liblcd: Add checksum and dql support

checksum and DQL (dynamic queue limits) are used by ixgbe driver. Add this to
liblcd as this may be used by other modules too in the future.
Signed-off-by: Vikram Narayanan <vikram186@gmail.com>

lcd-domains/liblcd/lib/checksum.c

+/*
+ *
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		IP/TCP/UDP checksumming routines
+ *
+ * Authors:	Jorge Cwik, <jorge@laser.satlink.net>
+ *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
+ *		Tom May, <ftom@netcom.com>
+ *		Andreas Schwab, <schwab@issan.informatik.uni-dortmund.de>
+ *		Lots of code moved from tcp.c and ip.c; see those files
+ *		for more names.
+ *
+ * 03/02/96	Jes Sorensen, Andreas Schwab, Roman Hodek:
+ *		Fixed some nasty bugs, causing some horrible crashes.
+ *		A: At some points, the sum (%0) was used as
+ *		length-counter instead of the length counter
+ *		(%1). Thanks to Roman Hodek for pointing this out.
+ *		B: GCC seems to mess up if one uses too many
+ *		data-registers to hold input values and one tries to
+ *		specify d0 and d1 as scratch registers. Letting gcc
+ *		choose these registers itself solves the problem.
+ *
+ *		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.
+ */
+
+/* Revised by Kenneth Albanowski for m68knommu. Basic problem: unaligned access
+ kills, so most of the assembly has to go. */
+
+#include <lcd_config/pre_hook.h>
+
+#include <linux/export.h>
+#include <net/checksum.h>
+
+#include <asm/byteorder.h>
+
+#include <lcd_config/post_hook.h>
+
+
+#ifndef do_csum
+static inline unsigned short from32to16(unsigned int x)
+{
+	/* add up 16-bit and 16-bit for 16+c bit */
+	x = (x & 0xffff) + (x >> 16);
+	/* add up carry.. */
+	x = (x & 0xffff) + (x >> 16);
+	return x;
+}
+
+static unsigned int do_csum(const unsigned char *buff, int len)
+{
+	int odd;
+	unsigned int result = 0;
+
+	if (len <= 0)
+		goto out;
+	odd = 1 & (unsigned long) buff;
+	if (odd) {
+#ifdef __LITTLE_ENDIAN
+		result += (*buff << 8);
+#else
+		result = *buff;
+#endif
+		len--;
+		buff++;
+	}
+	if (len >= 2) {
+		if (2 & (unsigned long) buff) {
+			result += *(unsigned short *) buff;
+			len -= 2;
+			buff += 2;
+		}
+		if (len >= 4) {
+			const unsigned char *end = buff + ((unsigned)len & ~3);
+			unsigned int carry = 0;
+			do {
+				unsigned int w = *(unsigned int *) buff;
+				buff += 4;
+				result += carry;
+				result += w;
+				carry = (w > result);
+			} while (buff < end);
+			result += carry;
+			result = (result & 0xffff) + (result >> 16);
+		}
+		if (len & 2) {
+			result += *(unsigned short *) buff;
+			buff += 2;
+		}
+	}
+	if (len & 1)
+#ifdef __LITTLE_ENDIAN
+		result += *buff;
+#else
+		result += (*buff << 8);
+#endif
+	result = from32to16(result);
+	if (odd)
+		result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
+out:
+	return result;
+}
+#endif
+
+#if 0 /* if 0 */
+#define ip_fast_csum
+#ifndef ip_fast_csum
+/*
+ *	This is a version of ip_compute_csum() optimized for IP headers,
+ *	which always checksum on 4 octet boundaries.
+ */
+__sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	return (__force __sum16)~do_csum(iph, ihl*4);
+}
+EXPORT_SYMBOL(ip_fast_csum);
+#endif
+#endif
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic
+ *
+ * this function must be called with even lengths, except
+ * for the last fragment, which may be odd
+ *
+ * it's best to have buff aligned on a 32-bit boundary
+ */
+__wsum csum_partial(const void *buff, int len, __wsum wsum)
+{
+	unsigned int sum = (__force unsigned int)wsum;
+	unsigned int result = do_csum(buff, len);
+
+	/* add in old sum, and carry.. */
+	result += sum;
+	if (sum > result)
+		result += 1;
+	return (__force __wsum)result;
+}
+EXPORT_SYMBOL(csum_partial);
+
+#if 0
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+__sum16 ip_compute_csum(const void *buff, int len)
+{
+	return (__force __sum16)~do_csum(buff, len);
+}
+EXPORT_SYMBOL(ip_compute_csum);
+
+/*
+ * copy from fs while checksumming, otherwise like csum_partial
+ */
+__wsum
+csum_partial_copy_from_user(const void __user *src, void *dst, int len,
+						__wsum sum, int *csum_err)
+{
+	int missing;
+
+	missing = __copy_from_user(dst, src, len);
+	if (missing) {
+		memset(dst + len - missing, 0, missing);
+		*csum_err = -EFAULT;
+	} else
+		*csum_err = 0;
+
+	return csum_partial(dst, len, sum);
+}
+EXPORT_SYMBOL(csum_partial_copy_from_user);
+
+/*
+ * copy from ds while checksumming, otherwise like csum_partial
+ */
+__wsum
+csum_partial_copy(const void *src, void *dst, int len, __wsum sum)
+{
+	memcpy(dst, src, len);
+	return csum_partial(dst, len, sum);
+}
+EXPORT_SYMBOL(csum_partial_copy);
+
+/* already defined in arch/x86/include/asm/checksum_64.h */
+#define csum_tcpudp_nofold
+
+#ifndef csum_tcpudp_nofold
+static inline u32 from64to32(u64 x)
+{
+	/* add up 32-bit and 32-bit for 32+c bit */
+	x = (x & 0xffffffff) + (x >> 32);
+	/* add up carry.. */
+	x = (x & 0xffffffff) + (x >> 32);
+	return (u32)x;
+}
+
+__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+			  __u32 len, __u8 proto, __wsum sum)
+{
+	unsigned long long s = (__force u32)sum;
+
+	s += (__force u32)saddr;
+	s += (__force u32)daddr;
+#ifdef __BIG_ENDIAN
+	s += proto + len;
+#else
+	s += (proto + len) << 8;
+#endif
+	return (__force __wsum)from64to32(s);
+}
+EXPORT_SYMBOL(csum_tcpudp_nofold);
+#endif
+#endif

