;
};
/* initialize a pool of objects with given limit on
--
2.25.1
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH for-next v5 04/12] rdma_rxe: Add alloc_mw and dealloc_mw verbs
2020-09-18 21:15 [PATCH for-next v5 00/12] rdma_rxe: API extensions Bob Pearson
` (2 preceding siblings ...)
2020-09-18 21:15 ` [PATCH for-next v5 03/12] rdma_rxe: Let pools support both keys and indices Bob Pearson
@ 2020-09-18 21:15 ` Bob Pearson
2020-09-18 21:15 ` [PATCH for-next v5 05/12] rdma_rxe: Add bind_mw and invalidate_mw verbs Bob Pearson
` (8 subsequent siblings)
12 siblings, 0 replies; 23+ messages in thread
From: Bob Pearson @ 2020-09-18 21:15 UTC (permalink / raw)
To: jgg, zyjzyj2000, linux-rdma; +Cc: Bob Pearson
- Add a new file focused on memory windows, rxe_mw.c.
- Add alloc_mw and dealloc_mw verbs and added them to
the list of supported user space verbs.
Signed-off-by: Bob Pearson <rpearson@hpe.com>
---
drivers/infiniband/sw/rxe/Makefile | 1 +
drivers/infiniband/sw/rxe/rxe_loc.h | 8 +++
drivers/infiniband/sw/rxe/rxe_mr.c | 77 ++++++++++-----------
drivers/infiniband/sw/rxe/rxe_mw.c | 98 +++++++++++++++++++++++++++
drivers/infiniband/sw/rxe/rxe_pool.c | 33 +++++----
drivers/infiniband/sw/rxe/rxe_pool.h | 2 +-
drivers/infiniband/sw/rxe/rxe_req.c | 24 +++----
drivers/infiniband/sw/rxe/rxe_resp.c | 4 +-
drivers/infiniband/sw/rxe/rxe_verbs.c | 52 +++++++++-----
drivers/infiniband/sw/rxe/rxe_verbs.h | 8 +++
include/uapi/rdma/rdma_user_rxe.h | 10 +++
11 files changed, 232 insertions(+), 85 deletions(-)
create mode 100644 drivers/infiniband/sw/rxe/rxe_mw.c
diff --git a/drivers/infiniband/sw/rxe/Makefile b/drivers/infiniband/sw/rxe/Makefile
index 66af72dca759..1e24673e9318 100644
--- a/drivers/infiniband/sw/rxe/Makefile
+++ b/drivers/infiniband/sw/rxe/Makefile
@@ -15,6 +15,7 @@ rdma_rxe-y := \
rxe_qp.o \
rxe_cq.o \
rxe_mr.o \
+ rxe_mw.o \
rxe_opcode.o \
rxe_mmap.o \
rxe_icrc.o \
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index 9ec6bff6863f..65f2e4a94956 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -109,6 +109,14 @@ void rxe_mr_cleanup(struct rxe_pool_entry *arg);
int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
+/* rxe_mw.c */
+struct ib_mw *rxe_alloc_mw(struct ib_pd *ibpd, enum ib_mw_type type,
+ struct ib_udata *udata);
+
+int rxe_dealloc_mw(struct ib_mw *ibmw);
+
+void rxe_mw_cleanup(struct rxe_pool_entry *arg);
+
/* rxe_net.c */
void rxe_loopback(struct sk_buff *skb);
int rxe_send(struct rxe_pkt_info *pkt, struct sk_buff *skb);
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index 368012904879..4c53badfa4e9 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -7,21 +7,18 @@
#include "rxe.h"
#include "rxe_loc.h"
-/*
- * lfsr (linear feedback shift register) with period 255
+/* choose a unique non zero random number for lkey
+ * use high order bit to indicate MR vs MW
*/
-static u8 rxe_get_key(void)
+static void rxe_set_mr_lkey(struct rxe_mr *mr)
{
- static u32 key = 1;
-
- key = key << 1;
-
- key |= (0 != (key & 0x100)) ^ (0 != (key & 0x10))
- ^ (0 != (key & 0x80)) ^ (0 != (key & 0x40));
-
- key &= 0xff;
-
- return key;
+ u32 lkey;
+again:
+ get_random_bytes(&lkey, sizeof(lkey));
+ lkey &= ~IS_MW;
+ if (likely(lkey && (rxe_add_key(mr, &lkey) == 0)))
+ return;
+ goto again;
}
int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length)
@@ -49,36 +46,19 @@ int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length)
static void rxe_mr_init(int access, struct rxe_mr *mr)
{
- u32 lkey = mr->pelem.index << 8 | rxe_get_key();
- u32 rkey = (access & IB_ACCESS_REMOTE) ? lkey : 0;
-
- if (mr->pelem.pool->type == RXE_TYPE_MR) {
- mr->ibmr.lkey = lkey;
- mr->ibmr.rkey = rkey;
- }
-
- mr->lkey = lkey;
- mr->rkey = rkey;
+ rxe_add_index(mr);
+ rxe_set_mr_lkey(mr);
+ if (access & IB_ACCESS_REMOTE)
+ mr->ibmr.rkey = mr->ibmr.lkey;
+
+ /* TODO should not have two copies of lkey and rkey in mr */
+ mr->lkey = mr->ibmr.lkey;
+ mr->rkey = mr->ibmr.rkey;
mr->state = RXE_MEM_STATE_INVALID;
mr->type = RXE_MR_TYPE_NONE;
mr->map_shift = ilog2(RXE_BUF_PER_MAP);
}
-void rxe_mr_cleanup(struct rxe_pool_entry *arg)
-{
- struct rxe_mr *mr = container_of(arg, typeof(*mr), pelem);
- int i;
-
- ib_umem_release(mr->umem);
-
- if (mr->map) {
- for (i = 0; i < mr->num_map; i++)
- kfree(mr->map[i]);
-
- kfree(mr->map);
- }
-}
-
static int rxe_mr_alloc(struct rxe_mr *mr, int num_buf)
{
int i;
@@ -541,9 +521,8 @@ struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
{
struct rxe_mr *mr;
struct rxe_dev *rxe = to_rdev(pd->ibpd.device);
- int index = key >> 8;
- mr = rxe_pool_get_index(&rxe->mr_pool, index);
+ mr = rxe_pool_get_key(&rxe->mr_pool, &key);
if (!mr)
return NULL;
@@ -558,3 +537,21 @@ struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
return mr;
}
+
+void rxe_mr_cleanup(struct rxe_pool_entry *arg)
+{
+ struct rxe_mr *mr = container_of(arg, typeof(*mr), pelem);
+ int i;
+
+ ib_umem_release(mr->umem);
+
+ if (mr->map) {
+ for (i = 0; i < mr->num_map; i++)
+ kfree(mr->map[i]);
+
+ kfree(mr->map);
+ }
+
+ rxe_drop_index(mr);
+ rxe_drop_key(mr);
+}
diff --git a/drivers/infiniband/sw/rxe/rxe_mw.c b/drivers/infiniband/sw/rxe/rxe_mw.c
new file mode 100644
index 000000000000..b818f1e869da
--- /dev/null
+++ b/drivers/infiniband/sw/rxe/rxe_mw.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2020 Hewlett Packard Enterprise, Inc. All rights reserved.
+ */
+
+#include "rxe.h"
+#include "rxe_loc.h"
+
+/* choose a unique non zero random number for rkey
+ * use high order bit to indicate MR vs MW
+ */
+static void rxe_set_mw_rkey(struct rxe_mw *mw)
+{
+ u32 rkey;
+again:
+ get_random_bytes(&rkey, sizeof(rkey));
+ rkey |= IS_MW;
+ if (likely((rkey & ~IS_MW) &&
+ (rxe_add_key(mw, &rkey) == 0)))
+ return;
+ goto again;
+}
+
+struct ib_mw *rxe_alloc_mw(struct ib_pd *ibpd, enum ib_mw_type type,
+ struct ib_udata *udata)
+{
+ struct rxe_pd *pd = to_rpd(ibpd);
+ struct rxe_dev *rxe = to_rdev(ibpd->device);
+ struct rxe_mw *mw;
+ struct rxe_alloc_mw_resp __user *uresp = NULL;
+
+ if (udata) {
+ if (udata->outlen < sizeof(*uresp))
+ return ERR_PTR(-EINVAL);
+ uresp = udata->outbuf;
+ }
+
+ if (unlikely((type != IB_MW_TYPE_1) &&
+ (type != IB_MW_TYPE_2)))
+ return ERR_PTR(-EINVAL);
+
+ rxe_add_ref(pd);
+
+ mw = rxe_alloc(&rxe->mw_pool);
+ if (unlikely(!mw)) {
+ rxe_drop_ref(pd);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ rxe_add_index(mw);
+ rxe_set_mw_rkey(mw); /* sets mw->ibmw.rkey */
+
+ spin_lock_init(&mw->lock);
+ mw->qp = NULL;
+ mw->mr = NULL;
+ mw->addr = 0;
+ mw->length = 0;
+ mw->ibmw.pd = ibpd;
+ mw->ibmw.type = type;
+ mw->state = (type == IB_MW_TYPE_2) ?
+ RXE_MEM_STATE_FREE :
+ RXE_MEM_STATE_VALID;
+
+ if (uresp) {
+ if (copy_to_user(&uresp->index, &mw->pelem.index,
+ sizeof(uresp->index))) {
+ rxe_drop_ref(mw);
+ rxe_drop_ref(pd);
+ return ERR_PTR(-EFAULT);
+ }
+ }
+
+ return &mw->ibmw;
+}
+
+int rxe_dealloc_mw(struct ib_mw *ibmw)
+{
+ struct rxe_mw *mw = to_rmw(ibmw);
+ struct rxe_pd *pd = to_rpd(ibmw->pd);
+ unsigned long flags;
+
+ spin_lock_irqsave(&mw->lock, flags);
+ mw->state = RXE_MEM_STATE_INVALID;
+ spin_unlock_irqrestore(&mw->lock, flags);
+
+ rxe_drop_ref(pd);
+ rxe_drop_ref(mw);
+
+ return 0;
+}
+
+void rxe_mw_cleanup(struct rxe_pool_entry *arg)
+{
+ struct rxe_mw *mw = container_of(arg, typeof(*mw), pelem);
+
+ rxe_drop_index(mw);
+ rxe_drop_key(mw);
+}
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c
index 30b8f037ee20..4bcb19a7b918 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.c
+++ b/drivers/infiniband/sw/rxe/rxe_pool.c
@@ -7,13 +7,12 @@
#include "rxe.h"
#include "rxe_loc.h"
-/* info about object pools
- */
+/* info about object pools */
struct rxe_type_info rxe_type_info[RXE_NUM_TYPES] = {
[RXE_TYPE_UC] = {
.name = "rxe-uc",
.size = sizeof(struct rxe_ucontext),
- .flags = RXE_POOL_NO_ALLOC,
+ .flags = RXE_POOL_NO_ALLOC,
},
[RXE_TYPE_PD] = {
.name = "rxe-pd",
@@ -43,23 +42,30 @@ struct rxe_type_info rxe_type_info[RXE_NUM_TYPES] = {
[RXE_TYPE_CQ] = {
.name = "rxe-cq",
.size = sizeof(struct rxe_cq),
- .flags = RXE_POOL_NO_ALLOC,
+ .flags = RXE_POOL_NO_ALLOC,
.cleanup = rxe_cq_cleanup,
},
[RXE_TYPE_MR] = {
.name = "rxe-mr",
.size = sizeof(struct rxe_mr),
.cleanup = rxe_mr_cleanup,
- .flags = RXE_POOL_INDEX,
+ .flags = RXE_POOL_INDEX
+ | RXE_POOL_KEY,
.max_index = RXE_MAX_MR_INDEX,
.min_index = RXE_MIN_MR_INDEX,
+ .key_offset = offsetof(struct rxe_mr, ibmr.lkey),
+ .key_size = sizeof(u32),
},
[RXE_TYPE_MW] = {
.name = "rxe-mw",
.size = sizeof(struct rxe_mw),
- .flags = RXE_POOL_INDEX,
+ .cleanup = rxe_mw_cleanup,
+ .flags = RXE_POOL_INDEX
+ | RXE_POOL_KEY,
.max_index = RXE_MAX_MW_INDEX,
.min_index = RXE_MIN_MW_INDEX,
+ .key_offset = offsetof(struct rxe_mw, ibmw.rkey),
+ .key_size = sizeof(u32),
},
[RXE_TYPE_MC_GRP] = {
.name = "rxe-mc_grp",
@@ -223,7 +229,7 @@ static void insert_index(struct rxe_pool *pool, struct rxe_pool_entry *new)
return;
}
-static void insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new)
+static int insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new)
{
struct rb_node **link = &pool->key.tree.rb_node;
struct rb_node *parent = NULL;
@@ -239,7 +245,7 @@ static void insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new)
if (cmp == 0) {
pr_warn("key already exists!\n");
- goto out;
+ return -EAGAIN;
}
if (cmp > 0)
@@ -250,20 +256,23 @@ static void insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new)
rb_link_node(&new->key_node, parent, link);
rb_insert_color(&new->key_node, &pool->key.tree);
-out:
- return;
+
+ return 0;
}
-void rxe_add_key(void *arg, void *key)
+int rxe_add_key(void *arg, void *key)
{
+ int ret;
struct rxe_pool_entry *elem = arg;
struct rxe_pool *pool = elem->pool;
unsigned long flags;
write_lock_irqsave(&pool->pool_lock, flags);
memcpy((u8 *)elem + pool->key.key_offset, key, pool->key.key_size);
- insert_key(pool, elem);
+ ret = insert_key(pool, elem);
write_unlock_irqrestore(&pool->pool_lock, flags);
+
+ return ret;
}
void rxe_drop_key(void *arg)
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.h b/drivers/infiniband/sw/rxe/rxe_pool.h
index 3d722aae5f15..5be975e3d5d3 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.h
+++ b/drivers/infiniband/sw/rxe/rxe_pool.h
@@ -122,7 +122,7 @@ void rxe_drop_index(void *elem);
/* assign a key to a keyed object and insert object into
* pool's rb tree
*/
-void rxe_add_key(void *elem, void *key);
+int rxe_add_key(void *elem, void *key);
/* remove elem from rb tree */
void rxe_drop_key(void *elem);
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 57236d8c2146..682f30bb3495 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -597,29 +597,29 @@ int rxe_requester(void *arg)
if (wqe->mask & WR_REG_MASK) {
if (wqe->wr.opcode == IB_WR_LOCAL_INV) {
struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
- struct rxe_mr *rmr;
+ struct rxe_mr *mr;
- rmr = rxe_pool_get_index(&rxe->mr_pool,
- wqe->wr.ex.invalidate_rkey >> 8);
- if (!rmr) {
+ mr = rxe_pool_get_key(&rxe->mr_pool,
+ &wqe->wr.ex.invalidate_rkey);
+ if (!mr) {
pr_err("No mr for key %#x\n",
wqe->wr.ex.invalidate_rkey);
wqe->state = wqe_state_error;
wqe->status = IB_WC_MW_BIND_ERR;
goto exit;
}
- rmr->state = RXE_MEM_STATE_FREE;
- rxe_drop_ref(rmr);
+ mr->state = RXE_MEM_STATE_FREE;
+ rxe_drop_ref(mr);
wqe->state = wqe_state_done;
wqe->status = IB_WC_SUCCESS;
} else if (wqe->wr.opcode == IB_WR_REG_MR) {
- struct rxe_mr *rmr = to_rmr(wqe->wr.wr.reg.mr);
+ struct rxe_mr *mr = to_rmr(wqe->wr.wr.reg.mr);
- rmr->state = RXE_MEM_STATE_VALID;
- rmr->access = wqe->wr.wr.reg.access;
- rmr->lkey = wqe->wr.wr.reg.key;
- rmr->rkey = wqe->wr.wr.reg.key;
- rmr->iova = wqe->wr.wr.reg.mr->iova;
+ mr->state = RXE_MEM_STATE_VALID;
+ mr->access = wqe->wr.wr.reg.access;
+ mr->lkey = wqe->wr.wr.reg.key;
+ mr->rkey = wqe->wr.wr.reg.key;
+ mr->iova = wqe->wr.wr.reg.mr->iova;
wqe->state = wqe_state_done;
wqe->status = IB_WC_SUCCESS;
} else {
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 69867bf39cfb..885b5bf6dc2e 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -888,8 +888,8 @@ static enum resp_states do_complete(struct rxe_qp *qp,
wc->wc_flags |= IB_WC_WITH_INVALIDATE;
wc->ex.invalidate_rkey = ieth_rkey(pkt);
- rmr = rxe_pool_get_index(&rxe->mr_pool,
- wc->ex.invalidate_rkey >> 8);
+ rmr = rxe_pool_get_key(&rxe->mr_pool,
+ &wc->ex.invalidate_rkey);
if (unlikely(!rmr)) {
pr_err("Bad rkey %#x invalidation\n",
wc->ex.invalidate_rkey);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 626706f25efc..96fea64ba02d 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -869,12 +869,14 @@ static struct ib_mr *rxe_get_dma_mr(struct ib_pd *ibpd, int access)
struct rxe_pd *pd = to_rpd(ibpd);
struct rxe_mr *mr;
+ rxe_add_ref(pd);
+
mr = rxe_alloc(&rxe->mr_pool);
- if (!mr)
+ if (!mr) {
+ rxe_drop_ref(pd);
return ERR_PTR(-ENOMEM);
+ }
- rxe_add_index(mr);
- rxe_add_ref(pd);
rxe_mr_init_dma(pd, access, mr);
return &mr->ibmr;
@@ -890,6 +892,17 @@ static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd,
struct rxe_dev *rxe = to_rdev(ibpd->device);
struct rxe_pd *pd = to_rpd(ibpd);
struct rxe_mr *mr;
+ struct rxe_reg_mr_resp __user *uresp = NULL;
+
+ if (udata) {
+ if (udata->outlen < sizeof(*uresp)) {
+ err = -EINVAL;
+ goto err1;
+ }
+ uresp = udata->outbuf;
+ }
+
+ rxe_add_ref(pd);
mr = rxe_alloc(&rxe->mr_pool);
if (!mr) {
@@ -897,22 +910,25 @@ static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd,
goto err2;
}
- rxe_add_index(mr);
-
- rxe_add_ref(pd);
-
err = rxe_mr_init_user(pd, start, length, iova,
- access, udata, mr);
+ access, udata, mr);
if (err)
goto err3;
- return &mr->ibmr;
+ if (uresp) {
+ if (copy_to_user(&uresp->index, &mr->pelem.index,
+ sizeof(uresp->index))) {
+ err = -EFAULT;
+ goto err3;
+ }
+ }
+ return &mr->ibmr;
err3:
- rxe_drop_ref(pd);
- rxe_drop_index(mr);
rxe_drop_ref(mr);
err2:
+ rxe_drop_ref(pd);
+err1:
return ERR_PTR(err);
}
@@ -922,7 +938,6 @@ static int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
mr->state = RXE_MEM_STATE_ZOMBIE;
rxe_drop_ref(mr->pd);
- rxe_drop_index(mr);
rxe_drop_ref(mr);
return 0;
}
@@ -938,16 +953,14 @@ static struct ib_mr *rxe_alloc_mr(struct ib_pd *ibpd, enum ib_mr_type mr_type,
if (mr_type != IB_MR_TYPE_MEM_REG)
return ERR_PTR(-EINVAL);
+ rxe_add_ref(pd);
+
mr = rxe_alloc(&rxe->mr_pool);
if (!mr) {
err = -ENOMEM;
goto err1;
}
- rxe_add_index(mr);
-
- rxe_add_ref(pd);
-
err = rxe_mr_init_fast(pd, max_num_sg, mr);
if (err)
goto err2;
@@ -955,10 +968,9 @@ static struct ib_mr *rxe_alloc_mr(struct ib_pd *ibpd, enum ib_mr_type mr_type,
return &mr->ibmr;
err2:
- rxe_drop_ref(pd);
- rxe_drop_index(mr);
rxe_drop_ref(mr);
err1:
+ rxe_drop_ref(pd);
return ERR_PTR(err);
}
@@ -1105,6 +1117,8 @@ static const struct ib_device_ops rxe_dev_ops = {
.reg_user_mr = rxe_reg_user_mr,
.req_notify_cq = rxe_req_notify_cq,
.resize_cq = rxe_resize_cq,
+ .alloc_mw = rxe_alloc_mw,
+ .dealloc_mw = rxe_dealloc_mw,
INIT_RDMA_OBJ_SIZE(ib_ah, rxe_ah, ibah),
INIT_RDMA_OBJ_SIZE(ib_cq, rxe_cq, ibcq),
@@ -1166,6 +1180,8 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name)
| BIT_ULL(IB_USER_VERBS_CMD_DESTROY_AH)
| BIT_ULL(IB_USER_VERBS_CMD_ATTACH_MCAST)
| BIT_ULL(IB_USER_VERBS_CMD_DETACH_MCAST)
+ | BIT_ULL(IB_USER_VERBS_CMD_ALLOC_MW)
+ | BIT_ULL(IB_USER_VERBS_CMD_DEALLOC_MW)
;
ib_set_device_ops(dev, &rxe_dev_ops);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index dbc649c9c43f..2233630fea7f 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -319,6 +319,9 @@ struct rxe_mr {
struct rxe_map **map;
};
+/* use high order bit to separate MW and MR rkeys */
+#define IS_MW (1 << 31)
+
struct rxe_mw {
struct rxe_pool_entry pelem;
struct ib_mw ibmw;
@@ -441,6 +444,11 @@ static inline struct rxe_mr *to_rmr(struct ib_mr *mr)
return mr ? container_of(mr, struct rxe_mr, ibmr) : NULL;
}
+static inline struct rxe_mw *to_rmw(struct ib_mw *mw)
+{
+ return mw ? container_of(mw, struct rxe_mw, ibmw) : NULL;
+}
+
int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name);
void rxe_mc_cleanup(struct rxe_pool_entry *arg);
diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h
index d8f2e0e46dab..4ad0fa0b2ab9 100644
--- a/include/uapi/rdma/rdma_user_rxe.h
+++ b/include/uapi/rdma/rdma_user_rxe.h
@@ -175,4 +175,14 @@ struct rxe_modify_srq_cmd {
__aligned_u64 mmap_info_addr;
};
+struct rxe_reg_mr_resp {
+ __u32 index;
+ __u32 reserved;
+};
+
+struct rxe_alloc_mw_resp {
+ __u32 index;
+ __u32 reserved;
+};
+
#endif /* RDMA_USER_RXE_H */
--
2.25.1
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH for-next v5 05/12] rdma_rxe: Add bind_mw and invalidate_mw verbs
2020-09-18 21:15 [PATCH for-next v5 00/12] rdma_rxe: API extensions Bob Pearson
` (3 preceding siblings ...)
