leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Revert "RDMA/rxe: Create duplicate mapping tables for FMRs"

Browse Source 
Below 2 commits will be reverted:
 commit 8ff5f5d9d8 ("RDMA/rxe: Prevent double freeing rxe_map_set()")
 commit 647bf13ce9 ("RDMA/rxe: Create duplicate mapping tables for FMRs")

The community has a few bug reports which pointed this commit at last.
Some proposals are raised up in the meantime but all of them have no
follow-up operation.

The previous commit led the map_set of FMR to be not available any more if
the MR is registered again after invalidating. Although the mentioned
patch try to fix a potential race in building/accessing the same table
for fast memory regions, it broke rtrs etc ULPs. Since the latter could
be worse, revert this patch.

With previous commit, it's observed that a same MR in rnbd server will
trigger below code path:
 -> rxe_mr_init_fast()
 |-> alloc map_set() # map_set is uninitialized
 |...-> rxe_map_mr_sg() # build the map_set
     |-> rxe_mr_set_page()
 |...-> rxe_reg_fast_mr() # mr->state change to VALID from FREE that means
                          # we can access host memory(such rxe_mr_copy)
 |...-> rxe_invalidate_mr() # mr->state change to FREE from VALID
 |...-> rxe_reg_fast_mr() # mr->state change to VALID from FREE,
                          # but map_set was not built again
 |...-> rxe_mr_copy() # kernel crash due to access wild addresses
                      # that lookup from the map_set

The backtraces are not always identical.
[1st]----------
  RIP: 0010:lookup_iova+0x66/0xa0 [rdma_rxe]
  Code: 00 00 00 48 d3 ee 89 32 c3 4c 8b 18 49 8b 3b 48 8b 47 08 48 39 c6 72 38 48 29 c6 45 31 d2 b8 01 00 00 00 48 63 c8 48 c1 e1 04 <48> 8b 4c 0f 08 48 39 f1 77 21 83 c0 01 48 29 ce 3d 00 01 00 00 75
  RSP: 0018:ffffb7ff80063bf0 EFLAGS: 00010246
  RAX: 0000000000000000 RBX: ffff9b9949d86800 RCX: 0000000000000000
  RDX: ffffb7ff80063c00 RSI: 0000000049f6b378 RDI: 002818da00000004
  RBP: 0000000000000120 R08: ffffb7ff80063c08 R09: ffffb7ff80063c04
  R10: 0000000000000002 R11: ffff9b9916f7eef8 R12: ffff9b99488a0038
  R13: ffff9b99488a0038 R14: ffff9b9914fb346a R15: ffff9b990ab27000
  FS:  0000000000000000(0000) GS:ffff9b997dc00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007efc33a98ed0 CR3: 0000000014f32004 CR4: 00000000001706f0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
   <TASK>
   rxe_mr_copy.part.0+0x6f/0x140 [rdma_rxe]
   rxe_responder+0x12ee/0x1b60 [rdma_rxe]
   ? rxe_icrc_check+0x7e/0x100 [rdma_rxe]
   ? rxe_rcv+0x1d0/0x780 [rdma_rxe]
   ? rxe_icrc_hdr.isra.0+0xf6/0x160 [rdma_rxe]
   rxe_do_task+0x67/0xb0 [rdma_rxe]
   rxe_xmit_packet+0xc7/0x210 [rdma_rxe]
   rxe_requester+0x680/0xee0 [rdma_rxe]
   ? update_load_avg+0x5f/0x690
   ? update_load_avg+0x5f/0x690
   ? rtrs_clt_recv_done+0x1b/0x30 [rtrs_client]

