Re: [PATCH rdma-next] RDMA/rxe: Break endless pagefault loop for RO pages

[Zhu Yanjun <yanjun.zhu@linux.dev>]

在 2025/5/22 13:36, Leon Romanovsky 写道:
> From: Leon Romanovsky <leonro@nvidia.com>
> 
> RO pages has "perm" equal to 0, that caused to the situation
> where such pages were marked as needed to have fault and caused
> to infinite loop.
> 
> Fixes: eedd5b1276e7 ("RDMA/umem: Store ODP access mask information in PFN")
> Reported-by: Daisuke Matsuda <dskmtsd@gmail.com>
> Closes: https://lore.kernel.org/all/3e8f343f-7d66-4f7a-9f08-3910623e322f@gmail.com
> Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
> ---
>   drivers/infiniband/sw/rxe/rxe_odp.c | 2 +-
>   1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/infiniband/sw/rxe/rxe_odp.c b/drivers/infiniband/sw/rxe/rxe_odp.c
> index a1416626f61a5..0f67167ddddd1 100644
> --- a/drivers/infiniband/sw/rxe/rxe_odp.c
> +++ b/drivers/infiniband/sw/rxe/rxe_odp.c
> @@ -137,7 +137,7 @@ static inline bool rxe_check_pagefault(struct ib_umem_odp *umem_odp,
>   	while (addr < iova + length) {
>   		idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift;
>   
> -		if (!(umem_odp->map.pfn_list[idx] & perm)) {
> +		if (!(umem_odp->map.pfn_list[idx] & HMM_PFN_VALID)) {

Because perm is not used, it is not necessary to calculate and pass perm 
to rxe_check_pagefault. The cleanup is as below:

diff --git a/drivers/infiniband/sw/rxe/rxe_odp.c 
b/drivers/infiniband/sw/rxe/rxe_odp.c
index 9f6e2bb2a269..f385fccd5988 100644
--- a/drivers/infiniband/sw/rxe/rxe_odp.c
+++ b/drivers/infiniband/sw/rxe/rxe_odp.c
@@ -125,7 +125,7 @@ int rxe_odp_mr_init_user(struct rxe_dev *rxe, u64 
start, u64 length,
  }

  static inline bool rxe_check_pagefault(struct ib_umem_odp *umem_odp,
-                                      u64 iova, int length, u32 perm)
+                                      u64 iova, int length)
  {
         bool need_fault = false;
         u64 addr;
@@ -137,7 +137,7 @@ static inline bool rxe_check_pagefault(struct 
ib_umem_odp *umem_odp,
         while (addr < iova + length) {
                 idx = (addr - ib_umem_start(umem_odp)) >> 
umem_odp->page_shift;

-               if (!(umem_odp->dma_list[idx] & perm)) {
+               if (!(umem_odp->dma_list[idx] & HMM_PFN_VALID)) {
                         need_fault = true;
                         break;
                 }
@@ -151,19 +151,14 @@ static int rxe_odp_map_range_and_lock(struct 
rxe_mr *mr, u64 iova, int length, u
  {
         struct ib_umem_odp *umem_odp = to_ib_umem_odp(mr->umem);
         bool need_fault;
-       u64 perm;
         int err;

         if (unlikely(length < 1))
                 return -EINVAL;

-       perm = ODP_READ_ALLOWED_BIT;
-       if (!(flags & RXE_PAGEFAULT_RDONLY))
-               perm |= ODP_WRITE_ALLOWED_BIT;
-
         mutex_lock(&umem_odp->umem_mutex);

-       need_fault = rxe_check_pagefault(umem_odp, iova, length, perm);
+       need_fault = rxe_check_pagefault(umem_odp, iova, length);
         if (need_fault) {
                 mutex_unlock(&umem_odp->umem_mutex);

@@ -173,7 +168,7 @@ static int rxe_odp_map_range_and_lock(struct rxe_mr 
*mr, u64 iova, int length, u
                 if (err < 0)
                         return err;

-               need_fault = rxe_check_pagefault(umem_odp, iova, length, 
perm);
+               need_fault = rxe_check_pagefault(umem_odp, iova, length);
                 if (need_fault)
                         return -EFAULT;
         }

Zhu Yanjun

>   			need_fault = true;
>   			break;
>   		}