2020-09-18 21:15 ` [PATCH for-next v5 04/12] rdma_rxe: Add alloc_mw and dealloc_mw verbs Bob Pearson
@ 2020-09-18 21:15 ` Bob Pearson
2020-09-18 21:15 ` [PATCH for-next v5 06/12] rdma_rxe: Add memory access through MWs Bob Pearson
` (7 subsequent siblings)
12 siblings, 0 replies; 23+ messages in thread
From: Bob Pearson @ 2020-09-18 21:15 UTC (permalink / raw)
To: jgg, zyjzyj2000, linux-rdma; +Cc: Bob Pearson
- Add code to implement ibv_bind_mw (for type 1 MWs) and
post send queue bind_mw (for type 2 MWs).
- Add code to implement local (post send) and remote
(send with invalidate) invalidate operations.
- Add rules checking for MW operations from IBA.
Signed-off-by: Bob Pearson <rpearson@hpe.com>
---
drivers/infiniband/sw/rxe/rxe_comp.c | 1 +
drivers/infiniband/sw/rxe/rxe_loc.h | 2 +
drivers/infiniband/sw/rxe/rxe_mr.c | 3 +-
drivers/infiniband/sw/rxe/rxe_mw.c | 289 ++++++++++++++++++++++++-
drivers/infiniband/sw/rxe/rxe_opcode.c | 11 +-
drivers/infiniband/sw/rxe/rxe_opcode.h | 1 -
drivers/infiniband/sw/rxe/rxe_req.c | 81 +++++--
drivers/infiniband/sw/rxe/rxe_verbs.c | 2 +-
drivers/infiniband/sw/rxe/rxe_verbs.h | 7 +
include/uapi/rdma/rdma_user_rxe.h | 34 ++-
10 files changed, 399 insertions(+), 32 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index 5dc86c9e74c2..8b81d3b24a8a 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -103,6 +103,7 @@ static enum ib_wc_opcode wr_to_wc_opcode(enum ib_wr_opcode opcode)
case IB_WR_RDMA_READ_WITH_INV: return IB_WC_RDMA_READ;
case IB_WR_LOCAL_INV: return IB_WC_LOCAL_INV;
case IB_WR_REG_MR: return IB_WC_REG_MR;
+ case IB_WR_BIND_MW: return IB_WC_BIND_MW;
default:
return 0xff;
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index 65f2e4a94956..d9a4004fddaa 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -117,6 +117,8 @@ int rxe_dealloc_mw(struct ib_mw *ibmw);
void rxe_mw_cleanup(struct rxe_pool_entry *arg);
+int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe);
+
/* rxe_net.c */
void rxe_loopback(struct sk_buff *skb);
int rxe_send(struct rxe_pkt_info *pkt, struct sk_buff *skb);
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index 4c53badfa4e9..f506dff25fdf 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -543,7 +543,8 @@ void rxe_mr_cleanup(struct rxe_pool_entry *arg)
struct rxe_mr *mr = container_of(arg, typeof(*mr), pelem);
int i;
- ib_umem_release(mr->umem);
+ if (mr->umem)
+ ib_umem_release(mr->umem);
if (mr->map) {
for (i = 0; i < mr->num_map; i++)
diff --git a/drivers/infiniband/sw/rxe/rxe_mw.c b/drivers/infiniband/sw/rxe/rxe_mw.c
index b818f1e869da..51bc71c98654 100644
--- a/drivers/infiniband/sw/rxe/rxe_mw.c
+++ b/drivers/infiniband/sw/rxe/rxe_mw.c
@@ -30,7 +30,7 @@ struct ib_mw *rxe_alloc_mw(struct ib_pd *ibpd, enum ib_mw_type type,
struct rxe_alloc_mw_resp __user *uresp = NULL;
if (udata) {
- if (udata->outlen < sizeof(*uresp))
+ if (unlikely(udata->outlen < sizeof(*uresp)))
return ERR_PTR(-EINVAL);
uresp = udata->outbuf;
}
@@ -62,10 +62,9 @@ struct ib_mw *rxe_alloc_mw(struct ib_pd *ibpd, enum ib_mw_type type,
RXE_MEM_STATE_VALID;
if (uresp) {
- if (copy_to_user(&uresp->index, &mw->pelem.index,
- sizeof(uresp->index))) {
+ if (unlikely(copy_to_user(&uresp->index, &mw->pelem.index,
+ sizeof(uresp->index)))) {
rxe_drop_ref(mw);
- rxe_drop_ref(pd);
return ERR_PTR(-EFAULT);
}
}
@@ -73,22 +72,298 @@ struct ib_mw *rxe_alloc_mw(struct ib_pd *ibpd, enum ib_mw_type type,
return &mw->ibmw;
}
+/* cleanup mw in case someone is still holding a ref */
+static void do_dealloc_mw(struct rxe_mw *mw)
+{
+ if (mw->mr) {
+ rxe_drop_ref(mw->mr);
+ atomic_dec(&mw->mr->num_mw);
+ mw->mr = NULL;
+ }
+
+ mw->qp = NULL;
+ mw->access = 0;
+ mw->addr = 0;
+ mw->length = 0;
+ mw->state = RXE_MEM_STATE_INVALID;
+}
+
int rxe_dealloc_mw(struct ib_mw *ibmw)
{
struct rxe_mw *mw = to_rmw(ibmw);
- struct rxe_pd *pd = to_rpd(ibmw->pd);
unsigned long flags;
spin_lock_irqsave(&mw->lock, flags);
- mw->state = RXE_MEM_STATE_INVALID;
+
+ do_dealloc_mw(mw);
+
+ spin_unlock_irqrestore(&mw->lock, flags);
+
+ rxe_drop_ref(mw);
+
+ return 0;
+}
+
+/* Check the rules for bind MW oepration. */
+static int check_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
+ struct rxe_mw *mw, struct rxe_mr *mr)
+{
+ /* check to see if bind operation came through
+ * ibv_bind_mw verbs API.
+ */
+ switch (mw->ibmw.type) {
+ case IB_MW_TYPE_1:
+ /* o10-37.2.34 */
+ if (unlikely(!(wqe->wr.wr.umw.flags & RXE_BIND_MW))) {
+ pr_err_once("attempt to bind type 1 MW with send WR\n");
+ return -EINVAL;
+ }
+ break;
+ case IB_MW_TYPE_2:
+ /* o10-37.2.35 */
+ if (unlikely(wqe->wr.wr.umw.flags & RXE_BIND_MW)) {
+ pr_err_once("attempt to bind type 2 MW with verbs API\n");
+ return -EINVAL;
+ }
+
+ /* C10-72 */
+ if (unlikely(qp->pd != to_rpd(mw->ibmw.pd))) {
+ pr_err_once("attempt to bind type 2 MW with qp with different PD\n");
+ return -EINVAL;
+ }
+
+ /* o10-37.2.40 */
+ if (unlikely(wqe->wr.wr.umw.length == 0)) {
+ pr_err_once("attempt to invalidate type 2 MW by binding with zero length\n");
+ return -EINVAL;
+ }
+
+ if (unlikely(!mr)) {
+ pr_err_once("attempt to bind MW to a NULL mr\n");
+ return -EINVAL;
+ }
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (unlikely((mw->ibmw.type == IB_MW_TYPE_1) &&
+ (mw->state != RXE_MEM_STATE_VALID))) {
+ pr_err_once("attempt to bind a type 1 MW not in the valid state\n");
+ return -EINVAL;
+ }
+
+ /* o10-36.2.2 */
+ if (unlikely((mw->access & IB_ZERO_BASED) &&
+ (mw->ibmw.type == IB_MW_TYPE_1))) {
+ pr_err_once("attempt to bind a zero based type 1 MW\n");
+ return -EINVAL;
+ }
+
+ if (unlikely((wqe->wr.wr.umw.rkey & 0xff) == (mw->ibmw.rkey & 0xff))) {
+ pr_err_once("attempt to bind MW with same key\n");
+ return -EINVAL;
+ }
+
+ /* remaining checks only apply to a nonzero MR */
+ if (!mr)
+ return 0;
+
+ if (unlikely(mr->access & IB_ZERO_BASED)) {
+ pr_err_once("attempt to bind MW to zero based MR\n");
+ return -EINVAL;
+ }
+
+ /* o10-37.2.30 */
+ if (unlikely((mw->ibmw.type == IB_MW_TYPE_2) &&
+ (mw->state != RXE_MEM_STATE_FREE))) {
+ pr_err_once("attempt to bind a type 2 MW not in the free state\n");
+ return -EINVAL;
+ }
+
+ /* C10-73 */
+ if (unlikely(!(mr->access & IB_ACCESS_MW_BIND))) {
+ pr_err_once("attempt to bind an MW to an MR without bind access\n");
+ return -EINVAL;
+ }
+
+ /* C10-74 */
+ if (unlikely((mw->access & (IB_ACCESS_REMOTE_WRITE |
+ IB_ACCESS_REMOTE_ATOMIC)) &&
+ !(mr->access & IB_ACCESS_LOCAL_WRITE))) {
+ pr_err_once("attempt to bind an writeable MW to an MR without local write access\n");
+ return -EINVAL;
+ }
+
+ /* C10-75 */
+ if (mw->access & IB_ZERO_BASED) {
+ if (unlikely(wqe->wr.wr.umw.length > mr->length)) {
+ pr_err_once("attempt to bind a ZB MW outside of the MR\n");
+ return -EINVAL;
+ }
+ } else {
+ if (unlikely((wqe->wr.wr.umw.addr < mr->iova) ||
+ ((wqe->wr.wr.umw.addr + wqe->wr.wr.umw.length) >
+ (mr->iova + mr->length)))) {
+ pr_err_once("attempt to bind a VA MW outside of the MR\n");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+static int do_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
+ struct rxe_mw *mw, struct rxe_mr *mr)
+{
+ u32 rkey;
+ u32 new_rkey;
+ struct rxe_mw *duplicate_mw;
+ struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
+
+ /* key part of new rkey is provided by user for type 2
+ * and ibv_bind_mw() for type 1 MWs
+ * there is a very rare chance that the new rkey will
+ * collide with an existing MW. Return an error if this
+ * occurs
+ */
+ rkey = mw->ibmw.rkey;
+ new_rkey = (rkey & 0xffffff00) | (wqe->wr.wr.umw.rkey & 0x000000ff);
+ duplicate_mw = rxe_pool_get_key(&rxe->mw_pool, &new_rkey);
+ if (duplicate_mw) {
+ pr_err_once("new MW key is a duplicate, try another\n");
+ rxe_drop_ref(duplicate_mw);
+ return -EINVAL;
+ }
+
+ rxe_drop_key(mw);
+ rxe_add_key(mw, &new_rkey);
+
+ mw->access = wqe->wr.wr.umw.access;
+ mw->state = RXE_MEM_STATE_VALID;
+ mw->addr = wqe->wr.wr.umw.addr;
+ mw->length = wqe->wr.wr.umw.length;
+
+ if (mw->mr) {
+ rxe_drop_ref(mw->mr);
+ atomic_dec(&mw->mr->num_mw);
+ mw->mr = NULL;
+ }
+
+ if (mw->length) {
+ mw->mr = mr;
+ atomic_inc(&mr->num_mw);
+ rxe_add_ref(mr);
+ }
+
+ if (mw->ibmw.type == IB_MW_TYPE_2)
+ mw->qp = qp;
+
+ return 0;
+}
+
+int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
+{
+ int ret;
+ struct rxe_mw *mw;
+ struct rxe_mr *mr;
+ struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
+ unsigned long flags;
+
+ if (qp->is_user) {
+ mw = rxe_pool_get_index(&rxe->mw_pool,
+ wqe->wr.wr.umw.mw_index);
+ if (!mw) {
+ pr_err_once("mw with index = %d not found\n",
+ wqe->wr.wr.umw.mw_index);
+ ret = -EINVAL;
+ goto err1;
+ }
+ mr = rxe_pool_get_index(&rxe->mr_pool,
+ wqe->wr.wr.umw.mr_index);
+ if (!mr && wqe->wr.wr.umw.length) {
+ pr_err_once("mr with index = %d not found\n",
+ wqe->wr.wr.umw.mr_index);
+ ret = -EINVAL;
+ goto err2;
+ }
+ } else {
+ mw = to_rmw(wqe->wr.wr.kmw.mw);
+ rxe_add_ref(mw);
+ if (wqe->wr.wr.kmw.mr) {
+ mr = to_rmr(wqe->wr.wr.kmw.mr);
+ rxe_add_ref(mr);
+ } else {
+ mr = NULL;
+ }
+ }
+
+ spin_lock_irqsave(&mw->lock, flags);
+
+ ret = check_bind_mw(qp, wqe, mw, mr);
+ if (ret)
+ goto err3;
+
+ ret = do_bind_mw(qp, wqe, mw, mr);
+err3:
spin_unlock_irqrestore(&mw->lock, flags);
- rxe_drop_ref(pd);
+ if (mr)
+ rxe_drop_ref(mr);
+err2:
rxe_drop_ref(mw);
+err1:
+ return ret;
+}
+
+static int check_invalidate_mw(struct rxe_qp *qp, struct rxe_mw *mw)
+{
+ if (unlikely(mw->state != RXE_MEM_STATE_VALID)) {
+ pr_err_once("attempt to invalidate a MW that is not valid\n");
+ return -EINVAL;
+ }
+
+ /* o10-37.2.26 */
+ if (unlikely(mw->ibmw.type == IB_MW_TYPE_1)) {
+ pr_err_once("attempt to invalidate a type 1 MW\n");
+ return -EINVAL;
+ }
return 0;
}
+static void do_invalidate_mw(struct rxe_mw *mw)
+{
+ mw->qp = NULL;
+
+ rxe_drop_ref(mw->mr);
+ atomic_dec(&mw->mr->num_mw);
+ mw->mr = NULL;
+
+ mw->access = 0;
+ mw->addr = 0;
+ mw->length = 0;
+ mw->state = RXE_MEM_STATE_FREE;
+}
+
+int rxe_invalidate_mw(struct rxe_qp *qp, struct rxe_mw *mw)
+{
+ int ret;
+ unsigned long flags;
+
+ spin_lock_irqsave(&mw->lock, flags);
+
+ ret = check_invalidate_mw(qp, mw);
+ if (ret)
+ goto err;
+
+ do_invalidate_mw(mw);
+err:
+ spin_unlock_irqrestore(&mw->lock, flags);
+
+ return ret;
+}
+
void rxe_mw_cleanup(struct rxe_pool_entry *arg)
{
struct rxe_mw *mw = container_of(arg, typeof(*mw), pelem);
diff --git a/drivers/infiniband/sw/rxe/rxe_opcode.c b/drivers/infiniband/sw/rxe/rxe_opcode.c
index 0cb4b01fd910..5532f01ae5a3 100644
--- a/drivers/infiniband/sw/rxe/rxe_opcode.c
+++ b/drivers/infiniband/sw/rxe/rxe_opcode.c
@@ -87,13 +87,20 @@ struct rxe_wr_opcode_info rxe_wr_opcode_info[] = {
[IB_WR_LOCAL_INV] = {
.name = "IB_WR_LOCAL_INV",
.mask = {
- [IB_QPT_RC] = WR_REG_MASK,
+ [IB_QPT_RC] = WR_LOCAL_MASK,
},
},
[IB_WR_REG_MR] = {
.name = "IB_WR_REG_MR",
.mask = {
- [IB_QPT_RC] = WR_REG_MASK,
+ [IB_QPT_RC] = WR_LOCAL_MASK,
+ },
+ },
+ [IB_WR_BIND_MW] = {
+ .name = "IB_WR_BIND_MW",
+ .mask = {
+ [IB_QPT_RC] = WR_LOCAL_MASK,
+ [IB_QPT_UC] = WR_LOCAL_MASK,
},
},
};
diff --git a/drivers/infiniband/sw/rxe/rxe_opcode.h b/drivers/infiniband/sw/rxe/rxe_opcode.h
index 1041ac9a9233..440e34f446bd 100644
--- a/drivers/infiniband/sw/rxe/rxe_opcode.h
+++ b/drivers/infiniband/sw/rxe/rxe_opcode.h
@@ -20,7 +20,6 @@ enum rxe_wr_mask {
WR_READ_MASK = BIT(3),
WR_WRITE_MASK = BIT(4),
WR_LOCAL_MASK = BIT(5),
- WR_REG_MASK = BIT(6),
WR_READ_OR_WRITE_MASK = WR_READ_MASK | WR_WRITE_MASK,
WR_READ_WRITE_OR_SEND_MASK = WR_READ_OR_WRITE_MASK | WR_SEND_MASK,
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 682f30bb3495..39ca88030d3a 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -524,9 +524,9 @@ static void save_state(struct rxe_send_wqe *wqe,
struct rxe_send_wqe *rollback_wqe,
u32 *rollback_psn)
{
- rollback_wqe->state = wqe->state;
+ rollback_wqe->state = wqe->state;
rollback_wqe->first_psn = wqe->first_psn;
- rollback_wqe->last_psn = wqe->last_psn;
+ rollback_wqe->last_psn = wqe->last_psn;
*rollback_psn = qp->req.psn;
}
@@ -559,6 +559,8 @@ static void update_state(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
int rxe_requester(void *arg)
{
struct rxe_qp *qp = (struct rxe_qp *)arg;
+ struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
+ struct rxe_mr *mr;
struct rxe_pkt_info pkt;
struct sk_buff *skb;
struct rxe_send_wqe *wqe;
@@ -594,11 +596,9 @@ int rxe_requester(void *arg)
if (unlikely(!wqe))
goto exit;
- if (wqe->mask & WR_REG_MASK) {
- if (wqe->wr.opcode == IB_WR_LOCAL_INV) {
- struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
- struct rxe_mr *mr;
-
+ if (wqe->mask & WR_LOCAL_MASK) {
+ switch (wqe->wr.opcode) {
+ case IB_WR_LOCAL_INV:
mr = rxe_pool_get_key(&rxe->mr_pool,
&wqe->wr.ex.invalidate_rkey);
if (!mr) {
@@ -606,15 +606,15 @@ int rxe_requester(void *arg)
wqe->wr.ex.invalidate_rkey);
wqe->state = wqe_state_error;
wqe->status = IB_WC_MW_BIND_ERR;
- goto exit;
+ goto err;
}
mr->state = RXE_MEM_STATE_FREE;
rxe_drop_ref(mr);
wqe->state = wqe_state_done;
wqe->status = IB_WC_SUCCESS;
- } else if (wqe->wr.opcode == IB_WR_REG_MR) {
- struct rxe_mr *mr = to_rmr(wqe->wr.wr.reg.mr);
-
+ break;
+ case IB_WR_REG_MR:
+ mr = to_rmr(wqe->wr.wr.reg.mr);
mr->state = RXE_MEM_STATE_VALID;
mr->access = wqe->wr.wr.reg.access;
mr->lkey = wqe->wr.wr.reg.key;
@@ -622,14 +622,30 @@ int rxe_requester(void *arg)
mr->iova = wqe->wr.wr.reg.mr->iova;
wqe->state = wqe_state_done;
wqe->status = IB_WC_SUCCESS;
- } else {
- goto exit;
+ break;
+ case IB_WR_BIND_MW:
+ ret = rxe_bind_mw(qp, wqe);
+ if (ret) {
+ wqe->state = wqe_state_done;
+ wqe->status = IB_WC_MW_BIND_ERR;
+ goto err;
+ }
+ wqe->state = wqe_state_done;
+ wqe->status = IB_WC_SUCCESS;
+ break;
+ default:
+ pr_err_once("unexpected LOCAL WR opcode = %d\n",
+ wqe->wr.opcode);
+ goto err;
}
+
+ qp->req.wqe_index = next_index(qp->sq.queue,
+ qp->req.wqe_index);
+
if ((wqe->wr.send_flags & IB_SEND_SIGNALED) ||
qp->sq_sig_type == IB_SIGNAL_ALL_WR)
rxe_run_task(&qp->comp.task, 1);
- qp->req.wqe_index = next_index(qp->sq.queue,
- qp->req.wqe_index);
+
goto next_wqe;
}
@@ -649,6 +665,7 @@ int rxe_requester(void *arg)
opcode = next_opcode(qp, wqe, wqe->wr.opcode);
if (unlikely(opcode < 0)) {
wqe->status = IB_WC_LOC_QP_OP_ERR;
+ /* TODO this should be goto err */
goto exit;
}
@@ -678,8 +695,7 @@ int rxe_requester(void *arg)
wqe->state = wqe_state_done;
wqe->status = IB_WC_SUCCESS;
__rxe_do_task(&qp->comp.task);
- rxe_drop_ref(qp);
- return 0;
+ goto again;
}
payload = mtu;
}
@@ -687,12 +703,14 @@ int rxe_requester(void *arg)
skb = init_req_packet(qp, wqe, opcode, payload, &pkt);
if (unlikely(!skb)) {
pr_err("qp#%d Failed allocating skb\n", qp_num(qp));
+ wqe->status = IB_WC_LOC_PROT_ERR;
goto err;
}
if (fill_packet(qp, wqe, &pkt, skb, payload)) {
pr_debug("qp#%d Error during fill packet\n", qp_num(qp));
kfree_skb(skb);
+ wqe->status = IB_WC_LOC_PROT_ERR;
goto err;
}
@@ -716,6 +734,7 @@ int rxe_requester(void *arg)
goto exit;
}
+ wqe->status = IB_WC_LOC_PROT_ERR;
goto err;
}
@@ -724,11 +743,35 @@ int rxe_requester(void *arg)
goto next_wqe;
err:
- wqe->status = IB_WC_LOC_PROT_ERR;
+ /* we come here if an error occurred while processing
+ * a send wqe. The completer will put the qp in error
+ * state and no more wqes will be processed unless
+ * the qp is cleaned up and restarted. We do not want
+ * to be called again
+ */
wqe->state = wqe_state_error;
__rxe_do_task(&qp->comp.task);
+ ret = -EAGAIN;
+ goto done;
exit:
+ /* we come here if either there are no more wqes in the send
+ * queue or we are blocked waiting for some resource or event.