[2nd]----------
  RIP: 0010:rxe_mr_copy.part.0+0xa8/0x140 [rdma_rxe]
  Code: 00 00 49 c1 e7 04 48 8b 00 4c 8d 2c d0 48 8b 44 24 10 4d 03 7d 00 85 ed 7f 10 eb 6c 89 54 24 0c 49 83 c7 10 31 c0 85 ed 7e 5e <49> 8b 3f 8b 14 24 4c 89 f6 48 01 c7 85 d2 74 06 48 89 fe 4c 89 f7
  RSP: 0018:ffffae3580063bf8 EFLAGS: 00010202
  RAX: 0000000000018978 RBX: ffff9d7ef7a03600 RCX: 0000000000000008
  RDX: 000000000000007c RSI: 000000000000007c RDI: ffff9d7ef7a03600
  RBP: 0000000000000120 R08: ffffae3580063c08 R09: ffffae3580063c04
  R10: ffff9d7efece0038 R11: ffff9d7ec4b1db00 R12: ffff9d7efece0038
  R13: ffff9d7ef4098260 R14: ffff9d7f11e23c6a R15: 4c79500065708144
  FS:  0000000000000000(0000) GS:ffff9d7f3dc00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007fce47276c60 CR3: 0000000003f66004 CR4: 00000000001706f0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
   <TASK>
   rxe_responder+0x12ee/0x1b60 [rdma_rxe]
   ? rxe_icrc_check+0x7e/0x100 [rdma_rxe]
   ? rxe_rcv+0x1d0/0x780 [rdma_rxe]
   ? rxe_icrc_hdr.isra.0+0xf6/0x160 [rdma_rxe]
   rxe_do_task+0x67/0xb0 [rdma_rxe]
   rxe_xmit_packet+0xc7/0x210 [rdma_rxe]
   rxe_requester+0x680/0xee0 [rdma_rxe]
   ? update_load_avg+0x5f/0x690
   ? update_load_avg+0x5f/0x690
   ? rtrs_clt_recv_done+0x1b/0x30 [rtrs_client]
   rxe_do_task+0x67/0xb0 [rdma_rxe]
   tasklet_action_common.constprop.0+0x92/0xc0
   __do_softirq+0xe1/0x2d8
   run_ksoftirqd+0x21/0x30
   smpboot_thread_fn+0x183/0x220
   ? sort_range+0x20/0x20
   kthread+0xe2/0x110
   ? kthread_complete_and_exit+0x20/0x20
   ret_from_fork+0x22/0x30

Link: https://lore.kernel.org/r/1658805386-2-1-git-send-email-lizhijian@fujitsu.com
Link: https://lore.kernel.org/all/20220210073655.42281-1-guoqing.jiang@linux.dev/T/
Link: https://www.spinics.net/lists/linux-rdma/msg110836.html
Link: https://lore.kernel.org/lkml/94a5ea93-b8bb-3a01-9497-e2021f29598a@linux.dev/t/
Tested-by: Md Haris Iqbal <haris.iqbal@ionos.com>
Reviewed-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
This commit is contained in:
Li Zhijian 2022-07-26 03:16:26 +00:00 committed by Leon Romanovsky
parent c2ea08ca5e
commit 1e75550648
5 changed files with 104 additions and 162 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
drivers/infiniband/sw/rxe/rxe_loc.h
View File

@ -79,7 +79,6 @@ int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length);
int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
int rxe_invalidate_mr(struct rxe_qp *qp, u32 key);
int rxe_reg_fast_mr(struct rxe_qp *qp, struct rxe_send_wqe *wqe);
int rxe_mr_set_page(struct ib_mr *ibmr, u64 addr);
int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata);
void rxe_mr_cleanup(struct rxe_pool_elem *elem);

