diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2010-05-25 12:05:17 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2010-05-25 12:05:17 -0700 |
| commit | 8e9815a0f8882aaa68645b001bb7538db8886802 (patch) | |
| tree | 5654a4f982ea681158185b21321acd470cb9b87c /drivers/net/mlx4 | |
| parent | 702c0b04978ce316ec05f4d0a9c148fac124335b (diff) | |
| parent | acdc30b56abc0db7d409a13e9b6c72ea23b6f90d (diff) | |
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
RDMA/nes: Fix incorrect unlock in nes_process_mac_intr()
RDMA/nes: Async event for closed QP causes crash
RDMA/nes: Have ethtool read hardware registers for rx/tx stats
RDMA/cxgb4: Only insert sq qid in lookup table
RDMA/cxgb4: Support IB_WR_READ_WITH_INV opcode
RDMA/cxgb4: Set fence flag for inv-local-stag work requests
RDMA/cxgb4: Update some HW limits
RDMA/cxgb4: Don't limit fastreg page list depth
RDMA/cxgb4: Return proper errors in fastreg mr/pbl allocation
RDMA/cxgb4: Fix overflow bug in CQ arm
RDMA/cxgb4: Optimize CQ overflow detection
RDMA/cxgb4: CQ size must be IQ size - 2
RDMA/cxgb4: Register RDMA provider based on LLD state_change events
RDMA/cxgb4: Detach from the LLD after unregistering RDMA device
IB/ipath: Remove support for QLogic PCIe QLE devices
IB/qib: Add new qib driver for QLogic PCIe InfiniBand adapters
IB/mad: Make needlessly global mad_sendq_size/mad_recvq_size static
IB/core: Allow device-specific per-port sysfs files
mlx4_core: Clean up mlx4_alloc_icm() a bit
mlx4_core: Fix possible chunk sg list overflow in mlx4_alloc_icm()
Diffstat (limited to 'drivers/net/mlx4')
| -rw-r--r-- | drivers/net/mlx4/icm.c | 36 |
1 files changed, 19 insertions, 17 deletions
diff --git a/drivers/net/mlx4/icm.c b/drivers/net/mlx4/icm.c index 57288ca1395..b07e4dee80a 100644 --- a/drivers/net/mlx4/icm.c +++ b/drivers/net/mlx4/icm.c @@ -163,28 +163,30 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages, ret = mlx4_alloc_icm_pages(&chunk->mem[chunk->npages], cur_order, gfp_mask); - if (!ret) { - ++chunk->npages; - - if (coherent) - ++chunk->nsg; - else if (chunk->npages == MLX4_ICM_CHUNK_LEN) { - chunk->nsg = pci_map_sg(dev->pdev, chunk->mem, - chunk->npages, - PCI_DMA_BIDIRECTIONAL); + if (ret) { + if (--cur_order < 0) + goto fail; + else + continue; + } - if (chunk->nsg <= 0) - goto fail; + ++chunk->npages; - chunk = NULL; - } + if (coherent) + ++chunk->nsg; + else if (chunk->npages == MLX4_ICM_CHUNK_LEN) { + chunk->nsg = pci_map_sg(dev->pdev, chunk->mem, + chunk->npages, + PCI_DMA_BIDIRECTIONAL); - npages -= 1 << cur_order; - } else { - --cur_order; - if (cur_order < 0) + if (chunk->nsg <= 0) goto fail; } + + if (chunk->npages == MLX4_ICM_CHUNK_LEN) + chunk = NULL; + + npages -= 1 << cur_order; } if (!coherent && chunk) { |