+ * The current wqe will be restarted or new wqe started when
+ * there is work to do or we can complete the current wqe.
+ */
+ ret = -EAGAIN;
+ goto done;
+
+again:
+ /* we come here if we are done with the current wqe but want to
+ * get called again. Mostly we loop back to next wqe so should
+ * be all one way or the other
+ */
+ ret = 0;
+ goto done;
+
+done:
rxe_drop_ref(qp);
- return -EAGAIN;
+ return ret;
}
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 96fea64ba02d..21582507ed32 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -577,7 +577,7 @@ static int init_send_wqe(struct rxe_qp *qp, const struct ib_send_wr *ibwr,
p += sge->length;
}
- } else if (mask & WR_REG_MASK) {
+ } else if (mask & WR_LOCAL_MASK) {
wqe->mask = mask;
wqe->state = wqe_state_posted;
return 0;
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index 2233630fea7f..2fb5581edd8a 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -316,9 +316,16 @@ struct rxe_mr {
u32 max_buf;
u32 num_map;
+ atomic_t num_mw;
+
struct rxe_map **map;
};
+enum rxe_send_flags {
+ /* flag indicaes bind call came through verbs API */
+ RXE_BIND_MW = (1 << 0),
+};
+
/* use high order bit to separate MW and MR rkeys */
#define IS_MW (1 << 31)
diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h
index 4ad0fa0b2ab9..d49125682359 100644
--- a/include/uapi/rdma/rdma_user_rxe.h
+++ b/include/uapi/rdma/rdma_user_rxe.h
@@ -93,7 +93,39 @@ struct rxe_send_wr {
__u32 remote_qkey;
__u16 pkey_index;
} ud;
- /* reg is only used by the kernel and is not part of the uapi */
+ struct {
+ __aligned_u64 addr;
+ __aligned_u64 length;
+ union {
+ __u32 mr_index;
+ __aligned_u64 reserved1;
+ };
+ union {
+ __u32 mw_index;
+ __aligned_u64 reserved2;
+ };
+ __u32 rkey;
+ __u32 access;
+ __u32 flags;
+ } umw;
+ /* The following are only used by the kernel
+ * and are not part of the uapi
+ */
+ struct {
+ __aligned_u64 addr;
+ __aligned_u64 length;
+ union {
+ struct ib_mr *mr;
+ __aligned_u64 reserved1;
+ };
+ union {
+ struct ib_mw *mw;
+ __aligned_u64 reserved2;
+ };
+ __u32 rkey;
+ __u32 access;
+ __u32 flags;
+ } kmw;
struct {
union {
struct ib_mr *mr;
--
2.25.1
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH for-next v5 06/12] rdma_rxe: Add memory access through MWs
2020-09-18 21:15 [PATCH for-next v5 00/12] rdma_rxe: API extensions Bob Pearson
` (4 preceding siblings ...)
2020-09-18 21:15 ` [PATCH for-next v5 05/12] rdma_rxe: Add bind_mw and invalidate_mw verbs Bob Pearson
@ 2020-09-18 21:15 ` Bob Pearson
2020-09-19 3:52 ` kernel test robot
2020-09-18 21:15 ` [PATCH for-next v5 07/12] rdma_rxe: Add support for ibv_query_device_ex Bob Pearson
` (6 subsequent siblings)
12 siblings, 1 reply; 23+ messages in thread
From: Bob Pearson @ 2020-09-18 21:15 UTC (permalink / raw)
To: jgg, zyjzyj2000, linux-rdma; +Cc: Bob Pearson
Implement memory access through MWs.
Add rules checks from IBA.
Signed-off-by: Bob Pearson <rpearson@hpe.com>
---
drivers/infiniband/sw/rxe/rxe_loc.h | 17 +++---
drivers/infiniband/sw/rxe/rxe_mr.c | 74 ++++++++++++++++--------
drivers/infiniband/sw/rxe/rxe_mw.c | 57 +++++++++++++++---
drivers/infiniband/sw/rxe/rxe_req.c | 16 ++----
drivers/infiniband/sw/rxe/rxe_resp.c | 83 ++++++++++++++++++++-------
drivers/infiniband/sw/rxe/rxe_verbs.h | 1 +
6 files changed, 176 insertions(+), 72 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index d9a4004fddaa..bd8fe4086fd4 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -100,25 +100,28 @@ enum lookup_type {
lookup_remote,
};
-struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
- enum lookup_type type);
+int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
-int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length);
+int rxe_mr_check_access(struct rxe_qp *qp, struct rxe_mr *mr,
+ int access, u64 va, u32 resid);
void rxe_mr_cleanup(struct rxe_pool_entry *arg);
-int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
-
/* rxe_mw.c */
struct ib_mw *rxe_alloc_mw(struct ib_pd *ibpd, enum ib_mw_type type,
struct ib_udata *udata);
int rxe_dealloc_mw(struct ib_mw *ibmw);
-void rxe_mw_cleanup(struct rxe_pool_entry *arg);
-
int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe);
+int rxe_invalidate_mw(struct rxe_qp *qp, struct rxe_mw *mw);
+
+int rxe_mw_check_access(struct rxe_qp *qp, struct rxe_mw *mw,
+ int access, u64 va, u32 resid);
+
+void rxe_mw_cleanup(struct rxe_pool_entry *arg);
+
/* rxe_net.c */
void rxe_loopback(struct sk_buff *skb);
int rxe_send(struct rxe_pkt_info *pkt, struct sk_buff *skb);
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index f506dff25fdf..9a1fb125679a 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -21,7 +21,7 @@ static void rxe_set_mr_lkey(struct rxe_mr *mr)
goto again;
}
-int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length)
+static int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length)
{
switch (mr->type) {
case RXE_MR_TYPE_DMA:
@@ -380,6 +380,25 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length,
return err;
}
+static struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 lkey)
+{
+ struct rxe_mr *mr;
+ struct rxe_dev *rxe = to_rdev(pd->ibpd.device);
+
+ mr = rxe_pool_get_key(&rxe->mr_pool, &lkey);
+ if (!mr)
+ return NULL;
+
+ if (unlikely((mr->ibmr.lkey != lkey) || (mr->pd != pd) ||
+ (access && !(access & mr->access)) ||
+ (mr->state != RXE_MEM_STATE_VALID))) {
+ rxe_drop_ref(mr);
+ return NULL;
+ }
+
+ return mr;
+}
+
/* copy data in or out of a wqe, i.e. sg list
* under the control of a dma descriptor
*/
@@ -409,7 +428,7 @@ int copy_data(
}
if (sge->length && (offset < sge->length)) {
- mr = lookup_mr(pd, access, sge->lkey, lookup_local);
+ mr = lookup_mr(pd, access, sge->lkey);
if (!mr) {
err = -EINVAL;
goto err1;
@@ -434,8 +453,7 @@ int copy_data(
}
if (sge->length) {
- mr = lookup_mr(pd, access, sge->lkey,
- lookup_local);
+ mr = lookup_mr(pd, access, sge->lkey);
if (!mr) {
err = -EINVAL;
goto err1;
@@ -510,32 +528,38 @@ int advance_dma_data(struct rxe_dma_info *dma, unsigned int length)
return 0;
}
-/* (1) find the mr corresponding to lkey/rkey
- * depending on lookup_type
- * (2) verify that the (qp) pd matches the mr pd
- * (3) verify that the mr can support the requested access
- * (4) verify that mr state is valid
- */
-struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
- enum lookup_type type)
+int rxe_invalidate_mr(struct rxe_qp *qp, struct rxe_mr *mr)
{
- struct rxe_mr *mr;
- struct rxe_dev *rxe = to_rdev(pd->ibpd.device);
+ mr->state = RXE_MEM_STATE_FREE;
+ return 0;
+}
- mr = rxe_pool_get_key(&rxe->mr_pool, &key);
- if (!mr)
- return NULL;
+int rxe_mr_check_access(struct rxe_qp *qp, struct rxe_mr *mr,
+ int access, u64 va, u32 resid)
+{
+ int ret;
+ struct rxe_pd *pd = to_rpd(mr->ibmr.pd);
- if (unlikely((type == lookup_local && mr->lkey != key) ||
- (type == lookup_remote && mr->rkey != key) ||
- mr->pd != pd ||
- (access && !(access & mr->access)) ||
- mr->state != RXE_MEM_STATE_VALID)) {
- rxe_drop_ref(mr);
- mr = NULL;
+ if (unlikely(mr->state != RXE_MEM_STATE_VALID)) {
+ pr_err("attempt to access a MR that is not in the valid state\n");
+ return -EINVAL;
}
- return mr;
+ /* C10-56 */
+ if (unlikely(pd != qp->pd)) {
+ pr_err("attempt to access a MR with a different PD than the QP\n");
+ return -EINVAL;
+ }
+
+ /* C10-57 */
+ if (unlikely(access && !(access & mr->access))) {
+ pr_err("attempt to access a MR without required access rights\n");
+ return -EINVAL;
+ }
+
+ ret = mr_check_range(mr, va, resid);
+
+ return ret;
}
void rxe_mr_cleanup(struct rxe_pool_entry *arg)
diff --git a/drivers/infiniband/sw/rxe/rxe_mw.c b/drivers/infiniband/sw/rxe/rxe_mw.c
index 51bc71c98654..50f3152d3b57 100644
--- a/drivers/infiniband/sw/rxe/rxe_mw.c
+++ b/drivers/infiniband/sw/rxe/rxe_mw.c
@@ -318,11 +318,6 @@ int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
static int check_invalidate_mw(struct rxe_qp *qp, struct rxe_mw *mw)
{
- if (unlikely(mw->state != RXE_MEM_STATE_VALID)) {
- pr_err_once("attempt to invalidate a MW that is not valid\n");
- return -EINVAL;
- }
-
/* o10-37.2.26 */
if (unlikely(mw->ibmw.type == IB_MW_TYPE_1)) {
pr_err_once("attempt to invalidate a type 1 MW\n");
@@ -336,9 +331,11 @@ static void do_invalidate_mw(struct rxe_mw *mw)
{
mw->qp = NULL;
- rxe_drop_ref(mw->mr);
- atomic_dec(&mw->mr->num_mw);
- mw->mr = NULL;
+ if (mw->mr) {
+ atomic_dec(&mw->mr->num_mw);
+ mw->mr = NULL;
+ rxe_drop_ref(mw->mr);
+ }
mw->access = 0;
mw->addr = 0;
@@ -364,6 +361,50 @@ int rxe_invalidate_mw(struct rxe_qp *qp, struct rxe_mw *mw)
return ret;
}
+int rxe_mw_check_access(struct rxe_qp *qp, struct rxe_mw *mw,
+ int access, u64 va, u32 resid)
+{
+ struct rxe_pd *pd = to_rpd(mw->ibmw.pd);
+
+ if (unlikely(mw->state != RXE_MEM_STATE_VALID)) {
+ pr_err_once("attempt to access a MW that is not valid\n");
+ return -EINVAL;
+ }
+
+ /* C10-76.2.1 */
+ if (unlikely((mw->ibmw.type == IB_MW_TYPE_1) && (pd != qp->pd))) {
+ pr_err_once("attempt to access a type 1 MW with a different PD than the QP\n");
+ return -EINVAL;
+ }
+
+ /* o10-37.2.43 */
+ if (unlikely((mw->ibmw.type == IB_MW_TYPE_2) && (mw->qp != qp))) {
+ pr_err_once("attempt to access a type 2 MW that is associated with a different QP\n");
+ return -EINVAL;
+ }
+
+ /* C10-77 */
+ if (unlikely(access && !(access & mw->access))) {
+ pr_err_once("attempt to access a MW without sufficient access\n");
+ return -EINVAL;
+ }
+
+ if (mw->access & IB_ZERO_BASED) {
+ if (unlikely((va + resid) > mw->length)) {
+ pr_err_once("attempt to access a ZB MW out of bounds\n");
+ return -EINVAL;
+ }
+ } else {
+ if (unlikely((va < mw->addr) ||
+ ((va + resid) > (mw->addr + mw->length)))) {
+ pr_err_once("attempt to access a VA MW out of bounds\n");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
void rxe_mw_cleanup(struct rxe_pool_entry *arg)
{
struct rxe_mw *mw = container_of(arg, typeof(*mw), pelem);
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 39ca88030d3a..e0dc79b960fa 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -604,7 +604,6 @@ int rxe_requester(void *arg)
if (!mr) {
pr_err("No mr for key %#x\n",
wqe->wr.ex.invalidate_rkey);
- wqe->state = wqe_state_error;
wqe->status = IB_WC_MW_BIND_ERR;
goto err;
}
@@ -626,7 +625,6 @@ int rxe_requester(void *arg)
case IB_WR_BIND_MW:
ret = rxe_bind_mw(qp, wqe);
if (ret) {
- wqe->state = wqe_state_done;
wqe->status = IB_WC_MW_BIND_ERR;
goto err;
}
@@ -636,6 +634,7 @@ int rxe_requester(void *arg)
default:
pr_err_once("unexpected LOCAL WR opcode = %d\n",
wqe->wr.opcode);
+ wqe->status = IB_WC_LOC_QP_OP_ERR;
goto err;
}
@@ -679,13 +678,7 @@ int rxe_requester(void *arg)
payload = (mask & RXE_WRITE_OR_SEND) ? wqe->dma.resid : 0;
if (payload > mtu) {
if (qp_type(qp) == IB_QPT_UD) {
- /* C10-93.1.1: If the total sum of all the buffer lengths specified for a
- * UD message exceeds the MTU of the port as returned by QueryHCA, the CI
- * shall not emit any packets for this message. Further, the CI shall not
- * generate an error due to this condition.
- */
-
- /* fake a successful UD send */
+ /* C10-93.1.1: fake a successful UD send */
wqe->first_psn = qp->req.psn;
wqe->last_psn = qp->req.psn;
qp->req.psn = (qp->req.psn + 1) & BTH_PSN_MASK;
@@ -750,6 +743,8 @@ int rxe_requester(void *arg)
* to be called again
*/
wqe->state = wqe_state_error;
+ qp->req.wqe_index = next_index(qp->sq.queue,
+ qp->req.wqe_index);
__rxe_do_task(&qp->comp.task);
ret = -EAGAIN;
goto done;
@@ -765,8 +760,7 @@ int rxe_requester(void *arg)
again:
/* we come here if we are done with the current wqe but want to
- * get called again. Mostly we loop back to next wqe so should
- * be all one way or the other
+ * get called again.