197
drivers/infiniband/sw/rxe/rxe_mr.c
View File

@ -24,7 +24,7 @@ u8 rxe_get_next_key(u32 last_key)
int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length)
{
struct rxe_map_set *set = mr->cur_map_set;
switch (mr->type) {
case IB_MR_TYPE_DMA:
@ -32,8 +32,8 @@ int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length)
case IB_MR_TYPE_USER:
case IB_MR_TYPE_MEM_REG:
if (iova < set->iova || length > set->length ||
iova > set->iova + set->length - length)
if (iova < mr->iova || length > mr->length ||
iova > mr->iova + mr->length - length)
return -EFAULT;
return 0;
@ -65,89 +65,41 @@ static void rxe_mr_init(int access, struct rxe_mr *mr)
mr->map_shift = ilog2(RXE_BUF_PER_MAP);
}
static void rxe_mr_free_map_set(int num_map, struct rxe_map_set *set)
static int rxe_mr_alloc(struct rxe_mr *mr, int num_buf)
{
int i;
int num_map;
struct rxe_map **map = mr->map;
for (i = 0; i < num_map; i++)
kfree(set->map[i]);
num_map = (num_buf + RXE_BUF_PER_MAP - 1) / RXE_BUF_PER_MAP;
kfree(set->map);
kfree(set);
}
static int rxe_mr_alloc_map_set(int num_map, struct rxe_map_set **setp)
{
int i;
struct rxe_map_set *set;
set = kmalloc(sizeof(*set), GFP_KERNEL);
if (!set)
goto err_out;
set->map = kmalloc_array(num_map, sizeof(struct rxe_map *), GFP_KERNEL);
if (!set->map)
goto err_free_set;
mr->map = kmalloc_array(num_map, sizeof(*map), GFP_KERNEL);
if (!mr->map)
goto err1;
for (i = 0; i < num_map; i++) {
set->map[i] = kmalloc(sizeof(struct rxe_map), GFP_KERNEL);
if (!set->map[i])
goto err_free_map;
mr->map[i] = kmalloc(sizeof(**map), GFP_KERNEL);
if (!mr->map[i])
goto err2;
}
*setp = set;
return 0;
err_free_map:
for (i--; i >= 0; i--)
kfree(set->map[i]);
kfree(set->map);
err_free_set:
kfree(set);
err_out:
return -ENOMEM;
}
/**
* rxe_mr_alloc() - Allocate memory map array(s) for MR
* @mr: Memory region
* @num_buf: Number of buffer descriptors to support
* @both: If non zero allocate both mr->map and mr->next_map
* else just allocate mr->map. Used for fast MRs
*
* Return: 0 on success else an error
*/
static int rxe_mr_alloc(struct rxe_mr *mr, int num_buf, int both)
{
int ret;
int num_map;
BUILD_BUG_ON(!is_power_of_2(RXE_BUF_PER_MAP));
num_map = (num_buf + RXE_BUF_PER_MAP - 1) / RXE_BUF_PER_MAP;
mr->map_shift = ilog2(RXE_BUF_PER_MAP);
mr->map_mask = RXE_BUF_PER_MAP - 1;
mr->num_buf = num_buf;
mr->max_buf = num_map * RXE_BUF_PER_MAP;
mr->num_map = num_map;
ret = rxe_mr_alloc_map_set(num_map, &mr->cur_map_set);
if (ret)
return -ENOMEM;
if (both) {
ret = rxe_mr_alloc_map_set(num_map, &mr->next_map_set);
if (ret)
goto err_free;
}
mr->max_buf = num_map * RXE_BUF_PER_MAP;
return 0;
err_free:
rxe_mr_free_map_set(mr->num_map, mr->cur_map_set);
mr->cur_map_set = NULL;
err2:
for (i--; i >= 0; i--)
kfree(mr->map[i]);
kfree(mr->map);
err1:
return -ENOMEM;
}
@ -164,7 +116,6 @@ void rxe_mr_init_dma(struct rxe_pd *pd, int access, struct rxe_mr *mr)
int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova,
int access, struct rxe_mr *mr)
{
struct rxe_map_set *set;
struct rxe_map **map;
struct rxe_phys_buf *buf = NULL;
struct ib_umem *umem;
@ -172,6 +123,7 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova,
int num_buf;
void *vaddr;
int err;
int i;
umem = ib_umem_get(pd->ibpd.device, start, length, access);
if (IS_ERR(umem)) {
@ -185,20 +137,18 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova,
rxe_mr_init(access, mr);
err = rxe_mr_alloc(mr, num_buf, 0);
err = rxe_mr_alloc(mr, num_buf);
if (err) {
pr_warn("%s: Unable to allocate memory for map\n",
__func__);
goto err_release_umem;
}
set = mr->cur_map_set;
set->page_shift = PAGE_SHIFT;
set->page_mask = PAGE_SIZE - 1;
mr->page_shift = PAGE_SHIFT;
mr->page_mask = PAGE_SIZE - 1;
num_buf = 0;
map = set->map;
map = mr->map;
if (length > 0) {
buf = map[0]->buf;
@ -214,29 +164,33 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova,
pr_warn("%s: Unable to get virtual address\n",
__func__);
err = -ENOMEM;
goto err_release_umem;
goto err_cleanup_map;
}
buf->addr = (uintptr_t)vaddr;
buf->size = PAGE_SIZE;
num_buf++;
buf++;
}
}
mr->ibmr.pd = &pd->ibpd;
mr->umem = umem;
mr->access = access;
mr->length = length;
mr->iova = iova;
mr->va = start;
mr->offset = ib_umem_offset(umem);
mr->state = RXE_MR_STATE_VALID;
mr->type = IB_MR_TYPE_USER;
set->length = length;
set->iova = iova;
