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
hweight.c
#include <linux/export.h>
#include <linux/bitops.h>
#include <asm/types.h>
/**
* hweightN - returns the hamming weight of a N-bit word
* @x: the word to weigh
*
* The Hamming Weight of a number is the total number of bits set in it.
*/
unsigned int __sw_hweight32(unsigned int w)
{
#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
w -= (w >> 1) & 0x55555555;
w = (w & 0x33333333) + ((w >> 2) & 0x33333333);
w = (w + (w >> 4)) & 0x0f0f0f0f;
return (w * 0x01010101) >> 24;
#else
unsigned int res = w - ((w >> 1) & 0x55555555);
res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
res = (res + (res >> 4)) & 0x0F0F0F0F;
res = res + (res >> 8);
return (res + (res >> 16)) & 0x000000FF;
#endif
}
EXPORT_SYMBOL(__sw_hweight32);
unsigned int __sw_hweight16(unsigned int w)
{
unsigned int res = w - ((w >> 1) & 0x5555);
res = (res & 0x3333) + ((res >> 2) & 0x3333);
res = (res + (res >> 4)) & 0x0F0F;
return (res + (res >> 8)) & 0x00FF;
}
EXPORT_SYMBOL(__sw_hweight16);
unsigned int __sw_hweight8(unsigned int w)
{
unsigned int res = w - ((w >> 1) & 0x55);
res = (res & 0x33) + ((res >> 2) & 0x33);
return (res + (res >> 4)) & 0x0F;
}
EXPORT_SYMBOL(__sw_hweight8);
unsigned long __sw_hweight64(__u64 w)
{
#if BITS_PER_LONG == 32
return __sw_hweight32((unsigned int)(w >> 32)) +
__sw_hweight32((unsigned int)w);
#elif BITS_PER_LONG == 64
#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
w -= (w >> 1) & 0x5555555555555555ul;
w = (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul);
w = (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful;
return (w * 0x0101010101010101ul) >> 56;
#else
__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
res = res + (res >> 8);
res = res + (res >> 16);
return (res + (res >> 32)) & 0x00000000000000FFul;
#endif
#endif
}
EXPORT_SYMBOL(__sw_hweight64);
Computing file changes ...