*/
ret = 0;
goto done;
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 885b5bf6dc2e..136c7699fed3 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -391,6 +391,8 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
struct rxe_pkt_info *pkt)
{
struct rxe_mr *mr = NULL;
+ struct rxe_mw *mw = NULL;
+ struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
u64 va;
u32 rkey;
u32 resid;
@@ -398,6 +400,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
int mtu = qp->mtu;
enum resp_states state;
int access;
+ unsigned long flags;
if (pkt->mask & (RXE_READ_MASK | RXE_WRITE_MASK)) {
if (pkt->mask & RXE_RETH_MASK) {
@@ -405,6 +408,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
qp->resp.rkey = reth_rkey(pkt);
qp->resp.resid = reth_len(pkt);
qp->resp.length = reth_len(pkt);
+ qp->resp.offset = 0;
}
access = (pkt->mask & RXE_READ_MASK) ? IB_ACCESS_REMOTE_READ
: IB_ACCESS_REMOTE_WRITE;
@@ -412,6 +416,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
qp->resp.va = atmeth_va(pkt);
qp->resp.rkey = atmeth_rkey(pkt);
qp->resp.resid = sizeof(u64);
+ qp->resp.offset = 0;
access = IB_ACCESS_REMOTE_ATOMIC;
} else {
return RESPST_EXECUTE;
@@ -429,20 +434,46 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
resid = qp->resp.resid;
pktlen = payload_size(pkt);
- mr = lookup_mr(qp->pd, access, rkey, lookup_remote);
- if (!mr) {
- state = RESPST_ERR_RKEY_VIOLATION;
- goto err;
- }
+ /* check rkey on each packet because someone could
+ * have invalidated, deallocated or unregistered it
+ * since the last packet
+ */
+ if (rkey & IS_MW) {
+ mw = rxe_pool_get_key(&rxe->mw_pool, &rkey);
+ if (!mw) {
+ pr_err_once("no MW found with rkey = 0x%08x\n", rkey);
+ state = RESPST_ERR_RKEY_VIOLATION;
+ goto err;
+ }
- if (unlikely(mr->state == RXE_MEM_STATE_FREE)) {
- state = RESPST_ERR_RKEY_VIOLATION;
- goto err;
- }
+ spin_lock_irqsave(&mw->lock, flags);
+ if (rxe_mw_check_access(qp, mw, access, va, resid)) {
+ spin_unlock_irqrestore(&mw->lock, flags);
+ rxe_drop_ref(mw);
+ state = RESPST_ERR_RKEY_VIOLATION;
+ goto err;
+ }
+
+ mr = mw->mr;
+ rxe_add_ref(mr);
+
+ if (mw->access & IB_ZERO_BASED)
+ qp->resp.offset = mw->addr;
- if (mr_check_range(mr, va, resid)) {
- state = RESPST_ERR_RKEY_VIOLATION;
- goto err;
+ spin_unlock_irqrestore(&mw->lock, flags);
+ rxe_drop_ref(mw);
+ } else {
+ mr = rxe_pool_get_key(&rxe->mr_pool, &rkey);
+ if (!mr || (mr->rkey != rkey)) {
+ pr_err_once("no MR found with rkey = 0x%08x\n", rkey);
+ state = RESPST_ERR_RKEY_VIOLATION;
+ goto err;
+ }
+
+ if (rxe_mr_check_access(qp, mr, access, va, resid)) {
+ state = RESPST_ERR_RKEY_VIOLATION;
+ goto err;
+ }
}
if (pkt->mask & RXE_WRITE_MASK) {
@@ -498,8 +529,8 @@ static enum resp_states write_data_in(struct rxe_qp *qp,
int err;
int data_len = payload_size(pkt);
- err = rxe_mr_copy(qp->resp.mr, qp->resp.va, payload_addr(pkt),
- data_len, to_mr_obj, NULL);
+ err = rxe_mr_copy(qp->resp.mr, qp->resp.va + qp->resp.offset,
+ payload_addr(pkt), data_len, to_mr_obj, NULL);
if (err) {
rc = RESPST_ERR_RKEY_VIOLATION;
goto out;
@@ -518,7 +549,6 @@ static DEFINE_SPINLOCK(atomic_ops_lock);
static enum resp_states process_atomic(struct rxe_qp *qp,
struct rxe_pkt_info *pkt)
{
- u64 iova = atmeth_va(pkt);
u64 *vaddr;
enum resp_states ret;
struct rxe_mr *mr = qp->resp.mr;
@@ -528,7 +558,7 @@ static enum resp_states process_atomic(struct rxe_qp *qp,
goto out;
}
- vaddr = iova_to_vaddr(mr, iova, sizeof(u64));
+ vaddr = iova_to_vaddr(mr, qp->resp.va + qp->resp.offset, sizeof(u64));
/* check vaddr is 8 bytes aligned. */
if (!vaddr || (uintptr_t)vaddr & 7) {
@@ -653,8 +683,10 @@ static enum resp_states read_reply(struct rxe_qp *qp,
res->type = RXE_READ_MASK;
res->replay = 0;
- res->read.va = qp->resp.va;
- res->read.va_org = qp->resp.va;
+ res->read.va = qp->resp.va +
+ qp->resp.offset;
+ res->read.va_org = qp->resp.va +
+ qp->resp.offset;
res->first_psn = req_pkt->psn;
@@ -1300,7 +1332,10 @@ int rxe_responder(void *arg)
/* Class C */
do_class_ac_error(qp, AETH_NAK_REM_ACC_ERR,
IB_WC_REM_ACCESS_ERR);
- state = RESPST_COMPLETE;
+ if (qp->resp.wqe)
+ state = RESPST_COMPLETE;
+ else
+ state = RESPST_ACKNOWLEDGE;
} else {
qp->resp.drop_msg = 1;
if (qp->srq) {
@@ -1319,7 +1354,10 @@ int rxe_responder(void *arg)
/* Class C */
do_class_ac_error(qp, AETH_NAK_INVALID_REQ,
IB_WC_REM_INV_REQ_ERR);
- state = RESPST_COMPLETE;
+ if (qp->resp.wqe)
+ state = RESPST_COMPLETE;
+ else
+ state = RESPST_ACKNOWLEDGE;
} else if (qp->srq) {
/* UC/UD - class E */
qp->resp.status = IB_WC_REM_INV_REQ_ERR;
@@ -1335,7 +1373,10 @@ int rxe_responder(void *arg)
/* All, Class A. */
do_class_ac_error(qp, AETH_NAK_REM_OP_ERR,
IB_WC_LOC_QP_OP_ERR);
- state = RESPST_COMPLETE;
+ if (qp->resp.wqe)
+ state = RESPST_COMPLETE;
+ else
+ state = RESPST_ACKNOWLEDGE;
break;
case RESPST_ERR_CQ_OVERFLOW:
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index 2fb5581edd8a..b24a9a0878c2 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -183,6 +183,7 @@ struct rxe_resp_info {
/* RDMA read / atomic only */
u64 va;
+ u64 offset;
struct rxe_mr *mr;
u32 resid;
u32 rkey;
--
2.25.1
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH for-next v5 06/12] rdma_rxe: Add memory access through MWs
2020-09-18 21:15 ` [PATCH for-next v5 06/12] rdma_rxe: Add memory access through MWs Bob Pearson
@ 2020-09-19 3:52 ` kernel test robot
0 siblings, 0 replies; 23+ messages in thread
From: kernel test robot @ 2020-09-19 3:52 UTC (permalink / raw)
To: Bob Pearson, jgg, zyjzyj2000, linux-rdma
Cc: kbuild-all, clang-built-linux, Bob Pearson
[-- Attachment #1: Type: text/plain, Size: 9439 bytes --]
Hi Bob,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on rdma/for-next]
[also build test WARNING on v5.9-rc5 next-20200918]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Bob-Pearson/rdma_rxe-API-extensions/20200919-051909
base: https://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git for-next
config: riscv-randconfig-r031-20200917 (attached as .config)
compiler: clang version 12.0.0 (https://github.com/llvm/llvm-project ed79827aea444e6995fb3d36abc2bfd36331773c)
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# install riscv cross compiling tool for clang build
# apt-get install binutils-riscv64-linux-gnu
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=riscv
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
All warnings (new ones prefixed by >>):
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:556:9: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
return inb(addr);
^~~~~~~~~
arch/riscv/include/asm/io.h:54:76: note: expanded from macro 'inb'
#define inb(c) ({ u8 __v; __io_pbr(); __v = readb_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:87:48: note: expanded from macro 'readb_cpu'
#define readb_cpu(c) ({ u8 __r = __raw_readb(c); __r; })
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:564:9: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
return inw(addr);
^~~~~~~~~
arch/riscv/include/asm/io.h:55:76: note: expanded from macro 'inw'
#define inw(c) ({ u16 __v; __io_pbr(); __v = readw_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:88:76: note: expanded from macro 'readw_cpu'
#define readw_cpu(c) ({ u16 __r = le16_to_cpu((__force __le16)__raw_readw(c)); __r; })
^
include/uapi/linux/byteorder/little_endian.h:36:51: note: expanded from macro '__le16_to_cpu'
#define __le16_to_cpu(x) ((__force __u16)(__le16)(x))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:572:9: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
return inl(addr);
^~~~~~~~~
arch/riscv/include/asm/io.h:56:76: note: expanded from macro 'inl'
#define inl(c) ({ u32 __v; __io_pbr(); __v = readl_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:89:76: note: expanded from macro 'readl_cpu'
#define readl_cpu(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; })
^
include/uapi/linux/byteorder/little_endian.h:34:51: note: expanded from macro '__le32_to_cpu'
#define __le32_to_cpu(x) ((__force __u32)(__le32)(x))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:580:2: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
outb(value, addr);
^~~~~~~~~~~~~~~~~
arch/riscv/include/asm/io.h:58:68: note: expanded from macro 'outb'
#define outb(v,c) ({ __io_pbw(); writeb_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:91:52: note: expanded from macro 'writeb_cpu'
#define writeb_cpu(v, c) ((void)__raw_writeb((v), (c)))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:588:2: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
outw(value, addr);
^~~~~~~~~~~~~~~~~
arch/riscv/include/asm/io.h:59:68: note: expanded from macro 'outw'
#define outw(v,c) ({ __io_pbw(); writew_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:92:76: note: expanded from macro 'writew_cpu'
#define writew_cpu(v, c) ((void)__raw_writew((__force u16)cpu_to_le16(v), (c)))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:596:2: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
outl(value, addr);
^~~~~~~~~~~~~~~~~
arch/riscv/include/asm/io.h:60:68: note: expanded from macro 'outl'
#define outl(v,c) ({ __io_pbw(); writel_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:93:76: note: expanded from macro 'writel_cpu'
#define writel_cpu(v, c) ((void)__raw_writel((__force u32)cpu_to_le32(v), (c)))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:1017:55: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port;
~~~~~~~~~~ ^
>> drivers/infiniband/sw/rxe/rxe_mr.c:531:5: warning: no previous prototype for function 'rxe_invalidate_mr' [-Wmissing-prototypes]
int rxe_invalidate_mr(struct rxe_qp *qp, struct rxe_mr *mr)
^
drivers/infiniband/sw/rxe/rxe_mr.c:531:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
int rxe_invalidate_mr(struct rxe_qp *qp, struct rxe_mr *mr)
^
static
8 warnings generated.
# https://github.com/0day-ci/linux/commit/ea6524464bcccdce769f9a046224290a51dee110
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Bob-Pearson/rdma_rxe-API-extensions/20200919-051909
git checkout ea6524464bcccdce769f9a046224290a51dee110
vim +/rxe_invalidate_mr +531 drivers/infiniband/sw/rxe/rxe_mr.c
530
> 531 int rxe_invalidate_mr(struct rxe_qp *qp, struct rxe_mr *mr)
532 {
533 mr->state = RXE_MEM_STATE_FREE;
534 return 0;
535 }
536
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 40267 bytes --]
^ permalink raw reply [flat|nested] 23+ messages in thread* Re: [PATCH for-next v5 06/12] rdma_rxe: Add memory access through MWs
@ 2020-09-19 3:52 ` kernel test robot
0 siblings, 0 replies; 23+ messages in thread
From: kernel test robot @ 2020-09-19 3:52 UTC (permalink / raw)
To: kbuild-all
[-- Attachment #1: Type: text/plain, Size: 9594 bytes --]
Hi Bob,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on rdma/for-next]
[also build test WARNING on v5.9-rc5 next-20200918]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Bob-Pearson/rdma_rxe-API-extensions/20200919-051909
base: https://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git for-next
config: riscv-randconfig-r031-20200917 (attached as .config)
compiler: clang version 12.0.0 (https://github.com/llvm/llvm-project ed79827aea444e6995fb3d36abc2bfd36331773c)
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# install riscv cross compiling tool for clang build
# apt-get install binutils-riscv64-linux-gnu
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=riscv
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
All warnings (new ones prefixed by >>):
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:556:9: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
return inb(addr);
^~~~~~~~~
arch/riscv/include/asm/io.h:54:76: note: expanded from macro 'inb'
#define inb(c) ({ u8 __v; __io_pbr(); __v = readb_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:87:48: note: expanded from macro 'readb_cpu'
#define readb_cpu(c) ({ u8 __r = __raw_readb(c); __r; })
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:564:9: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
return inw(addr);
^~~~~~~~~
arch/riscv/include/asm/io.h:55:76: note: expanded from macro 'inw'
#define inw(c) ({ u16 __v; __io_pbr(); __v = readw_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:88:76: note: expanded from macro 'readw_cpu'
#define readw_cpu(c) ({ u16 __r = le16_to_cpu((__force __le16)__raw_readw(c)); __r; })
^
include/uapi/linux/byteorder/little_endian.h:36:51: note: expanded from macro '__le16_to_cpu'
#define __le16_to_cpu(x) ((__force __u16)(__le16)(x))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:572:9: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
return inl(addr);
^~~~~~~~~
arch/riscv/include/asm/io.h:56:76: note: expanded from macro 'inl'
#define inl(c) ({ u32 __v; __io_pbr(); __v = readl_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:89:76: note: expanded from macro 'readl_cpu'
#define readl_cpu(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; })
^
include/uapi/linux/byteorder/little_endian.h:34:51: note: expanded from macro '__le32_to_cpu'
#define __le32_to_cpu(x) ((__force __u32)(__le32)(x))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:580:2: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
outb(value, addr);
^~~~~~~~~~~~~~~~~
arch/riscv/include/asm/io.h:58:68: note: expanded from macro 'outb'
#define outb(v,c) ({ __io_pbw(); writeb_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:91:52: note: expanded from macro 'writeb_cpu'
#define writeb_cpu(v, c) ((void)__raw_writeb((v), (c)))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:588:2: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
outw(value, addr);
^~~~~~~~~~~~~~~~~
arch/riscv/include/asm/io.h:59:68: note: expanded from macro 'outw'
#define outw(v,c) ({ __io_pbw(); writew_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:92:76: note: expanded from macro 'writew_cpu'
#define writew_cpu(v, c) ((void)__raw_writew((__force u16)cpu_to_le16(v), (c)))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:596:2: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
outl(value, addr);
^~~~~~~~~~~~~~~~~
arch/riscv/include/asm/io.h:60:68: note: expanded from macro 'outl'
#define outl(v,c) ({ __io_pbw(); writel_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:93:76: note: expanded from macro 'writel_cpu'
#define writel_cpu(v, c) ((void)__raw_writel((__force u32)cpu_to_le32(v), (c)))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:1017:55: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port;
~~~~~~~~~~ ^
>> drivers/infiniband/sw/rxe/rxe_mr.c:531:5: warning: no previous prototype for function 'rxe_invalidate_mr' [-Wmissing-prototypes]
int rxe_invalidate_mr(struct rxe_qp *qp, struct rxe_mr *mr)
^
drivers/infiniband/sw/rxe/rxe_mr.c:531:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
int rxe_invalidate_mr(struct rxe_qp *qp, struct rxe_mr *mr)
^
static
8 warnings generated.
# https://github.com/0day-ci/linux/commit/ea6524464bcccdce769f9a046224290a51dee110
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Bob-Pearson/rdma_rxe-API-extensions/20200919-051909
git checkout ea6524464bcccdce769f9a046224290a51dee110
vim +/rxe_invalidate_mr +531 drivers/infiniband/sw/rxe/rxe_mr.c
530
> 531 int rxe_invalidate_mr(struct rxe_qp *qp, struct rxe_mr *mr)
532 {
533 mr->state = RXE_MEM_STATE_FREE;
534 return 0;
535 }
536
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org
[-- Attachment #2: config.gz --]
[-- Type: application/gzip, Size: 40267 bytes --]
^ permalink raw reply [flat|nested] 23+ messages in thread
* [PATCH for-next v5 07/12] rdma_rxe: Add support for ibv_query_device_ex
2020-09-18 21:15 [PATCH for-next v5 00/12] rdma_rxe: API extensions Bob Pearson
` (5 preceding siblings ...)
2020-09-18 21:15 ` [PATCH for-next v5 06/12] rdma_rxe: Add memory access through MWs Bob Pearson
@ 2020-09-18 21:15 ` Bob Pearson
2020-09-18 23:40 ` Jason Gunthorpe
2020-09-18 21:15 ` [PATCH for-next v5 08/12] rdma_rxe: Add support for extended CQ operations Bob Pearson
` (5 subsequent siblings)
12 siblings, 1 reply; 23+ messages in thread
From: Bob Pearson @ 2020-09-18 21:15 UTC (permalink / raw)
To: jgg, zyjzyj2000, linux-rdma; +Cc: Bob Pearson
Add code to initialize new struct members in
ib_device_attr as place holders.
