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
Raw File
find_bit.c
/* bit search implementation
 *
 * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * Copyright (C) 2008 IBM Corporation
 * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au>
 * (Inspired by David Howell's find_next_bit implementation)
 *
 * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease
 * size and improve performance, 2015.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */

#include <linux/bitops.h>
#include <linux/bitmap.h>
#include <linux/export.h>
#include <linux/kernel.h>

#if !defined(find_next_bit) || !defined(find_next_zero_bit)

/*
 * This is a common helper function for find_next_bit and
 * find_next_zero_bit.  The difference is the "invert" argument, which
 * is XORed with each fetched word before searching it for one bits.
 */
static unsigned long _find_next_bit(const unsigned long *addr,
		unsigned long nbits, unsigned long start, unsigned long invert)
{
	unsigned long tmp;

	if (!nbits || start >= nbits)
		return nbits;

	tmp = addr[start / BITS_PER_LONG] ^ invert;

	/* Handle 1st word. */
	tmp &= BITMAP_FIRST_WORD_MASK(start);
	start = round_down(start, BITS_PER_LONG);

	while (!tmp) {
		start += BITS_PER_LONG;
		if (start >= nbits)
			return nbits;

		tmp = addr[start / BITS_PER_LONG] ^ invert;
	}

	return min(start + __ffs(tmp), nbits);
}
#endif

#ifndef find_next_bit
/*
 * Find the next set bit in a memory region.
 */
unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
			    unsigned long offset)
{
	return _find_next_bit(addr, size, offset, 0UL);
}
EXPORT_SYMBOL(find_next_bit);
#endif

#ifndef find_next_zero_bit
unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
				 unsigned long offset)
{
	return _find_next_bit(addr, size, offset, ~0UL);
}
EXPORT_SYMBOL(find_next_zero_bit);
#endif

#ifndef find_first_bit
/*
 * Find the first set bit in a memory region.
 */
unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
{
	unsigned long idx;

	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
		if (addr[idx])
			return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size);
	}

	return size;
}
EXPORT_SYMBOL(find_first_bit);
#endif

#ifndef find_first_zero_bit
/*
 * Find the first cleared bit in a memory region.
 */
unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
{
	unsigned long idx;

	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
		if (addr[idx] != ~0UL)
			return min(idx * BITS_PER_LONG + ffz(addr[idx]), size);
	}

	return size;
}
EXPORT_SYMBOL(find_first_zero_bit);
#endif

#ifndef find_last_bit
unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
{
	if (size) {
		unsigned long val = BITMAP_LAST_WORD_MASK(size);
		unsigned long idx = (size-1) / BITS_PER_LONG;

		do {
			val &= addr[idx];
			if (val)
				return idx * BITS_PER_LONG + __fls(val);

			val = ~0ul;
		} while (idx--);
	}
	return size;
}
EXPORT_SYMBOL(find_last_bit);
#endif

#ifdef __BIG_ENDIAN

/* include/linux/byteorder does not support "unsigned long" type */
static inline unsigned long ext2_swab(const unsigned long y)
{
#if BITS_PER_LONG == 64
	return (unsigned long) __swab64((u64) y);
#elif BITS_PER_LONG == 32
	return (unsigned long) __swab32((u32) y);
#else
#error BITS_PER_LONG not defined
#endif
}

#if !defined(find_next_bit_le) || !defined(find_next_zero_bit_le)
static unsigned long _find_next_bit_le(const unsigned long *addr,
		unsigned long nbits, unsigned long start, unsigned long invert)
{
	unsigned long tmp;

	if (!nbits || start >= nbits)
		return nbits;

	tmp = addr[start / BITS_PER_LONG] ^ invert;

	/* Handle 1st word. */
	tmp &= ext2_swab(BITMAP_FIRST_WORD_MASK(start));
	start = round_down(start, BITS_PER_LONG);

	while (!tmp) {
		start += BITS_PER_LONG;
		if (start >= nbits)
			return nbits;

		tmp = addr[start / BITS_PER_LONG] ^ invert;
	}

	return min(start + __ffs(ext2_swab(tmp)), nbits);
}
#endif

#ifndef find_next_zero_bit_le
unsigned long find_next_zero_bit_le(const void *addr, unsigned
		long size, unsigned long offset)
{
	return _find_next_bit_le(addr, size, offset, ~0UL);
}
EXPORT_SYMBOL(find_next_zero_bit_le);
#endif

#ifndef find_next_bit_le
unsigned long find_next_bit_le(const void *addr, unsigned
		long size, unsigned long offset)
{
	return _find_next_bit_le(addr, size, offset, 0UL);
}
EXPORT_SYMBOL(find_next_bit_le);
#endif

#endif /* __BIG_ENDIAN */
back to top