set->va = start;
set->offset = ib_umem_offset(umem);
return 0;
err_cleanup_map:
for (i = 0; i < mr->num_map; i++)
kfree(mr->map[i]);
kfree(mr->map);
err_release_umem:
ib_umem_release(umem);
err_out:
@ -250,7 +204,7 @@ int rxe_mr_init_fast(struct rxe_pd *pd, int max_pages, struct rxe_mr *mr)
/* always allow remote access for FMRs */
rxe_mr_init(IB_ACCESS_REMOTE, mr);
err = rxe_mr_alloc(mr, max_pages, 1);
err = rxe_mr_alloc(mr, max_pages);
if (err)
goto err1;
@ -268,24 +222,21 @@ err1:
static void lookup_iova(struct rxe_mr *mr, u64 iova, int *m_out, int *n_out,
size_t *offset_out)
{
struct rxe_map_set *set = mr->cur_map_set;
size_t offset = iova - set->iova + set->offset;
size_t offset = iova - mr->iova + mr->offset;
int map_index;
int buf_index;
u64 length;
struct rxe_map *map;
if (likely(set->page_shift)) {
*offset_out = offset & set->page_mask;
offset >>= set->page_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;
map = set->map[map_index];
length = map->buf[buf_index].size;
length = mr->map[map_index]->buf[buf_index].size;
while (offset >= length) {
offset -= length;
@ -295,8 +246,7 @@ static void lookup_iova(struct rxe_mr *mr, u64 iova, int *m_out, int *n_out,
map_index++;
buf_index = 0;
}
map = set->map[map_index];
length = map->buf[buf_index].size;
length = mr->map[map_index]->buf[buf_index].size;
}
*m_out = map_index;
@ -317,7 +267,7 @@ void *iova_to_vaddr(struct rxe_mr *mr, u64 iova, int length)
goto out;
}
if (!mr->cur_map_set) {
if (!mr->map) {
addr = (void *)(uintptr_t)iova;
goto out;
}
@ -330,13 +280,13 @@ void *iova_to_vaddr(struct rxe_mr *mr, u64 iova, int length)
lookup_iova(mr, iova, &m, &n, &offset);
if (offset + length > mr->cur_map_set->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)mr->cur_map_set->map[m]->buf[n].addr + offset;
addr = (void *)(uintptr_t)mr->map[m]->buf[n].addr + offset;
out:
return addr;
@ -372,7 +322,7 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length,
return 0;
}
WARN_ON_ONCE(!mr->cur_map_set);
WARN_ON_ONCE(!mr->map);
err = mr_check_range(mr, iova, length);
if (err) {
@ -382,7 +332,7 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length,
lookup_iova(mr, iova, &m, &i, &offset);
map = mr->cur_map_set->map + m;
map = mr->map + m;
buf = map[0]->buf + i;
while (length > 0) {
@ -628,9 +578,8 @@ err:
int rxe_reg_fast_mr(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
{
struct rxe_mr *mr = to_rmr(wqe->wr.wr.reg.mr);
u32 key = wqe->wr.wr.reg.key & 0xff;
u32 key = wqe->wr.wr.reg.key;
u32 access = wqe->wr.wr.reg.access;
struct rxe_map_set *set;
/* user can only register MR in free state */
if (unlikely(mr->state != RXE_MR_STATE_FREE)) {
@ -646,35 +595,18 @@ int rxe_reg_fast_mr(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
return -EINVAL;
}
mr->access = access;
mr->lkey = (mr->lkey & ~0xff) | key;
mr->rkey = (access & IB_ACCESS_REMOTE) ? mr->lkey : 0;
mr->state = RXE_MR_STATE_VALID;
set = mr->cur_map_set;
mr->cur_map_set = mr->next_map_set;
mr->cur_map_set->iova = wqe->wr.wr.reg.mr->iova;
mr->next_map_set = set;
return 0;
/* user is only allowed to change key portion of l/rkey */
if (unlikely((mr->lkey & ~0xff) != (key & ~0xff))) {
pr_warn("%s: key = 0x%x has wrong index mr->lkey = 0x%x\n",
__func__, key, mr->lkey);
return -EINVAL;
}
int rxe_mr_set_page(struct ib_mr *ibmr, u64 addr)
{
struct rxe_mr *mr = to_rmr(ibmr);
struct rxe_map_set *set = mr->next_map_set;
struct rxe_map *map;
struct rxe_phys_buf *buf;
if (unlikely(set->nbuf == mr->num_buf))
return -ENOMEM;
map = set->map[set->nbuf / RXE_BUF_PER_MAP];
buf = &map->buf[set->nbuf % RXE_BUF_PER_MAP];
buf->addr = addr;
buf->size = ibmr->page_size;
set->nbuf++;
mr->access = access;
mr->lkey = key;
mr->rkey = (access & IB_ACCESS_REMOTE) ? key : 0;
mr->iova = wqe->wr.wr.reg.mr->iova;
mr->state = RXE_MR_STATE_VALID;
return 0;
}
@ -695,14 +627,15 @@ int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
void rxe_mr_cleanup(struct rxe_pool_elem *elem)
{
struct rxe_mr *mr = container_of(elem, typeof(*mr), elem);
int i;
rxe_put(mr_pd(mr));
ib_umem_release(mr->umem);
if (mr->cur_map_set)
rxe_mr_free_map_set(mr->num_map, mr->cur_map_set);
if (mr->map) {
for (i = 0; i < mr->num_map; i++)
kfree(mr->map[i]);
if (mr->next_map_set)
rxe_mr_free_map_set(mr->num_map, mr->next_map_set);
kfree(mr->map);
}
}