Signed-off-by: Bob Pearson <rpearson@hpe.com>
---
drivers/infiniband/sw/rxe/rxe.c | 101 ++++++++++++++++++--------
drivers/infiniband/sw/rxe/rxe_verbs.c | 7 +-
2 files changed, 75 insertions(+), 33 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index fab291245366..8d2be78e72ef 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -38,40 +38,77 @@ void rxe_dealloc(struct ib_device *ib_dev)
/* initialize rxe device parameters */
static void rxe_init_device_param(struct rxe_dev *rxe)
{
- rxe->max_inline_data = RXE_MAX_INLINE_DATA;
-
- rxe->attr.vendor_id = RXE_VENDOR_ID;
- rxe->attr.max_mr_size = RXE_MAX_MR_SIZE;
- rxe->attr.page_size_cap = RXE_PAGE_SIZE_CAP;
- rxe->attr.max_qp = RXE_MAX_QP;
- rxe->attr.max_qp_wr = RXE_MAX_QP_WR;
- rxe->attr.device_cap_flags = RXE_DEVICE_CAP_FLAGS;
- rxe->attr.max_send_sge = RXE_MAX_SGE;
- rxe->attr.max_recv_sge = RXE_MAX_SGE;
- rxe->attr.max_sge_rd = RXE_MAX_SGE_RD;
- rxe->attr.max_cq = RXE_MAX_CQ;
- rxe->attr.max_cqe = (1 << RXE_MAX_LOG_CQE) - 1;
- rxe->attr.max_mr = RXE_MAX_MR;
- rxe->attr.max_mw = RXE_MAX_MW;
- rxe->attr.max_pd = RXE_MAX_PD;
- rxe->attr.max_qp_rd_atom = RXE_MAX_QP_RD_ATOM;
- rxe->attr.max_res_rd_atom = RXE_MAX_RES_RD_ATOM;
- rxe->attr.max_qp_init_rd_atom = RXE_MAX_QP_INIT_RD_ATOM;
- rxe->attr.atomic_cap = IB_ATOMIC_HCA;
- rxe->attr.max_mcast_grp = RXE_MAX_MCAST_GRP;
- rxe->attr.max_mcast_qp_attach = RXE_MAX_MCAST_QP_ATTACH;
- rxe->attr.max_total_mcast_qp_attach = RXE_MAX_TOT_MCAST_QP_ATTACH;
- rxe->attr.max_ah = RXE_MAX_AH;
- rxe->attr.max_srq = RXE_MAX_SRQ;
- rxe->attr.max_srq_wr = RXE_MAX_SRQ_WR;
- rxe->attr.max_srq_sge = RXE_MAX_SRQ_SGE;
- rxe->attr.max_fast_reg_page_list_len = RXE_MAX_FMR_PAGE_LIST_LEN;
- rxe->attr.max_pkeys = RXE_MAX_PKEYS;
- rxe->attr.local_ca_ack_delay = RXE_LOCAL_CA_ACK_DELAY;
- addrconf_addr_eui48((unsigned char *)&rxe->attr.sys_image_guid,
- rxe->ndev->dev_addr);
+ struct ib_device_attr *a = &rxe->attr;
+ rxe->max_inline_data = RXE_MAX_INLINE_DATA;
rxe->max_ucontext = RXE_MAX_UCONTEXT;
+
+ a->atomic_cap = IB_ATOMIC_HCA;
+ a->cq_caps.max_cq_moderation_count = 0;
+ a->cq_caps.max_cq_moderation_period = 0;
+ a->device_cap_flags = RXE_DEVICE_CAP_FLAGS;
+ a->fw_ver = 0;
+ a->hca_core_clock = 0;
+ a->hw_ver = 0;
+ a->local_ca_ack_delay = RXE_LOCAL_CA_ACK_DELAY;
+ a->masked_atomic_cap = 0;
+ a->max_ah = RXE_MAX_AH;
+ a->max_cqe = (1 << RXE_MAX_LOG_CQE) - 1;
+ a->max_cq = RXE_MAX_CQ;
+ a->max_dm_size = 0;
+ a->max_ee_init_rd_atom = 0;
+ a->max_ee = 0;
+ a->max_ee_rd_atom = 0;
+ a->max_fast_reg_page_list_len = RXE_MAX_FMR_PAGE_LIST_LEN;
+ a->max_mcast_grp = RXE_MAX_MCAST_GRP;
+ a->max_mcast_qp_attach = RXE_MAX_MCAST_QP_ATTACH;
+ a->max_mr = RXE_MAX_MR;
+ a->max_mr_size = RXE_MAX_MR_SIZE;
+ a->max_mw = RXE_MAX_MW;
+ a->max_pd = RXE_MAX_PD;
+ a->max_pi_fast_reg_page_list_len = 0;
+ a->max_pkeys = RXE_MAX_PKEYS;
+ a->max_qp_init_rd_atom = RXE_MAX_QP_INIT_RD_ATOM;
+ a->max_qp_rd_atom = RXE_MAX_QP_RD_ATOM;
+ a->max_qp = RXE_MAX_QP;
+ a->max_qp_wr = RXE_MAX_QP_WR;
+ a->max_raw_ethy_qp = 0;
+ a->max_raw_ipv6_qp = 0;
+ a->max_rdd = 0;
+ a->max_recv_sge = RXE_MAX_SGE;
+ a->max_res_rd_atom = RXE_MAX_RES_RD_ATOM;
+ a->max_send_sge = RXE_MAX_SGE;
+ a->max_sge_rd = RXE_MAX_SGE_RD;
+ a->max_sgl_rd = 0;
+ a->max_srq = RXE_MAX_SRQ;
+ a->max_srq_sge = RXE_MAX_SRQ_SGE;
+ a->max_srq_wr = RXE_MAX_SRQ_WR;
+ a->max_total_mcast_qp_attach = RXE_MAX_TOT_MCAST_QP_ATTACH;
+ a->max_wq_type_rq = 0;
+ a->odp_caps.general_caps = 0;
+ a->odp_caps.per_transport_caps.rc_odp_caps = 0;
+ a->odp_caps.per_transport_caps.uc_odp_caps = 0;
+ a->odp_caps.per_transport_caps.ud_odp_caps = 0;
+ a->odp_caps.per_transport_caps.xrc_odp_caps = 0;
+ a->page_size_cap = RXE_PAGE_SIZE_CAP;
+ a->raw_packet_caps = 0;
+ a->rss_caps.supported_qpts = 0;
+ a->rss_caps.max_rwq_indirection_tables = 0;
+ a->rss_caps.max_rwq_indirection_table_size = 0;
+ a->sig_guard_cap = 0;
+ a->sig_prot_cap = 0;
+ a->sys_image_guid = 0;
+ a->timestamp_mask = 0;
+ a->tm_caps.max_rndv_hdr_size = 0;
+ a->tm_caps.max_num_tags = 0;
+ a->tm_caps.flags = 0;
+ a->tm_caps.max_ops = 0;
+ a->tm_caps.max_sge = 0;
+ a->vendor_id = RXE_VENDOR_ID;
+ a->vendor_part_id = 0;
+
+ addrconf_addr_eui48((unsigned char *)&a->sys_image_guid,
+ rxe->ndev->dev_addr);
}
/* initialize port attributes */
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 21582507ed32..a77f2e0ef68f 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -1149,7 +1149,8 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name)
dma_coerce_mask_and_coherent(&dev->dev,
dma_get_required_mask(&dev->dev));
- dev->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT)
+ dev->uverbs_cmd_mask =
+ BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT)
| BIT_ULL(IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL)
| BIT_ULL(IB_USER_VERBS_CMD_QUERY_DEVICE)
| BIT_ULL(IB_USER_VERBS_CMD_QUERY_PORT)
@@ -1184,6 +1185,10 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name)
| BIT_ULL(IB_USER_VERBS_CMD_DEALLOC_MW)
;
+ dev->uverbs_ex_cmd_mask =
+ BIT_ULL(IB_USER_VERBS_EX_CMD_QUERY_DEVICE)
+ ;
+
ib_set_device_ops(dev, &rxe_dev_ops);
err = ib_device_set_netdev(&rxe->ib_dev, rxe->ndev, 1);
if (err)
--
2.25.1
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH for-next v5 07/12] rdma_rxe: Add support for ibv_query_device_ex
2020-09-18 21:15 ` [PATCH for-next v5 07/12] rdma_rxe: Add support for ibv_query_device_ex Bob Pearson
@ 2020-09-18 23:40 ` Jason Gunthorpe
0 siblings, 0 replies; 23+ messages in thread
From: Jason Gunthorpe @ 2020-09-18 23:40 UTC (permalink / raw)
To: Bob Pearson; +Cc: zyjzyj2000, linux-rdma, Bob Pearson
On Fri, Sep 18, 2020 at 04:15:12PM -0500, Bob Pearson wrote:
> Add code to initialize new struct members in
> ib_device_attr as place holders.
>
> Signed-off-by: Bob Pearson <rpearson@hpe.com>
> drivers/infiniband/sw/rxe/rxe.c | 101 ++++++++++++++++++--------
> drivers/infiniband/sw/rxe/rxe_verbs.c | 7 +-
> 2 files changed, 75 insertions(+), 33 deletions(-)
>
> diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
> index fab291245366..8d2be78e72ef 100644
> +++ b/drivers/infiniband/sw/rxe/rxe.c
> @@ -38,40 +38,77 @@ void rxe_dealloc(struct ib_device *ib_dev)
> /* initialize rxe device parameters */
> static void rxe_init_device_param(struct rxe_dev *rxe)
> {
> - rxe->max_inline_data = RXE_MAX_INLINE_DATA;
What actually changed here? Isn't dev_attr zero initialized?
> /* initialize port attributes */
> diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
> index 21582507ed32..a77f2e0ef68f 100644
> +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
> @@ -1149,7 +1149,8 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name)
> dma_coerce_mask_and_coherent(&dev->dev,
> dma_get_required_mask(&dev->dev));
>
> - dev->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT)
> + dev->uverbs_cmd_mask =
> + BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT)
> | BIT_ULL(IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL)
> | BIT_ULL(IB_USER_VERBS_CMD_QUERY_DEVICE)
> | BIT_ULL(IB_USER_VERBS_CMD_QUERY_PORT)
> @@ -1184,6 +1185,10 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name)
> | BIT_ULL(IB_USER_VERBS_CMD_DEALLOC_MW)
> ;
>
> + dev->uverbs_ex_cmd_mask =
> + BIT_ULL(IB_USER_VERBS_EX_CMD_QUERY_DEVICE)
> + ;
Hurm, I don't even know why we have this bit, did you see a reason?
Jason
^ permalink raw reply [flat|nested] 23+ messages in thread
* [PATCH for-next v5 08/12] rdma_rxe: Add support for extended CQ operations
2020-09-18 21:15 [PATCH for-next v5 00/12] rdma_rxe: API extensions Bob Pearson
` (6 preceding siblings ...)
2020-09-18 21:15 ` [PATCH for-next v5 07/12] rdma_rxe: Add support for ibv_query_device_ex Bob Pearson
@ 2020-09-18 21:15 ` Bob Pearson
2020-09-18 21:15 ` [PATCH for-next v5 09/12] rdma_rxe: Add support for extended QP operations Bob Pearson
` (4 subsequent siblings)
12 siblings, 0 replies; 23+ messages in thread
From: Bob Pearson @ 2020-09-18 21:15 UTC (permalink / raw)
To: jgg, zyjzyj2000, linux-rdma; +Cc: Bob Pearson
Add private members to user/kernel wc struct to carry
extensions used by cq_ex.
Add timestamps on completion.
Add ignore overrun support.
Add commands to user API bitmasks.
Signed-off-by: Bob Pearson <rpearson@hpe.com>
---
drivers/infiniband/sw/rxe/rxe_comp.c | 7 ++++-
drivers/infiniband/sw/rxe/rxe_resp.c | 20 +++++++++-----
drivers/infiniband/sw/rxe/rxe_verbs.c | 10 ++++---
drivers/infiniband/sw/rxe/rxe_verbs.h | 3 ++-
include/uapi/rdma/rdma_user_rxe.h | 38 ++++++++++++++++++++++-----
5 files changed, 58 insertions(+), 20 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index 8b81d3b24a8a..72745ffcf118 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -390,7 +390,7 @@ static void make_send_cqe(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
wc->byte_len = wqe->dma.length;
wc->qp = &qp->ibqp;
} else {
- struct ib_uverbs_wc *uwc = &cqe->uibwc;
+ struct rxe_uverbs_wc *uwc = &cqe->ruwc;
uwc->wr_id = wqe->wr.wr_id;
uwc->status = wqe->status;
@@ -400,6 +400,11 @@ static void make_send_cqe(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
uwc->wc_flags = IB_WC_WITH_IMM;
uwc->byte_len = wqe->dma.length;
uwc->qp_num = qp->ibqp.qp_num;
+ if (qp->scq->flags &
+ IB_UVERBS_CQ_FLAGS_TIMESTAMP_COMPLETION) {
+ uwc->timestamp = (u64)ktime_get();
+ uwc->realtime = (u64)ktime_get_real();
+ }
}
}
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 136c7699fed3..660f33318ec9 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -844,7 +844,7 @@ static enum resp_states do_complete(struct rxe_qp *qp,
{
struct rxe_cqe cqe;
struct ib_wc *wc = &cqe.ibwc;
- struct ib_uverbs_wc *uwc = &cqe.uibwc;
+ struct rxe_uverbs_wc *uwc = &cqe.ruwc;
struct rxe_recv_wqe *wqe = qp->resp.wqe;
struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
@@ -854,13 +854,13 @@ static enum resp_states do_complete(struct rxe_qp *qp,
memset(&cqe, 0, sizeof(cqe));
if (qp->rcq->is_user) {
- uwc->status = qp->resp.status;
- uwc->qp_num = qp->ibqp.qp_num;
- uwc->wr_id = wqe->wr_id;
+ uwc->status = qp->resp.status;
+ uwc->qp_num = qp->ibqp.qp_num;
+ uwc->wr_id = wqe->wr_id;
} else {
- wc->status = qp->resp.status;
- wc->qp = &qp->ibqp;
- wc->wr_id = wqe->wr_id;
+ wc->status = qp->resp.status;
+ wc->qp = &qp->ibqp;
+ wc->wr_id = wqe->wr_id;
}
if (wc->status == IB_WC_SUCCESS) {
@@ -895,6 +895,12 @@ static enum resp_states do_complete(struct rxe_qp *qp,
uwc->src_qp = deth_sqp(pkt);
uwc->port_num = qp->attr.port_num;
+
+ if (qp->rcq->flags &
+ IB_UVERBS_CQ_FLAGS_TIMESTAMP_COMPLETION) {
+ uwc->timestamp = (u64)ktime_get();
+ uwc->realtime = (u64)ktime_get_real();
+ }
} else {
struct sk_buff *skb = PKT_TO_SKB(pkt);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index a77f2e0ef68f..594d8353600a 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -749,7 +749,8 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
return err;
}
-static int rxe_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
+static int rxe_create_cq(struct ib_cq *ibcq,
+ const struct ib_cq_init_attr *attr,
struct ib_udata *udata)
{
int err;
@@ -764,13 +765,12 @@ static int rxe_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
uresp = udata->outbuf;
}
- if (attr->flags)
- return -EINVAL;
-
err = rxe_cq_chk_attr(rxe, NULL, attr->cqe, attr->comp_vector);
if (err)
return err;
+ cq->flags = attr->flags;
+
err = rxe_cq_from_init(rxe, cq, attr->cqe, attr->comp_vector, udata,
uresp);
if (err)
@@ -1187,6 +1187,8 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name)
dev->uverbs_ex_cmd_mask =
BIT_ULL(IB_USER_VERBS_EX_CMD_QUERY_DEVICE)
+ | BIT_ULL(IB_USER_VERBS_EX_CMD_CREATE_CQ)
+ | BIT_ULL(IB_USER_VERBS_EX_CMD_MODIFY_CQ)
;
ib_set_device_ops(dev, &rxe_dev_ops);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index b24a9a0878c2..784ae4102265 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -53,7 +53,7 @@ struct rxe_ah {
struct rxe_cqe {
union {
struct ib_wc ibwc;
- struct ib_uverbs_wc uibwc;
+ struct rxe_uverbs_wc ruwc;
};
};
@@ -62,6 +62,7 @@ struct rxe_cq {
struct rxe_pool_entry pelem;
struct rxe_queue *queue;
spinlock_t cq_lock;
+ u32 flags;
u8 notify;
bool is_dying;
int is_user;
diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h
index d49125682359..95352e050ab4 100644
--- a/include/uapi/rdma/rdma_user_rxe.h
+++ b/include/uapi/rdma/rdma_user_rxe.h
@@ -98,29 +98,27 @@ struct rxe_send_wr {
__aligned_u64 length;
union {
__u32 mr_index;
- __aligned_u64 reserved1;
+ __aligned_u64 pad1;
};
union {
__u32 mw_index;
- __aligned_u64 reserved2;
+ __aligned_u64 pad2;
};
__u32 rkey;
__u32 access;
__u32 flags;
} umw;
- /* The following are only used by the kernel
- * and are not part of the uapi
- */
+ /* below are only used by the kernel */
struct {
__aligned_u64 addr;
__aligned_u64 length;
union {
struct ib_mr *mr;
- __aligned_u64 reserved1;
+ __aligned_u64 reserved1;
};
union {
struct ib_mw *mw;
- __aligned_u64 reserved2;
+ __aligned_u64 reserved2;
};
__u32 rkey;
__u32 access;
@@ -184,6 +182,32 @@ struct rxe_recv_wqe {
struct rxe_dma_info dma;
};
+struct rxe_uverbs_wc {
+ /* keep these the same as ib_uverbs_wc */
+ __aligned_u64 wr_id;
+ __u32 status;
+ __u32 opcode;
+ __u32 vendor_err;
+ __u32 byte_len;
+ union {
+ __be32 imm_data;
+ __u32 invalidate_rkey;
+ } ex;
+ __u32 qp_num;
+ __u32 src_qp;
+ __u32 wc_flags;
+ __u16 pkey_index;
+ __u16 slid;
+ __u8 sl;
+ __u8 dlid_path_bits;
+ __u8 port_num;
+ __u8 reserved;
+
+ /* any extras go here */
+ __aligned_u64 timestamp;
+ __aligned_u64 realtime;
+};
+
struct rxe_create_cq_resp {
struct mminfo mi;
};
--
2.25.1
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH for-next v5 09/12] rdma_rxe: Add support for extended QP operations
2020-09-18 21:15 [PATCH for-next v5 00/12] rdma_rxe: API extensions Bob Pearson
` (7 preceding siblings ...)
2020-09-18 21:15 ` [PATCH for-next v5 08/12] rdma_rxe: Add support for extended CQ operations Bob Pearson
@ 2020-09-18 21:15 ` Bob Pearson
2020-09-18 23:40 ` Jason Gunthorpe
2020-09-18 21:15 ` [PATCH for-next v5 10/12] rdma_rxe: Fix pool related bugs Bob Pearson
` (3 subsequent siblings)
12 siblings, 1 reply; 23+ messages in thread
From: Bob Pearson @ 2020-09-18 21:15 UTC (permalink / raw)
To: jgg, zyjzyj2000, linux-rdma; +Cc: Bob Pearson
Add bits to user api command bitmask.
Signed-off-by: Bob Pearson <rpearson@hpe.com>
---
drivers/infiniband/sw/rxe/rxe_verbs.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 594d8353600a..7849d8d72d4c 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -1187,6 +1187,8 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name)
dev->uverbs_ex_cmd_mask =
BIT_ULL(IB_USER_VERBS_EX_CMD_QUERY_DEVICE)
+ | BIT_ULL(IB_USER_VERBS_EX_CMD_CREATE_QP)
+ | BIT_ULL(IB_USER_VERBS_EX_CMD_MODIFY_QP)
| BIT_ULL(IB_USER_VERBS_EX_CMD_CREATE_CQ)
| BIT_ULL(IB_USER_VERBS_EX_CMD_MODIFY_CQ)
;
--
2.25.1
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH for-next v5 09/12] rdma_rxe: Add support for extended QP operations
2020-09-18 21:15 ` [PATCH for-next v5 09/12] rdma_rxe: Add support for extended QP operations Bob Pearson
@ 2020-09-18 23:40 ` Jason Gunthorpe
0 siblings, 0 replies; 23+ messages in thread
From: Jason Gunthorpe @ 2020-09-18 23:40 UTC (permalink / raw)
To: Bob Pearson; +Cc: zyjzyj2000, linux-rdma, Bob Pearson
On Fri, Sep 18, 2020 at 04:15:14PM -0500, Bob Pearson wrote:
> Add bits to user api command bitmask.
>
> Signed-off-by: Bob Pearson <rpearson@hpe.com>
> drivers/infiniband/sw/rxe/rxe_verbs.c | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
> index 594d8353600a..7849d8d72d4c 100644
> +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
> @@ -1187,6 +1187,8 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name)
>
> dev->uverbs_ex_cmd_mask =
> BIT_ULL(IB_USER_VERBS_EX_CMD_QUERY_DEVICE)
> + | BIT_ULL(IB_USER_VERBS_EX_CMD_CREATE_QP)
> + | BIT_ULL(IB_USER_VERBS_EX_CMD_MODIFY_QP)
> | BIT_ULL(IB_USER_VERBS_EX_CMD_CREATE_CQ)
> | BIT_ULL(IB_USER_VERBS_EX_CMD_MODIFY_CQ)
> ;
Again I wonder if we should just set these always in the core code,
can you see a reason why not?
I really hate these cmd_masks and want to get rid of them anyhow
Jason
^ permalink raw reply [flat|nested] 23+ messages in thread
* [PATCH for-next v5 10/12] rdma_rxe: Fix pool related bugs
2020-09-18 21:15 [PATCH for-next v5 00/12] rdma_rxe: API extensions Bob Pearson
` (8 preceding siblings ...)
2020-09-18 21:15 ` [PATCH for-next v5 09/12] rdma_rxe: Add support for extended QP operations Bob Pearson
@ 2020-09-18 21:15 ` Bob Pearson
2020-09-18 23:49 ` Jason Gunthorpe
2020-09-18 21:15 ` [PATCH for-next v5 11/12] rdma_rxe: Fix mcast group allocation bug Bob Pearson
` (2 subsequent siblings)
12 siblings, 1 reply; 23+ messages in thread
From: Bob Pearson @ 2020-09-18 21:15 UTC (permalink / raw)
To: jgg, zyjzyj2000, linux-rdma; +Cc: Bob Pearson
This patch does following:
- Replace the rwlock used for pool->pool_lock by a spinlock.
Rwlock is a multi-reader single writer lock but there are
cases where a multi-writer lock is required, especially where
multiple objects can be created at the same time.
- Be more careful about type checking in pool APIs.
Originally each object used in rxe had a pool_entry struct as
the first member of it's struct. Since then about half have
it first and the other half have it later in the struct. The
pool APIs used void * as a hack to avoid type checking. This
patch changes the APIs so the pool_entry struct is position
independent. When used a parameter a macro is used to convert
the object pointer to the entry pointer. The offset of the entry
is stored for each pool and used to convert the entry address to
the object address.
- Provide locked and unlocked versions of the APIs.
The current code uses a lock in each API to allow atomic
updates to the pools. But some uses fail to work because they
combined multiple pool operations and expect them to be
atomic. As an example doing a lookup to see if a matching object
exists for a multicast group followed by a create of a new group
if it does not. By letting the caller take the pool lock and then
combine unlocked operations this problem is fixed.
- Replace calls to pool APIs with the typesafe versions.
- Replaced a few calls to pr_warn with pr_err_once.
