Revision c0cf4512a31eb3cec70b066bc36ed55f7d05b8c0 authored by Bart Van Assche on 23 June 2016, 07:35:48 UTC, committed by Doug Ledford on 23 June 2016, 16:04:09 UTC
The memory needed for the send and receive queues associated with
a QP is proportional to the max_sge parameter. The current value
of that parameter is such that with an mlx4 HCA the QP buffer size
is 8 MB. Since DMA is used for communication between HCA and CPU
that buffer either has to be allocated coherently or map_single()
must succeed for that buffer. Since large contiguous allocations
are fragile and since the maximum segment size for e.g. swiotlb
is 256 KB, reduce the max_sge parameter. This patch avoids that
the following text appears on the console after SRP logout and
relogin on a system equipped with multiple IB HCAs:
mlx4_core 0000:05:00.0: swiotlb buffer is full (sz: 8388608 bytes)
swiotlb: coherent allocation failed for device 0000:05:00.0 size=8388608
CPU: 11 PID: 148 Comm: kworker/11:1 Not tainted 4.7.0-rc4-dbg+ #1
Call Trace:
[<ffffffff812c6d35>] dump_stack+0x67/0x92
[<ffffffff812efe71>] swiotlb_alloc_coherent+0x141/0x150
[<ffffffff810458be>] x86_swiotlb_alloc_coherent+0x3e/0x50
[<ffffffffa03861fa>] mlx4_buf_direct_alloc.isra.5+0x9a/0x120 [mlx4_core]
[<ffffffffa0386545>] mlx4_buf_alloc+0x165/0x1a0 [mlx4_core]
[<ffffffffa035053d>] create_qp_common.isra.29+0x57d/0xff0 [mlx4_ib]
[<ffffffffa03510da>] mlx4_ib_create_qp+0x12a/0x3f0 [mlx4_ib]
[<ffffffffa031154a>] ib_create_qp+0x3a/0x250 [ib_core]
[<ffffffffa055dd4b>] srpt_cm_handler+0x4bb/0xcad [ib_srpt]
[<ffffffffa02c1ab0>] cm_process_work+0x20/0xf0 [ib_cm]
[<ffffffffa02c3640>] cm_work_handler+0x1ac0/0x2059 [ib_cm]
[<ffffffff810737ed>] process_one_work+0x19d/0x490
[<ffffffff81073b29>] worker_thread+0x49/0x490
[<ffffffff8107a0ea>] kthread+0xea/0x100
[<ffffffff815b25af>] ret_from_fork+0x1f/0x40
Fixes: b99f8e4d7bcd ("IB/srpt: convert to the generic RDMA READ/WRITE API")
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Doug Ledford <dledford@redhat.com>
1 parent 37e07cd
dma-noop.c
/*
* lib/dma-noop.c
*
* Simple DMA noop-ops that map 1:1 with memory
*/
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/dma-mapping.h>
#include <linux/scatterlist.h>
static void *dma_noop_alloc(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t gfp,
struct dma_attrs *attrs)
{
void *ret;
ret = (void *)__get_free_pages(gfp, get_order(size));
if (ret)
*dma_handle = virt_to_phys(ret);
return ret;
}
static void dma_noop_free(struct device *dev, size_t size,
void *cpu_addr, dma_addr_t dma_addr,
struct dma_attrs *attrs)
{
free_pages((unsigned long)cpu_addr, get_order(size));
}
static dma_addr_t dma_noop_map_page(struct device *dev, struct page *page,
unsigned long offset, size_t size,
enum dma_data_direction dir,
struct dma_attrs *attrs)
{
return page_to_phys(page) + offset;
}
static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
enum dma_data_direction dir, struct dma_attrs *attrs)
{
int i;
struct scatterlist *sg;
for_each_sg(sgl, sg, nents, i) {
void *va;
BUG_ON(!sg_page(sg));
va = sg_virt(sg);
sg_dma_address(sg) = (dma_addr_t)virt_to_phys(va);
sg_dma_len(sg) = sg->length;
}
return nents;
}
static int dma_noop_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
return 0;
}
static int dma_noop_supported(struct device *dev, u64 mask)
{
return 1;
}
struct dma_map_ops dma_noop_ops = {
.alloc = dma_noop_alloc,
.free = dma_noop_free,
.map_page = dma_noop_map_page,
.map_sg = dma_noop_map_sg,
.mapping_error = dma_noop_mapping_error,
.dma_supported = dma_noop_supported,
};
EXPORT_SYMBOL(dma_noop_ops);
Computing file changes ...