6
drivers/infiniband/sw/rxe/rxe_mw.c
View File

@ -114,15 +114,15 @@ static int rxe_check_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
/* C10-75 */
if (mw->access & IB_ZERO_BASED) {
if (unlikely(wqe->wr.wr.mw.length > mr->cur_map_set->length)) {
if (unlikely(wqe->wr.wr.mw.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.mw.addr < mr->cur_map_set->iova) ||
if (unlikely((wqe->wr.wr.mw.addr < mr->iova) ||
((wqe->wr.wr.mw.addr + wqe->wr.wr.mw.length) >
(mr->cur_map_set->iova + mr->cur_map_set->length)))) {
(mr->iova + mr->length)))) {
pr_err_once(
"attempt to bind a VA MW outside of the MR\n");
return -EINVAL;

39
drivers/infiniband/sw/rxe/rxe_verbs.c
View File

@ -978,26 +978,41 @@ err1:
return ERR_PTR(err);
}
/* build next_map_set from scatterlist
* The IB_WR_REG_MR WR will swap map_sets
*/
static int rxe_set_page(struct ib_mr *ibmr, u64 addr)
{
struct rxe_mr *mr = to_rmr(ibmr);
struct rxe_map *map;
struct rxe_phys_buf *buf;
if (unlikely(mr->nbuf == mr->num_buf))
return -ENOMEM;
map = mr->map[mr->nbuf / RXE_BUF_PER_MAP];
buf = &map->buf[mr->nbuf % RXE_BUF_PER_MAP];
buf->addr = addr;
buf->size = ibmr->page_size;
mr->nbuf++;
return 0;
}
static int rxe_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg,
int sg_nents, unsigned int *sg_offset)
{
struct rxe_mr *mr = to_rmr(ibmr);
struct rxe_map_set *set = mr->next_map_set;
int n;
set->nbuf = 0;
mr->nbuf = 0;
n = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, rxe_mr_set_page);
n = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, rxe_set_page);
set->va = ibmr->iova;
set->iova = ibmr->iova;
set->length = ibmr->length;
set->page_shift = ilog2(ibmr->page_size);
set->page_mask = ibmr->page_size - 1;
set->offset = set->iova & set->page_mask;
mr->va = ibmr->iova;
mr->iova = ibmr->iova;
mr->length = ibmr->length;
mr->page_shift = ilog2(ibmr->page_size);
mr->page_mask = ibmr->page_size - 1;
mr->offset = mr->iova & mr->page_mask;
return n;
}

21
drivers/infiniband/sw/rxe/rxe_verbs.h
View File

@ -287,17 +287,6 @@ struct rxe_map {
struct rxe_phys_buf buf[RXE_BUF_PER_MAP];
};
struct rxe_map_set {
struct rxe_map **map;
u64 va;
u64 iova;
size_t length;
u32 offset;
u32 nbuf;
int page_shift;
int page_mask;
};
static inline int rkey_is_mw(u32 rkey)
{
u32 index = rkey >> 8;
@ -315,20 +304,26 @@ struct rxe_mr {
u32 rkey;
enum rxe_mr_state state;
enum ib_mr_type type;
u64 va;
u64 iova;
size_t length;
u32 offset;
int access;
int page_shift;
int page_mask;
int map_shift;
int map_mask;
u32 num_buf;
u32 nbuf;
u32 max_buf;
u32 num_map;
atomic_t num_mw;
struct rxe_map_set *cur_map_set;
struct rxe_map_set *next_map_set;
struct rxe_map **map;
};
enum rxe_mw_state {