Signed-off-by: Bob Pearson <rpearson@hpe.com>
---
drivers/infiniband/sw/rxe/rxe_cq.c | 12 +-
drivers/infiniband/sw/rxe/rxe_mcast.c | 4 +-
drivers/infiniband/sw/rxe/rxe_mr.c | 2 +-
drivers/infiniband/sw/rxe/rxe_mw.c | 18 ++-
drivers/infiniband/sw/rxe/rxe_pool.c | 220 ++++++++++++++++++--------
drivers/infiniband/sw/rxe/rxe_pool.h | 77 ++++++---
drivers/infiniband/sw/rxe/rxe_recv.c | 4 +-
drivers/infiniband/sw/rxe/rxe_req.c | 4 +-
drivers/infiniband/sw/rxe/rxe_resp.c | 8 +-
drivers/infiniband/sw/rxe/rxe_verbs.c | 10 +-
10 files changed, 238 insertions(+), 121 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c
index 43394c3f29d4..68b0753ad63f 100644
--- a/drivers/infiniband/sw/rxe/rxe_cq.c
+++ b/drivers/infiniband/sw/rxe/rxe_cq.c
@@ -14,21 +14,21 @@ int rxe_cq_chk_attr(struct rxe_dev *rxe, struct rxe_cq *cq,
int count;
if (cqe <= 0) {
- pr_warn("cqe(%d) <= 0\n", cqe);
+ pr_err_once("%s: cqe(%d) <= 0\n", __func__, cqe);
goto err1;
}
if (cqe > rxe->attr.max_cqe) {
- pr_warn("cqe(%d) > max_cqe(%d)\n",
- cqe, rxe->attr.max_cqe);
+ pr_err_once("%s: cqe(%d) > max_cqe(%d)\n",
+ __func__, cqe, rxe->attr.max_cqe);
goto err1;
}
if (cq) {
count = queue_count(cq->queue);
if (cqe < count) {
- pr_warn("cqe(%d) < current # elements in queue (%d)",
- cqe, count);
+ pr_err_once("%s: cqe(%d) < current # elements in queue (%d)",
+ __func__, cqe, count);
goto err1;
}
}
@@ -63,7 +63,7 @@ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe,
cq->queue = rxe_queue_init(rxe, &cqe,
sizeof(struct rxe_cqe));
if (!cq->queue) {
- pr_warn("unable to create cq\n");
+ pr_err_once("%s: unable to create cq\n", __func__);
return -ENOMEM;
}
diff --git a/drivers/infiniband/sw/rxe/rxe_mcast.c b/drivers/infiniband/sw/rxe/rxe_mcast.c
index c02315aed8d1..b09c6594045a 100644
--- a/drivers/infiniband/sw/rxe/rxe_mcast.c
+++ b/drivers/infiniband/sw/rxe/rxe_mcast.c
@@ -18,7 +18,7 @@ int rxe_mcast_get_grp(struct rxe_dev *rxe, union ib_gid *mgid,
goto err1;
}
- grp = rxe_pool_get_key(&rxe->mc_grp_pool, mgid);
+ grp = rxe_get_key(&rxe->mc_grp_pool, mgid);
if (grp)
goto done;
@@ -98,7 +98,7 @@ int rxe_mcast_drop_grp_elem(struct rxe_dev *rxe, struct rxe_qp *qp,
struct rxe_mc_grp *grp;
struct rxe_mc_elem *elem, *tmp;
- grp = rxe_pool_get_key(&rxe->mc_grp_pool, mgid);
+ grp = rxe_get_key(&rxe->mc_grp_pool, mgid);
if (!grp)
goto err1;
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index 9a1fb125679a..b3132b583446 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -385,7 +385,7 @@ static struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 lkey)
struct rxe_mr *mr;
struct rxe_dev *rxe = to_rdev(pd->ibpd.device);
- mr = rxe_pool_get_key(&rxe->mr_pool, &lkey);
+ mr = rxe_get_key(&rxe->mr_pool, &lkey);
if (!mr)
return NULL;
diff --git a/drivers/infiniband/sw/rxe/rxe_mw.c b/drivers/infiniband/sw/rxe/rxe_mw.c
index 50f3152d3b57..842e3b5c23e7 100644
--- a/drivers/infiniband/sw/rxe/rxe_mw.c
+++ b/drivers/infiniband/sw/rxe/rxe_mw.c
@@ -219,8 +219,10 @@ static int do_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
u32 rkey;
u32 new_rkey;
struct rxe_mw *duplicate_mw;
- struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
+ struct rxe_pool *pool = mw->pelem.pool;
+ unsigned long flags;
+ spin_lock_irqsave(&pool->pool_lock, flags);
/* key part of new rkey is provided by user for type 2
* and ibv_bind_mw() for type 1 MWs
* there is a very rare chance that the new rkey will
@@ -229,15 +231,17 @@ static int do_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
*/
rkey = mw->ibmw.rkey;
new_rkey = (rkey & 0xffffff00) | (wqe->wr.wr.umw.rkey & 0x000000ff);
- duplicate_mw = rxe_pool_get_key(&rxe->mw_pool, &new_rkey);
+ duplicate_mw = __get_key(pool, &new_rkey);
if (duplicate_mw) {
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
pr_err_once("new MW key is a duplicate, try another\n");
rxe_drop_ref(duplicate_mw);
return -EINVAL;
}
- rxe_drop_key(mw);
- rxe_add_key(mw, &new_rkey);
+ drop_key(mw);
+ add_key(mw, &new_rkey);
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
mw->access = wqe->wr.wr.umw.access;
mw->state = RXE_MEM_STATE_VALID;
@@ -271,16 +275,14 @@ int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
unsigned long flags;
if (qp->is_user) {
- mw = rxe_pool_get_index(&rxe->mw_pool,
- wqe->wr.wr.umw.mw_index);
+ mw = rxe_get_index(&rxe->mw_pool, wqe->wr.wr.umw.mw_index);
if (!mw) {
pr_err_once("mw with index = %d not found\n",
wqe->wr.wr.umw.mw_index);
ret = -EINVAL;
goto err1;
}
- mr = rxe_pool_get_index(&rxe->mr_pool,
- wqe->wr.wr.umw.mr_index);
+ mr = rxe_get_index(&rxe->mr_pool, wqe->wr.wr.umw.mr_index);
if (!mr && wqe->wr.wr.umw.length) {
pr_err_once("mr with index = %d not found\n",
wqe->wr.wr.umw.mr_index);
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c
index 4bcb19a7b918..974e26561087 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.c
+++ b/drivers/infiniband/sw/rxe/rxe_pool.c
@@ -12,21 +12,25 @@ struct rxe_type_info rxe_type_info[RXE_NUM_TYPES] = {
[RXE_TYPE_UC] = {
.name = "rxe-uc",
.size = sizeof(struct rxe_ucontext),
+ .elem_offset = offsetof(struct rxe_ucontext, pelem),
.flags = RXE_POOL_NO_ALLOC,
},
[RXE_TYPE_PD] = {
.name = "rxe-pd",
.size = sizeof(struct rxe_pd),
+ .elem_offset = offsetof(struct rxe_pd, pelem),
.flags = RXE_POOL_NO_ALLOC,
},
[RXE_TYPE_AH] = {
.name = "rxe-ah",
.size = sizeof(struct rxe_ah),
+ .elem_offset = offsetof(struct rxe_ah, pelem),
.flags = RXE_POOL_ATOMIC | RXE_POOL_NO_ALLOC,
},
[RXE_TYPE_SRQ] = {
.name = "rxe-srq",
.size = sizeof(struct rxe_srq),
+ .elem_offset = offsetof(struct rxe_srq, pelem),
.flags = RXE_POOL_INDEX | RXE_POOL_NO_ALLOC,
.min_index = RXE_MIN_SRQ_INDEX,
.max_index = RXE_MAX_SRQ_INDEX,
@@ -34,6 +38,7 @@ struct rxe_type_info rxe_type_info[RXE_NUM_TYPES] = {
[RXE_TYPE_QP] = {
.name = "rxe-qp",
.size = sizeof(struct rxe_qp),
+ .elem_offset = offsetof(struct rxe_qp, pelem),
.cleanup = rxe_qp_cleanup,
.flags = RXE_POOL_INDEX,
.min_index = RXE_MIN_QP_INDEX,
@@ -42,12 +47,14 @@ struct rxe_type_info rxe_type_info[RXE_NUM_TYPES] = {
[RXE_TYPE_CQ] = {
.name = "rxe-cq",
.size = sizeof(struct rxe_cq),
+ .elem_offset = offsetof(struct rxe_cq, pelem),
.flags = RXE_POOL_NO_ALLOC,
.cleanup = rxe_cq_cleanup,
},
[RXE_TYPE_MR] = {
.name = "rxe-mr",
.size = sizeof(struct rxe_mr),
+ .elem_offset = offsetof(struct rxe_mr, pelem),
.cleanup = rxe_mr_cleanup,
.flags = RXE_POOL_INDEX
| RXE_POOL_KEY,
@@ -59,6 +66,7 @@ struct rxe_type_info rxe_type_info[RXE_NUM_TYPES] = {
[RXE_TYPE_MW] = {
.name = "rxe-mw",
.size = sizeof(struct rxe_mw),
+ .elem_offset = offsetof(struct rxe_mw, pelem),
.cleanup = rxe_mw_cleanup,
.flags = RXE_POOL_INDEX
| RXE_POOL_KEY,
@@ -70,6 +78,7 @@ struct rxe_type_info rxe_type_info[RXE_NUM_TYPES] = {
[RXE_TYPE_MC_GRP] = {
.name = "rxe-mc_grp",
.size = sizeof(struct rxe_mc_grp),
+ .elem_offset = offsetof(struct rxe_mc_grp, pelem),
.cleanup = rxe_mc_cleanup,
.flags = RXE_POOL_KEY,
.key_offset = offsetof(struct rxe_mc_grp, mgid),
@@ -78,6 +87,7 @@ struct rxe_type_info rxe_type_info[RXE_NUM_TYPES] = {
[RXE_TYPE_MC_ELEM] = {
.name = "rxe-mc_elem",
.size = sizeof(struct rxe_mc_elem),
+ .elem_offset = offsetof(struct rxe_mc_elem, pelem),
.flags = RXE_POOL_ATOMIC,
},
};
@@ -139,7 +149,7 @@ int rxe_pool_init(
kref_init(&pool->ref_cnt);
- rwlock_init(&pool->pool_lock);
+ spin_lock_init(&pool->pool_lock);
if (rxe_type_info[type].flags & RXE_POOL_INDEX) {
err = rxe_pool_init_index(pool,
@@ -177,12 +187,12 @@ void rxe_pool_cleanup(struct rxe_pool *pool)
{
unsigned long flags;
- write_lock_irqsave(&pool->pool_lock, flags);
+ spin_lock_irqsave(&pool->pool_lock, flags);
pool->state = RXE_POOL_STATE_INVALID;
if (atomic_read(&pool->num_elem) > 0)
pr_warn("%s pool destroyed with unfree'd elem\n",
pool_name(pool));
- write_unlock_irqrestore(&pool->pool_lock, flags);
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
rxe_pool_put(pool);
}
@@ -241,7 +251,8 @@ static int insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new)
elem = rb_entry(parent, struct rxe_pool_entry, key_node);
cmp = memcmp((u8 *)elem + pool->key.key_offset,
- (u8 *)new + pool->key.key_offset, pool->key.key_size);
+ (u8 *)new + pool->key.key_offset,
+ pool->key.key_size);
if (cmp == 0) {
pr_warn("key already exists!\n");
@@ -260,70 +271,93 @@ static int insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new)
return 0;
}
-int rxe_add_key(void *arg, void *key)
+/* add/drop index and key are called through macros */
+int __add_key(struct rxe_pool_entry *elem, void *key)
{
int ret;
- struct rxe_pool_entry *elem = arg;
struct rxe_pool *pool = elem->pool;
- unsigned long flags;
- write_lock_irqsave(&pool->pool_lock, flags);
memcpy((u8 *)elem + pool->key.key_offset, key, pool->key.key_size);
ret = insert_key(pool, elem);
- write_unlock_irqrestore(&pool->pool_lock, flags);
return ret;
}
-void rxe_drop_key(void *arg)
+int __rxe_add_key(struct rxe_pool_entry *elem, void *key)
{
- struct rxe_pool_entry *elem = arg;
+ int ret;
struct rxe_pool *pool = elem->pool;
unsigned long flags;
- write_lock_irqsave(&pool->pool_lock, flags);
+ spin_lock_irqsave(&pool->pool_lock, flags);
+ ret = __add_key(elem, key);
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
+
+ return ret;
+}
+
+void __drop_key(struct rxe_pool_entry *elem)
+{
+ struct rxe_pool *pool = elem->pool;
+
rb_erase(&elem->key_node, &pool->key.tree);
- write_unlock_irqrestore(&pool->pool_lock, flags);
}
-void rxe_add_index(void *arg)
+
+void __rxe_drop_key(struct rxe_pool_entry *elem)
{
- struct rxe_pool_entry *elem = arg;
struct rxe_pool *pool = elem->pool;
unsigned long flags;
- write_lock_irqsave(&pool->pool_lock, flags);
+ spin_lock_irqsave(&pool->pool_lock, flags);
+ __drop_key(elem);
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
+}
+
+void __add_index(struct rxe_pool_entry *elem)
+{
+ struct rxe_pool *pool = elem->pool;
+
elem->index = alloc_index(pool);
insert_index(pool, elem);
- write_unlock_irqrestore(&pool->pool_lock, flags);
}
-void rxe_drop_index(void *arg)
+void __rxe_add_index(struct rxe_pool_entry *elem)
{
- struct rxe_pool_entry *elem = arg;
struct rxe_pool *pool = elem->pool;
unsigned long flags;
- write_lock_irqsave(&pool->pool_lock, flags);
+ spin_lock_irqsave(&pool->pool_lock, flags);
+ __add_index(elem);
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
+}
+
+void __drop_index(struct rxe_pool_entry *elem)
+{
+ struct rxe_pool *pool = elem->pool;
+
clear_bit(elem->index - pool->index.min_index, pool->index.table);
rb_erase(&elem->index_node, &pool->index.tree);
- write_unlock_irqrestore(&pool->pool_lock, flags);
}
-void *rxe_alloc(struct rxe_pool *pool)
+void __rxe_drop_index(struct rxe_pool_entry *elem)
{
- struct rxe_pool_entry *elem;
+ struct rxe_pool *pool = elem->pool;
unsigned long flags;
+ spin_lock_irqsave(&pool->pool_lock, flags);
+ __drop_index(elem);
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
+}
+
+int __add_to_pool(struct rxe_pool *pool, struct rxe_pool_entry *elem)
+{
might_sleep_if(!(pool->flags & RXE_POOL_ATOMIC));
- read_lock_irqsave(&pool->pool_lock, flags);
- if (pool->state != RXE_POOL_STATE_VALID) {
- read_unlock_irqrestore(&pool->pool_lock, flags);
- return NULL;
- }
+ if (pool->state != RXE_POOL_STATE_VALID)
+ return -EINVAL;
+
kref_get(&pool->ref_cnt);
- read_unlock_irqrestore(&pool->pool_lock, flags);
if (!ib_device_try_get(&pool->rxe->ib_dev))
goto out_put_pool;
@@ -331,38 +365,41 @@ void *rxe_alloc(struct rxe_pool *pool)
if (atomic_inc_return(&pool->num_elem) > pool->max_elem)
goto out_cnt;
- elem = kzalloc(rxe_type_info[pool->type].size,
- (pool->flags & RXE_POOL_ATOMIC) ?
- GFP_ATOMIC : GFP_KERNEL);
- if (!elem)
- goto out_cnt;
-
elem->pool = pool;
kref_init(&elem->ref_cnt);
- return elem;
-
+ return 0;
out_cnt:
atomic_dec(&pool->num_elem);
ib_device_put(&pool->rxe->ib_dev);
out_put_pool:
rxe_pool_put(pool);
- return NULL;
+ return -EINVAL;
}
-int rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_entry *elem)
+int __rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_entry *elem)
{
+ int err;
unsigned long flags;
+ spin_lock_irqsave(&pool->pool_lock, flags);
+ err = __add_to_pool(pool, elem);
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
+
+ return err;
+}
+
+void *__alloc(struct rxe_pool *pool)
+{
+ void *obj;
+ struct rxe_pool_entry *elem;
+
might_sleep_if(!(pool->flags & RXE_POOL_ATOMIC));
- read_lock_irqsave(&pool->pool_lock, flags);
- if (pool->state != RXE_POOL_STATE_VALID) {
- read_unlock_irqrestore(&pool->pool_lock, flags);
- return -EINVAL;
- }
+ if (pool->state != RXE_POOL_STATE_VALID)
+ return NULL;
+
kref_get(&pool->ref_cnt);
- read_unlock_irqrestore(&pool->pool_lock, flags);
if (!ib_device_try_get(&pool->rxe->ib_dev))
goto out_put_pool;
@@ -370,17 +407,40 @@ int rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_entry *elem)
if (atomic_inc_return(&pool->num_elem) > pool->max_elem)
goto out_cnt;
+ obj = kzalloc(rxe_type_info[pool->type].size,
+ (pool->flags & RXE_POOL_ATOMIC) ?
+ GFP_ATOMIC : GFP_KERNEL);
+ if (!obj)
+ goto out_cnt;
+
+ elem = (struct rxe_pool_entry *)((u8 *)obj +
+ rxe_type_info[pool->type].elem_offset);
+
elem->pool = pool;
kref_init(&elem->ref_cnt);
- return 0;
+ return obj;
out_cnt:
atomic_dec(&pool->num_elem);
ib_device_put(&pool->rxe->ib_dev);
out_put_pool:
rxe_pool_put(pool);
- return -EINVAL;
+ return NULL;
+}
+
+void *rxe_alloc(struct rxe_pool *pool)
+{
+ void *obj;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pool->pool_lock, flags);
+
+ obj = __alloc(pool);
+
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
+
+ return obj;
}
void rxe_elem_release(struct kref *kref)
@@ -394,21 +454,20 @@ void rxe_elem_release(struct kref *kref)
if (!(pool->flags & RXE_POOL_NO_ALLOC))
kfree(elem);
+
atomic_dec(&pool->num_elem);
ib_device_put(&pool->rxe->ib_dev);
rxe_pool_put(pool);
}
-void *rxe_pool_get_index(struct rxe_pool *pool, u32 index)
+void *__get_index(struct rxe_pool *pool, u32 index)
{
- struct rb_node *node = NULL;
+ struct rb_node *node;
struct rxe_pool_entry *elem = NULL;
- unsigned long flags;
-
- read_lock_irqsave(&pool->pool_lock, flags);
+ void *obj;
if (pool->state != RXE_POOL_STATE_VALID)
- goto out;
+ return NULL;
node = pool->index.tree.rb_node;
@@ -425,22 +484,32 @@ void *rxe_pool_get_index(struct rxe_pool *pool, u32 index)
}
}
-out:
- read_unlock_irqrestore(&pool->pool_lock, flags);
- return node ? elem : NULL;
+ obj = (u8 *)elem - rxe_type_info[pool->type].elem_offset;
+
+ return node ? obj : NULL;
}
-void *rxe_pool_get_key(struct rxe_pool *pool, void *key)
+void *rxe_get_index(struct rxe_pool *pool, u32 index)
{
- struct rb_node *node = NULL;
- struct rxe_pool_entry *elem = NULL;
- int cmp;
+ void *obj;
unsigned long flags;
- read_lock_irqsave(&pool->pool_lock, flags);
+ spin_lock_irqsave(&pool->pool_lock, flags);
+ obj = __get_index(pool, index);
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
+
+ return obj;
+}
+
+void *__get_key(struct rxe_pool *pool, void *key)
+{
+ struct rb_node *node;
+ struct rxe_pool_entry *elem = NULL;
+ int cmp;
+ void *obj;
if (pool->state != RXE_POOL_STATE_VALID)
- goto out;
+ return NULL;
node = pool->key.tree.rb_node;
@@ -450,18 +519,29 @@ void *rxe_pool_get_key(struct rxe_pool *pool, void *key)
cmp = memcmp((u8 *)elem + pool->key.key_offset,
key, pool->key.key_size);
- if (cmp > 0)
+ if (cmp > 0) {
node = node->rb_left;
- else if (cmp < 0)
+ } else if (cmp < 0) {
node = node->rb_right;
- else
+ } else {
+ kref_get(&elem->ref_cnt);
break;
+ }
}
- if (node)
- kref_get(&elem->ref_cnt);
+ obj = (u8 *)elem - rxe_type_info[pool->type].elem_offset;
-out:
- read_unlock_irqrestore(&pool->pool_lock, flags);
- return node ? elem : NULL;
+ return node ? obj : NULL;
+}
+
+void *rxe_get_key(struct rxe_pool *pool, void *key)
+{
+ void *obj;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pool->pool_lock, flags);
+ obj = __get_key(pool, key);
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
+
+ return obj;
}
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.h b/drivers/infiniband/sw/rxe/rxe_pool.h
index 5be975e3d5d3..9414b85e45ec 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.h
+++ b/drivers/infiniband/sw/rxe/rxe_pool.h
@@ -36,6 +36,7 @@ struct rxe_pool_entry;
struct rxe_type_info {
const char *name;
size_t size;
+ size_t elem_offset;
void (*cleanup)(struct rxe_pool_entry *obj);
enum rxe_pool_flags flags;
u32 max_index;
@@ -66,7 +67,7 @@ struct rxe_pool_entry {
struct rxe_pool {
struct rxe_dev *rxe;
- rwlock_t pool_lock; /* protects pool add/del/search */
+ spinlock_t pool_lock; /* protects pool add/del/search */
size_t elem_size;
struct kref ref_cnt;
void (*cleanup)(struct rxe_pool_entry *obj);
@@ -105,35 +106,69 @@ int rxe_pool_init(struct rxe_dev *rxe, struct rxe_pool *pool,
/* free resources from object pool */
void rxe_pool_cleanup(struct rxe_pool *pool);
-/* allocate an object from pool */
-void *rxe_alloc(struct rxe_pool *pool);
+/* in the following rxe_xxx() take pool->pool_lock
+ * and xxx() do not. Sequences of xxx() calls should be
+ * protected by taking the pool->pool_lock by caller
+ */
+void __add_index(struct rxe_pool_entry *elem);
-/* connect already allocated object to pool */
-int rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_entry *elem);
+#define add_index(obj) __add_index(&(obj)->pelem)
-/* assign an index to an indexed object and insert object into
- * pool's rb tree
- */
-void rxe_add_index(void *elem);
+void __rxe_add_index(struct rxe_pool_entry *elem);
+
+#define rxe_add_index(obj) __rxe_add_index(&(obj)->pelem)
+
+void __drop_index(struct rxe_pool_entry *elem);
+
+#define drop_index(obj) __drop_index(&(obj)->pelem)
+
+void __rxe_drop_index(struct rxe_pool_entry *elem);
+
+#define rxe_drop_index(obj) __rxe_drop_index(&(obj)->pelem)
+
+int __add_key(struct rxe_pool_entry *elem, void *key);
+
+#define add_key(obj, key) __add_key(&(obj)->pelem, key)
+
+int __rxe_add_key(struct rxe_pool_entry *elem, void *key);
-/* drop an index and remove object from rb tree */
-void rxe_drop_index(void *elem);
+#define rxe_add_key(obj, key) __rxe_add_key(&(obj)->pelem, key)
-/* assign a key to a keyed object and insert object into
- * pool's rb tree
+void __drop_key(struct rxe_pool_entry *elem);
+
+#define drop_key(obj) __drop_key(&(obj)->pelem)
+
+void __rxe_drop_key(struct rxe_pool_entry *elem);
+
+#define rxe_drop_key(obj) __rxe_drop_key(&(obj)->pelem)
+
+int __add_to_pool(struct rxe_pool *pool, struct rxe_pool_entry *elem);
+
+#define add_to_pool(pool, obj) __add_to_pool(pool, &(obj)->pelem)
+
+int __rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_entry *elem);
+
+#define rxe_add_to_pool(pool, obj) __rxe_add_to_pool(pool, &(obj)->pelem)
+
+/* the following routines allocate new objects or
+ * lookup objects from an index or key and return
+ * the address if found. the rxe_XXX() routines take the
+ * pool->pool_lock the __xxx() do not. Sequences of
+ * unprotected pool operations should be protected by
+ * taking the pool->pool_lock by the caller
*/
-int rxe_add_key(void *elem, void *key);
+void *__alloc(struct rxe_pool *pool);
+
+void *rxe_alloc(struct rxe_pool *pool);
+
+void *__get_index(struct rxe_pool *pool, u32 index);
-/* remove elem from rb tree */
-void rxe_drop_key(void *elem);
+void *rxe_get_index(struct rxe_pool *pool, u32 index);
-/* lookup an indexed object from index. takes a reference on object */
-void *rxe_pool_get_index(struct rxe_pool *pool, u32 index);
+void *__get_key(struct rxe_pool *pool, void *key);
-/* lookup keyed object from key. takes a reference on the object */
-void *rxe_pool_get_key(struct rxe_pool *pool, void *key);
+void *rxe_get_key(struct rxe_pool *pool, void *key);
-/* cleanup an object when all references are dropped */
void rxe_elem_release(struct kref *kref);
/* take a reference on an object */
diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c
index a3eed4da1540..50411b0069ba 100644
--- a/drivers/infiniband/sw/rxe/rxe_recv.c
+++ b/drivers/infiniband/sw/rxe/rxe_recv.c
@@ -185,7 +185,7 @@ static int hdr_check(struct rxe_pkt_info *pkt)
if (qpn != IB_MULTICAST_QPN) {
index = (qpn == 1) ? port->qp_gsi_index : qpn;
- qp = rxe_pool_get_index(&rxe->qp_pool, index);
+ qp = rxe_get_index(&rxe->qp_pool, index);
if (unlikely(!qp)) {
pr_warn_ratelimited("no qp matches qpn 0x%x\n", qpn);
goto err1;
@@ -242,7 +242,7 @@ static void rxe_rcv_mcast_pkt(struct rxe_dev *rxe, struct sk_buff *skb)
memcpy(&dgid, &ipv6_hdr(skb)->daddr, sizeof(dgid));
/* lookup mcast group corresponding to mgid, takes a ref */
- mcg = rxe_pool_get_key(&rxe->mc_grp_pool, &dgid);
+ mcg = rxe_get_key(&rxe->mc_grp_pool, &dgid);
if (!mcg)
goto err1; /* mcast group not registered */
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index e0dc79b960fa..42f5d286ca11 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -599,8 +599,8 @@ int rxe_requester(void *arg)
if (wqe->mask & WR_LOCAL_MASK) {
switch (wqe->wr.opcode) {
case IB_WR_LOCAL_INV:
- mr = rxe_pool_get_key(&rxe->mr_pool,
- &wqe->wr.ex.invalidate_rkey);
+ mr = rxe_get_key(&rxe->mr_pool,
+ &wqe->wr.ex.invalidate_rkey);
if (!mr) {
pr_err("No mr for key %#x\n",
wqe->wr.ex.invalidate_rkey);
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 660f33318ec9..046ffe5f331b 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -439,7 +439,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
* since the last packet
*/
if (rkey & IS_MW) {
- mw = rxe_pool_get_key(&rxe->mw_pool, &rkey);
+ mw = rxe_get_key(&rxe->mw_pool, &rkey);
if (!mw) {
pr_err_once("no MW found with rkey = 0x%08x\n", rkey);
state = RESPST_ERR_RKEY_VIOLATION;
@@ -463,7 +463,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
spin_unlock_irqrestore(&mw->lock, flags);
rxe_drop_ref(mw);
} else {
- mr = rxe_pool_get_key(&rxe->mr_pool, &rkey);
+ mr = rxe_get_key(&rxe->mr_pool, &rkey);
if (!mr || (mr->rkey != rkey)) {
pr_err_once("no MR found with rkey = 0x%08x\n", rkey);
state = RESPST_ERR_RKEY_VIOLATION;
@@ -926,8 +926,8 @@ static enum resp_states do_complete(struct rxe_qp *qp,
wc->wc_flags |= IB_WC_WITH_INVALIDATE;
wc->ex.invalidate_rkey = ieth_rkey(pkt);
- rmr = rxe_pool_get_key(&rxe->mr_pool,
- &wc->ex.invalidate_rkey);
+ rmr = rxe_get_key(&rxe->mr_pool,
+ &wc->ex.invalidate_rkey);
if (unlikely(!rmr)) {
pr_err("Bad rkey %#x invalidation\n",
wc->ex.invalidate_rkey);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 7849d8d72d4c..8f18b992983f 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -111,7 +111,7 @@ static int rxe_alloc_ucontext(struct ib_ucontext *uctx, struct ib_udata *udata)
struct rxe_dev *rxe = to_rdev(uctx->device);
struct rxe_ucontext *uc = to_ruc(uctx);
- return rxe_add_to_pool(&rxe->uc_pool, &uc->pelem);
+ return rxe_add_to_pool(&rxe->uc_pool, uc);
}
static void rxe_dealloc_ucontext(struct ib_ucontext *ibuc)
@@ -145,7 +145,7 @@ static int rxe_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
struct rxe_dev *rxe = to_rdev(ibpd->device);
struct rxe_pd *pd = to_rpd(ibpd);
- return rxe_add_to_pool(&rxe->pd_pool, &pd->pelem);
+ return rxe_add_to_pool(&rxe->pd_pool, pd);
}
static int rxe_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
@@ -169,7 +169,7 @@ static int rxe_create_ah(struct ib_ah *ibah,
if (err)
return err;
- err = rxe_add_to_pool(&rxe->ah_pool, &ah->pelem);
+ err = rxe_add_to_pool(&rxe->ah_pool, ah);
if (err)
return err;
@@ -275,7 +275,7 @@ static int rxe_create_srq(struct ib_srq *ibsrq, struct ib_srq_init_attr *init,
if (err)
goto err1;
- err = rxe_add_to_pool(&rxe->srq_pool, &srq->pelem);
+ err = rxe_add_to_pool(&rxe->srq_pool, srq);
if (err)
goto err1;
@@ -776,7 +776,7 @@ static int rxe_create_cq(struct ib_cq *ibcq,
if (err)
return err;
- return rxe_add_to_pool(&rxe->cq_pool, &cq->pelem);
+ return rxe_add_to_pool(&rxe->cq_pool, cq);
}
static int rxe_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
--
2.25.1
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH for-next v5 10/12] rdma_rxe: Fix pool related bugs
2020-09-18 21:15 ` [PATCH for-next v5 10/12] rdma_rxe: Fix pool related bugs Bob Pearson
@ 2020-09-18 23:49 ` Jason Gunthorpe
0 siblings, 0 replies; 23+ messages in thread
From: Jason Gunthorpe @ 2020-09-18 23:49 UTC (permalink / raw)
To: Bob Pearson; +Cc: zyjzyj2000, linux-rdma, Bob Pearson
On Fri, Sep 18, 2020 at 04:15:15PM -0500, Bob Pearson wrote:
> This patch does following:
> - Replace the rwlock used for pool->pool_lock by a spinlock.
> Rwlock is a multi-reader single writer lock but there are
> cases where a multi-writer lock is required, especially where
> multiple objects can be created at the same time.
Not sure what a multi-write lock is, sounds scary
> - Be more careful about type checking in pool APIs.
> Originally each object used in rxe had a pool_entry struct as
> the first member of it's struct. Since then about half have
> it first and the other half have it later in the struct. The
> pool APIs used void * as a hack to avoid type checking. This
> patch changes the APIs so the pool_entry struct is position
> independent. When used a parameter a macro is used to convert
> the object pointer to the entry pointer. The offset of the entry
> is stored for each pool and used to convert the entry address to
> the object address.
> - Provide locked and unlocked versions of the APIs.
> The current code uses a lock in each API to allow atomic
> updates to the pools. But some uses fail to work because they
> combined multiple pool operations and expect them to be
> atomic. As an example doing a lookup to see if a matching object
> exists for a multicast group followed by a create of a new group
> if it does not. By letting the caller take the pool lock and then
> combine unlocked operations this problem is fixed.
> - Replace calls to pool APIs with the typesafe versions.
> - Replaced a few calls to pr_warn with pr_err_once.
This probably needs to be split up
Jason
^ permalink raw reply [flat|nested] 23+ messages in thread
* [PATCH for-next v5 11/12] rdma_rxe: Fix mcast group allocation bug
2020-09-18 21:15 [PATCH for-next v5 00/12] rdma_rxe: API extensions Bob Pearson
` (9 preceding siblings ...)
2020-09-18 21:15 ` [PATCH for-next v5 10/12] rdma_rxe: Fix pool related bugs Bob Pearson
@ 2020-09-18 21:15 ` Bob Pearson
2020-09-18 21:15 ` [PATCH for-next v5 12/12] rdma_rxe: Fix bugs in the multicast receive path Bob Pearson
2020-09-18 23:51 ` [PATCH for-next v5 00/12] rdma_rxe: API extensions Jason Gunthorpe
12 siblings, 0 replies; 23+ messages in thread
From: Bob Pearson @ 2020-09-18 21:15 UTC (permalink / raw)
To: jgg, zyjzyj2000, linux-rdma; +Cc: Bob Pearson
This patch does the following:
- Cleans up multicast group create to use an atomic
sequence of lookup followed by allocate. This fixes an
error that occurred when two QPs were attempting to attach
to the same mcast address at the same time.
- Fixes a bug in rxe_mcast_get_grp not initializing err = 0.
If the group is found in get_key the routine can return an
uninitialized value to caller.
- Changes the variable elem to mce (for mcast elem).
This is less likely to confuse readers because of the ambiguity
with elem as pool element which is also used.
Signed-off-by: Bob Pearson <rpearson@hpe.com>
---
drivers/infiniband/sw/rxe/rxe_mcast.c | 108 ++++++++++++++------------
1 file changed, 60 insertions(+), 48 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_mcast.c b/drivers/infiniband/sw/rxe/rxe_mcast.c
index b09c6594045a..d8831757e91e 100644
--- a/drivers/infiniband/sw/rxe/rxe_mcast.c
+++ b/drivers/infiniband/sw/rxe/rxe_mcast.c
@@ -7,44 +7,56 @@
#include "rxe.h"
#include "rxe_loc.h"
-int rxe_mcast_get_grp(struct rxe_dev *rxe, union ib_gid *mgid,
- struct rxe_mc_grp **grp_p)
+/* caller should hold mc_grp_pool->pool_lock */
+static struct rxe_mc_grp *create_grp(struct rxe_dev *rxe,
+ struct rxe_pool *pool,
+ union ib_gid *mgid)
{
int err;
struct rxe_mc_grp *grp;
- if (rxe->attr.max_mcast_qp_attach == 0) {
- err = -EINVAL;
- goto err1;
- }
-
- grp = rxe_get_key(&rxe->mc_grp_pool, mgid);
- if (grp)
- goto done;
-
- grp = rxe_alloc(&rxe->mc_grp_pool);
- if (!grp) {
- err = -ENOMEM;
- goto err1;
- }
+ grp = __alloc(&rxe->mc_grp_pool);
+ if (unlikely(!grp))
+ return NULL;
INIT_LIST_HEAD(&grp->qp_list);
spin_lock_init(&grp->mcg_lock);
grp->rxe = rxe;
-
- rxe_add_key(grp, mgid);
+ add_key(grp, mgid);
err = rxe_mcast_add(rxe, mgid);
- if (err)
- goto err2;
+ if (unlikely(err)) {
+ drop_key(grp);
+ rxe_drop_ref(grp);
+ return NULL;
+ }
+ return grp;
+}
+
+/* atomically lookup or create mc group */
+int rxe_mcast_get_grp(struct rxe_dev *rxe, union ib_gid *mgid,
+ struct rxe_mc_grp **grp_p)
+{
+ int err = 0;
+ struct rxe_mc_grp *grp;
+ struct rxe_pool *pool = &rxe->mc_grp_pool;
+ unsigned long flags;
+
+ if (unlikely(rxe->attr.max_mcast_qp_attach == 0))
+ return -EINVAL;
+
+ spin_lock_irqsave(&pool->pool_lock, flags);
+ grp = __get_key(pool, mgid);
+ if (grp)
+ goto done;
+
+ grp = create_grp(rxe, pool, mgid);
+ if (unlikely(!grp))
+ err = -ENOMEM;
done:
+ spin_unlock_irqrestore(&pool->pool_lock, flags);
*grp_p = grp;
- return 0;
-
-err2:
- rxe_drop_ref(grp);
-err1:
return err;
}
@@ -52,13 +64,13 @@ int rxe_mcast_add_grp_elem(struct rxe_dev *rxe, struct rxe_qp *qp,
struct rxe_mc_grp *grp)
{
int err;
- struct rxe_mc_elem *elem;
+ struct rxe_mc_elem *mce;
/* check to see of the qp is already a member of the group */
spin_lock_bh(&qp->grp_lock);
spin_lock_bh(&grp->mcg_lock);
- list_for_each_entry(elem, &grp->qp_list, qp_list) {
- if (elem->qp == qp) {
+ list_for_each_entry(mce, &grp->qp_list, qp_list) {
+ if (mce->qp == qp) {
err = 0;
goto out;
}
@@ -69,8 +81,8 @@ int rxe_mcast_add_grp_elem(struct rxe_dev *rxe, struct rxe_qp *qp,
goto out;
}
- elem = rxe_alloc(&rxe->mc_elem_pool);
- if (!elem) {
+ mce = rxe_alloc(&rxe->mc_elem_pool);
+ if (!mce) {
err = -ENOMEM;
goto out;
}
@@ -79,11 +91,11 @@ int rxe_mcast_add_grp_elem(struct rxe_dev *rxe, struct rxe_qp *qp,
rxe_add_ref(grp);
grp->num_qp++;
- elem->qp = qp;
- elem->grp = grp;
+ mce->qp = qp;
+ mce->grp = grp;
- list_add(&elem->qp_list, &grp->qp_list);
- list_add(&elem->grp_list, &qp->grp_list);
+ list_add(&mce->qp_list, &grp->qp_list);
+ list_add(&mce->grp_list, &qp->grp_list);
err = 0;
out:
@@ -96,7 +108,7 @@ int rxe_mcast_drop_grp_elem(struct rxe_dev *rxe, struct rxe_qp *qp,
union ib_gid *mgid)
{
struct rxe_mc_grp *grp;
- struct rxe_mc_elem *elem, *tmp;
+ struct rxe_mc_elem *mce, *tmp;
grp = rxe_get_key(&rxe->mc_grp_pool, mgid);
if (!grp)
@@ -105,15 +117,15 @@ int rxe_mcast_drop_grp_elem(struct rxe_dev *rxe, struct rxe_qp *qp,
spin_lock_bh(&qp->grp_lock);
spin_lock_bh(&grp->mcg_lock);
- list_for_each_entry_safe(elem, tmp, &grp->qp_list, qp_list) {
- if (elem->qp == qp) {
- list_del(&elem->qp_list);
- list_del(&elem->grp_list);
+ list_for_each_entry_safe(mce, tmp, &grp->qp_list, qp_list) {
+ if (mce->qp == qp) {
+ list_del(&mce->qp_list);
+ list_del(&mce->grp_list);
grp->num_qp--;
spin_unlock_bh(&grp->mcg_lock);
spin_unlock_bh(&qp->grp_lock);
- rxe_drop_ref(elem);
+ rxe_drop_ref(mce);
rxe_drop_ref(grp); /* ref held by QP */
rxe_drop_ref(grp); /* ref from get_key */
return 0;
@@ -130,7 +142,7 @@ int rxe_mcast_drop_grp_elem(struct rxe_dev *rxe, struct rxe_qp *qp,
void rxe_drop_all_mcast_groups(struct rxe_qp *qp)
{
struct rxe_mc_grp *grp;
- struct rxe_mc_elem *elem;
+ struct rxe_mc_elem *mce;
while (1) {
spin_lock_bh(&qp->grp_lock);
@@ -138,24 +150,24 @@ void rxe_drop_all_mcast_groups(struct rxe_qp *qp)
spin_unlock_bh(&qp->grp_lock);
break;
}
- elem = list_first_entry(&qp->grp_list, struct rxe_mc_elem,
+ mce = list_first_entry(&qp->grp_list, struct rxe_mc_elem,
grp_list);
- list_del(&elem->grp_list);
+ list_del(&mce->grp_list);
spin_unlock_bh(&qp->grp_lock);
- grp = elem->grp;
+ grp = mce->grp;
spin_lock_bh(&grp->mcg_lock);
- list_del(&elem->qp_list);
+ list_del(&mce->qp_list);
grp->num_qp--;
spin_unlock_bh(&grp->mcg_lock);
rxe_drop_ref(grp);
- rxe_drop_ref(elem);
+ rxe_drop_ref(mce);
}
}
-void rxe_mc_cleanup(struct rxe_pool_entry *arg)
+void rxe_mc_cleanup(struct rxe_pool_entry *pelem)
{
- struct rxe_mc_grp *grp = container_of(arg, typeof(*grp), pelem);
+ struct rxe_mc_grp *grp = container_of(pelem, struct rxe_mc_grp, pelem);
struct rxe_dev *rxe = grp->rxe;
rxe_drop_key(grp);
--
2.25.1
^ permalink raw reply related [flat|nested] 23+ messages in thread* [PATCH for-next v5 12/12] rdma_rxe: Fix bugs in the multicast receive path
2020-09-18 21:15 [PATCH for-next v5 00/12] rdma_rxe: API extensions Bob Pearson
` (10 preceding siblings ...)
2020-09-18 21:15 ` [PATCH for-next v5 11/12] rdma_rxe: Fix mcast group allocation bug Bob Pearson
@ 2020-09-18 21:15 ` Bob Pearson
2020-09-18 23:51 ` [PATCH for-next v5 00/12] rdma_rxe: API extensions Jason Gunthorpe
12 siblings, 0 replies; 23+ messages in thread
From: Bob Pearson @ 2020-09-18 21:15 UTC (permalink / raw)
To: jgg, zyjzyj2000, linux-rdma; +Cc: Bob Pearson
This patch does the following
- Fix a bug in rxe_rcv.
The current code calls rxe_match_dgid which checks to see if the
destination ip address (dgid) matches one of the addresses in
the gid table. This is ok for unicast adfdresses but not mcast
addresses. Because of this all mcast packets were previously
dropped.
- Fix a bug in rxe_rcv_mcast_pkt.
The current code is just wrong. It assumed that it could pass
the same skb to rxe_rcv_pkt changing the qp pointer as it went
when multiple QPs were attached to the same mcast address. In
fact each QP needs a separate clone of the skb which it will
delete later.
Signed-off-by: Bob Pearson <rpearson@hpe.com>
---
drivers/infiniband/sw/rxe/rxe_recv.c | 60 +++++++++++++++++-----------
1 file changed, 36 insertions(+), 24 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c
index 50411b0069ba..3522b8c4a267 100644
--- a/drivers/infiniband/sw/rxe/rxe_recv.c
+++ b/drivers/infiniband/sw/rxe/rxe_recv.c
@@ -233,6 +233,8 @@ static void rxe_rcv_mcast_pkt(struct rxe_dev *rxe, struct sk_buff *skb)
struct rxe_mc_elem *mce;
struct rxe_qp *qp;
union ib_gid dgid;
+ struct sk_buff *per_qp_skb;
+ struct rxe_pkt_info *per_qp_pkt;
int err;
if (skb->protocol == htons(ETH_P_IP))
@@ -261,42 +263,37 @@ static void rxe_rcv_mcast_pkt(struct rxe_dev *rxe, struct sk_buff *skb)
if (err)
continue;
- /* if *not* the last qp in the list
- * increase the users of the skb then post to the next qp
+ /* for all but the last qp create a new clone of the
+ * skb and pass to the qp.
+ * This effectively reverts an earlier change
+ * which did not work. The pkt struct is contained
+ * in the skb so each time you changed pkt you also
+ * changed all the earlier pkts as well. Caused a mess.
*/
if (mce->qp_list.next != &mcg->qp_list)
- skb_get(skb);
+ per_qp_skb = skb_clone(skb, GFP_ATOMIC);
+ else
+ per_qp_skb = skb;
- pkt->qp = qp;
+ per_qp_pkt = SKB_TO_PKT(per_qp_skb);
+ per_qp_pkt->qp = qp;
rxe_add_ref(qp);
- rxe_rcv_pkt(pkt, skb);
+ rxe_rcv_pkt(per_qp_pkt, per_qp_skb);
}
spin_unlock_bh(&mcg->mcg_lock);
-
rxe_drop_ref(mcg); /* drop ref from rxe_pool_get_key. */
+ return;
err1:
kfree_skb(skb);
+ return;
}
-static int rxe_match_dgid(struct rxe_dev *rxe, struct sk_buff *skb)
+static int rxe_match_dgid(struct rxe_dev *rxe, struct sk_buff *skb,
+ union ib_gid *pdgid)
{
- struct rxe_pkt_info *pkt = SKB_TO_PKT(skb);
const struct ib_gid_attr *gid_attr;
- union ib_gid dgid;
- union ib_gid *pdgid;
-
- if (pkt->mask & RXE_LOOPBACK_MASK)
- return 0;
-
- if (skb->protocol == htons(ETH_P_IP)) {
- ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr,
- (struct in6_addr *)&dgid);
- pdgid = &dgid;
- } else {
- pdgid = (union ib_gid *)&ipv6_hdr(skb)->daddr;
- }
gid_attr = rdma_find_gid_by_port(&rxe->ib_dev, pdgid,
IB_GID_TYPE_ROCE_UDP_ENCAP,
@@ -314,17 +311,32 @@ void rxe_rcv(struct sk_buff *skb)
int err;
struct rxe_pkt_info *pkt = SKB_TO_PKT(skb);
struct rxe_dev *rxe = pkt->rxe;
+ union ib_gid dgid;
+ union ib_gid *pdgid;
__be32 *icrcp;
u32 calc_icrc, pack_icrc;
+ int is_mc;
pkt->offset = 0;
if (unlikely(skb->len < pkt->offset + RXE_BTH_BYTES))
goto drop;
- if (rxe_match_dgid(rxe, skb) < 0) {
- pr_warn_ratelimited("failed matching dgid\n");
- goto drop;
+ if (skb->protocol == htons(ETH_P_IP)) {
+ ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr,
+ (struct in6_addr *)&dgid);
+ pdgid = &dgid;
+ } else {
+ pdgid = (union ib_gid *)&ipv6_hdr(skb)->daddr;
+ }
+
+ is_mc = rdma_is_multicast_addr((struct in6_addr *)pdgid);
+
+ if (!(pkt->mask & RXE_LOOPBACK_MASK) && !is_mc) {
+ if (rxe_match_dgid(rxe, skb, pdgid) < 0) {
+ pr_warn_ratelimited("failed matching dgid\n");
+ goto drop;
+ }
}
pkt->opcode = bth_opcode(pkt);
--
2.25.1
^ permalink raw reply related [flat|nested] 23+ messages in thread* Re: [PATCH for-next v5 00/12] rdma_rxe: API extensions
2020-09-18 21:15 [PATCH for-next v5 00/12] rdma_rxe: API extensions Bob Pearson
` (11 preceding siblings ...)
2020-09-18 21:15 ` [PATCH for-next v5 12/12] rdma_rxe: Fix bugs in the multicast receive path Bob Pearson
@ 2020-09-18 23:51 ` Jason Gunthorpe
2020-09-19 8:44 ` Zhu Yanjun
12 siblings, 1 reply; 23+ messages in thread
From: Jason Gunthorpe @ 2020-09-18 23:51 UTC (permalink / raw)
To: Bob Pearson, Zhu Yanjun; +Cc: zyjzyj2000, linux-rdma, Bob Pearson
On Fri, Sep 18, 2020 at 04:15:05PM -0500, Bob Pearson wrote:
> This patch series is a collection of API extensions for the rdma_rxe driver.
> With this patch set installed there are no errors in pyverbs run-tests and
> 31 tests are skipped down from 56. The remaining skipped test cases include
> - XRC tests
> - ODP tests
> - Parent device tests
> - Import tests
> - Device memory
> - MLX5 specific tests
> - EFA tests
It seems like a big improvement! Thanks!
Zhu, can you look through this too?
Jason
> It continues from the previous (v4) set which implemented memory windows and
> has had a number of individual patches picked up in for-next.
>
> This set (v5) includes:
> Ported to current head of tree
> Memory windows patches not yet picked up
> kernel support for the extended user space APIs:
> - ibv_query_device_ex
> - ibv_create_cq_ex
> - ibv_create_qp_ex
> Fixes for multicast which is not currently working
I would like to progress the simple independent obviously OK bits,
could you split them out?
Jason
^ permalink raw reply [flat|nested] 23+ messages in thread* Re: [PATCH for-next v5 00/12] rdma_rxe: API extensions
2020-09-18 23:51 ` [PATCH for-next v5 00/12] rdma_rxe: API extensions Jason Gunthorpe
@ 2020-09-19 8:44 ` Zhu Yanjun
2020-09-19 8:46 ` Zhu Yanjun
0 siblings, 1 reply; 23+ messages in thread
From: Zhu Yanjun @ 2020-09-19 8:44 UTC (permalink / raw)
To: Jason Gunthorpe, Bob Pearson; +Cc: zyjzyj2000, linux-rdma, Bob Pearson
On 9/19/2020 7:51 AM, Jason Gunthorpe wrote:
> On Fri, Sep 18, 2020 at 04:15:05PM -0500, Bob Pearson wrote:
>> This patch series is a collection of API extensions for the rdma_rxe driver.
>> With this patch set installed there are no errors in pyverbs run-tests and
>> 31 tests are skipped down from 56. The remaining skipped test cases include
>> - XRC tests
>> - ODP tests
>> - Parent device tests
>> - Import tests
>> - Device memory
>> - MLX5 specific tests
>> - EFA tests
> It seems like a big improvement! Thanks!
>
> Zhu, can you look through this too?
OK. It seems that a problem occurred in this patch set.
Hi, Bob
Please fix this problem. Thanks a lot.
Zhu Yanjun
>
> Jason
>
>> It continues from the previous (v4) set which implemented memory windows and
>> has had a number of individual patches picked up in for-next.
>>
>> This set (v5) includes:
>> Ported to current head of tree
>> Memory windows patches not yet picked up
>> kernel support for the extended user space APIs:
>> - ibv_query_device_ex
>> - ibv_create_cq_ex
>> - ibv_create_qp_ex
>> Fixes for multicast which is not currently working
> I would like to progress the simple independent obviously OK bits,
> could you split them out?
>
> Jason
^ permalink raw reply [flat|nested] 23+ messages in thread
* Re: [PATCH for-next v5 00/12] rdma_rxe: API extensions
2020-09-19 8:44 ` Zhu Yanjun
@ 2020-09-19 8:46 ` Zhu Yanjun
2020-09-20 21:13 ` Bob Pearson
0 siblings, 1 reply; 23+ messages in thread
From: Zhu Yanjun @ 2020-09-19 8:46 UTC (permalink / raw)
To: Jason Gunthorpe, Bob Pearson; +Cc: linux-rdma, Bob Pearson
[-- Attachment #1: Type: text/plain, Size: 1536 bytes --]
On 9/19/2020 4:44 PM, Zhu Yanjun wrote:
>
> On 9/19/2020 7:51 AM, Jason Gunthorpe wrote:
>> On Fri, Sep 18, 2020 at 04:15:05PM -0500, Bob Pearson wrote:
>>> This patch series is a collection of API extensions for the rdma_rxe
>>> driver.
>>> With this patch set installed there are no errors in pyverbs
>>> run-tests and
>>> 31 tests are skipped down from 56. The remaining skipped test cases
>>> include
>>> - XRC tests
>>> - ODP tests
>>> - Parent device tests
>>> - Import tests
>>> - Device memory
>>> - MLX5 specific tests
>>> - EFA tests
>> It seems like a big improvement! Thanks!
>>
>> Zhu, can you look through this too?
>
> OK. It seems that a problem occurred in this patch set.
>
> Hi, Bob
>
> Please fix this problem. Thanks a lot.
The problem mail is in the attachment. Please check and fix it.
Zhu Yanjun
>
> Zhu Yanjun
>
>>
>> Jason
>>
>>> It continues from the previous (v4) set which implemented memory
>>> windows and
>>> has had a number of individual patches picked up in for-next.
>>>
>>> This set (v5) includes:
>>> Ported to current head of tree
>>> Memory windows patches not yet picked up
>>> kernel support for the extended user space APIs:
>>> - ibv_query_device_ex
>>> - ibv_create_cq_ex
>>> - ibv_create_qp_ex
>>> Fixes for multicast which is not currently working
>> I would like to progress the simple independent obviously OK bits,
>> could you split them out?
>>
>> Jason
[-- Attachment #2: Re [PATCH for-next v5 06_12] rdma_rxe Add memory access through MWs.eml --]
[-- Type: message/rfc822, Size: 68423 bytes --]
[-- Attachment #2.1.1: Type: text/plain, Size: 9439 bytes --]
Hi Bob,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on rdma/for-next]
[also build test WARNING on v5.9-rc5 next-20200918]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Bob-Pearson/rdma_rxe-API-extensions/20200919-051909
base: https://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git for-next
config: riscv-randconfig-r031-20200917 (attached as .config)
compiler: clang version 12.0.0 (https://github.com/llvm/llvm-project ed79827aea444e6995fb3d36abc2bfd36331773c)
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# install riscv cross compiling tool for clang build
# apt-get install binutils-riscv64-linux-gnu
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=riscv
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
All warnings (new ones prefixed by >>):
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:556:9: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
return inb(addr);
^~~~~~~~~
arch/riscv/include/asm/io.h:54:76: note: expanded from macro 'inb'
#define inb(c) ({ u8 __v; __io_pbr(); __v = readb_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:87:48: note: expanded from macro 'readb_cpu'
#define readb_cpu(c) ({ u8 __r = __raw_readb(c); __r; })
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:564:9: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
return inw(addr);
^~~~~~~~~
arch/riscv/include/asm/io.h:55:76: note: expanded from macro 'inw'
#define inw(c) ({ u16 __v; __io_pbr(); __v = readw_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:88:76: note: expanded from macro 'readw_cpu'
#define readw_cpu(c) ({ u16 __r = le16_to_cpu((__force __le16)__raw_readw(c)); __r; })
^
include/uapi/linux/byteorder/little_endian.h:36:51: note: expanded from macro '__le16_to_cpu'
#define __le16_to_cpu(x) ((__force __u16)(__le16)(x))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:572:9: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
return inl(addr);
^~~~~~~~~
arch/riscv/include/asm/io.h:56:76: note: expanded from macro 'inl'
#define inl(c) ({ u32 __v; __io_pbr(); __v = readl_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:89:76: note: expanded from macro 'readl_cpu'
#define readl_cpu(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; })
^
include/uapi/linux/byteorder/little_endian.h:34:51: note: expanded from macro '__le32_to_cpu'
#define __le32_to_cpu(x) ((__force __u32)(__le32)(x))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:580:2: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
outb(value, addr);
^~~~~~~~~~~~~~~~~
arch/riscv/include/asm/io.h:58:68: note: expanded from macro 'outb'
#define outb(v,c) ({ __io_pbw(); writeb_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:91:52: note: expanded from macro 'writeb_cpu'
#define writeb_cpu(v, c) ((void)__raw_writeb((v), (c)))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:588:2: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
outw(value, addr);
^~~~~~~~~~~~~~~~~
arch/riscv/include/asm/io.h:59:68: note: expanded from macro 'outw'
#define outw(v,c) ({ __io_pbw(); writew_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:92:76: note: expanded from macro 'writew_cpu'
#define writew_cpu(v, c) ((void)__raw_writew((__force u16)cpu_to_le16(v), (c)))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:596:2: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
outl(value, addr);
^~~~~~~~~~~~~~~~~
arch/riscv/include/asm/io.h:60:68: note: expanded from macro 'outl'
#define outl(v,c) ({ __io_pbw(); writel_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
~~~~~~~~~~ ^
arch/riscv/include/asm/mmio.h:93:76: note: expanded from macro 'writel_cpu'
#define writel_cpu(v, c) ((void)__raw_writel((__force u32)cpu_to_le32(v), (c)))
^
In file included from drivers/infiniband/sw/rxe/rxe_mr.c:7:
In file included from drivers/infiniband/sw/rxe/rxe.h:16:
In file included from include/linux/skbuff.h:31:
In file included from include/linux/dma-mapping.h:11:
In file included from include/linux/scatterlist.h:9:
In file included from arch/riscv/include/asm/io.h:148:
include/asm-generic/io.h:1017:55: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port;
~~~~~~~~~~ ^
>> drivers/infiniband/sw/rxe/rxe_mr.c:531:5: warning: no previous prototype for function 'rxe_invalidate_mr' [-Wmissing-prototypes]
int rxe_invalidate_mr(struct rxe_qp *qp, struct rxe_mr *mr)
^
drivers/infiniband/sw/rxe/rxe_mr.c:531:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
int rxe_invalidate_mr(struct rxe_qp *qp, struct rxe_mr *mr)
^
static
8 warnings generated.
# https://github.com/0day-ci/linux/commit/ea6524464bcccdce769f9a046224290a51dee110
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Bob-Pearson/rdma_rxe-API-extensions/20200919-051909
git checkout ea6524464bcccdce769f9a046224290a51dee110
vim +/rxe_invalidate_mr +531 drivers/infiniband/sw/rxe/rxe_mr.c
530
> 531 int rxe_invalidate_mr(struct rxe_qp *qp, struct rxe_mr *mr)
532 {
533 mr->state = RXE_MEM_STATE_FREE;
534 return 0;
535 }
536
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2.1.2: .config.gz --]
[-- Type: application/gzip, Size: 40267 bytes --]
^ permalink raw reply [flat|nested] 23+ messages in thread* Re: [PATCH for-next v5 00/12] rdma_rxe: API extensions
2020-09-19 8:46 ` Zhu Yanjun
@ 2020-09-20 21:13 ` Bob Pearson
2020-09-21 14:10 ` Jason Gunthorpe
0 siblings, 1 reply; 23+ messages in thread
From: Bob Pearson @ 2020-09-20 21:13 UTC (permalink / raw)
To: Zhu Yanjun, Jason Gunthorpe; +Cc: linux-rdma, Bob Pearson
On 9/19/20 3:46 AM, Zhu Yanjun wrote:
> On 9/19/2020 4:44 PM, Zhu Yanjun wrote:
>>
>> On 9/19/2020 7:51 AM, Jason Gunthorpe wrote:
>>> On Fri, Sep 18, 2020 at 04:15:05PM -0500, Bob Pearson wrote:
>>>> This patch series is a collection of API extensions for the rdma_rxe driver.
>>>> With this patch set installed there are no errors in pyverbs run-tests and
>>>> 31 tests are skipped down from 56. The remaining skipped test cases include
>>>> - XRC tests
>>>> - ODP tests
>>>> - Parent device tests
>>>> - Import tests
>>>> - Device memory
>>>> - MLX5 specific tests
>>>> - EFA tests
>>> It seems like a big improvement! Thanks!
>>>
>>> Zhu, can you look through this too?
>>
>> OK. It seems that a problem occurred in this patch set.
>>
>> Hi, Bob
>>
>> Please fix this problem. Thanks a lot.
>
> The problem mail is in the attachment. Please check and fix it.
>
> Zhu Yanjun
>
>>
>> Zhu Yanjun
>>
>>>
>>> Jason
>>>
>>>> It continues from the previous (v4) set which implemented memory windows and
>>>> has had a number of individual patches picked up in for-next.
>>>>
>>>> This set (v5) includes:
>>>> Ported to current head of tree
>>>> Memory windows patches not yet picked up
>>>> kernel support for the extended user space APIs:
>>>> - ibv_query_device_ex
>>>> - ibv_create_cq_ex
>>>> - ibv_create_qp_ex
>>>> Fixes for multicast which is not currently working
>>> I would like to progress the simple independent obviously OK bits,
>>> could you split them out?
>>>
>>> Jason
>
>
Zhu,
The missing prototype was a good catch. (That is resolved now.) But I can't figure out the null pointer arithmetic warnings. They are all in obscure distant header files. Do you have any insight about those?
Bob
^ permalink raw reply [flat|nested] 23+ messages in thread
* Re: [PATCH for-next v5 00/12] rdma_rxe: API extensions
2020-09-20 21:13 ` Bob Pearson
@ 2020-09-21 14:10 ` Jason Gunthorpe
0 siblings, 0 replies; 23+ messages in thread
From: Jason Gunthorpe @ 2020-09-21 14:10 UTC (permalink / raw)
To: Bob Pearson; +Cc: Zhu Yanjun, linux-rdma, Bob Pearson
On Sun, Sep 20, 2020 at 04:13:29PM -0500, Bob Pearson wrote:
> The missing prototype was a good catch. (That is resolved now.) But
> I can't figure out the null pointer arithmetic warnings. They are
> all in obscure distant header files. Do you have any insight about
> those?
Just ignore thouse
Jason
^ permalink raw reply [flat|nested] 23+ messages in thread