lcd-domains/liblcd/lib/dynamic_queue_limits.c

+/*
+ * Dynamic byte queue limits.  See include/linux/dynamic_queue_limits.h
+ *
+ * Copyright (c) 2011, Tom Herbert <therbert@google.com>
+ */
+
+#include <lcd_config/pre_hook.h>
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/jiffies.h>
+#include <linux/dynamic_queue_limits.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
+
+#include <lcd_config/post_hook.h>
+
+#define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0)
+#define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0)
+
+/* Records completed count and recalculates the queue limit */
+void dql_completed(struct dql *dql, unsigned int count)
+{
+	unsigned int inprogress, prev_inprogress, limit;
+	unsigned int ovlimit, completed, num_queued;
+	bool all_prev_completed;
+
+	num_queued = ACCESS_ONCE(dql->num_queued);
+
+	/* Can't complete more than what's in queue */
+	BUG_ON(count > num_queued - dql->num_completed);
+
+	completed = dql->num_completed + count;
+	limit = dql->limit;
+	ovlimit = POSDIFF(num_queued - dql->num_completed, limit);
+	inprogress = num_queued - completed;
+	prev_inprogress = dql->prev_num_queued - dql->num_completed;
+	all_prev_completed = AFTER_EQ(completed, dql->prev_num_queued);
+
+	if ((ovlimit && !inprogress) ||
+	    (dql->prev_ovlimit && all_prev_completed)) {
+		/*
+		 * Queue considered starved if:
+		 *   - The queue was over-limit in the last interval,
+		 *     and there is no more data in the queue.
+		 *  OR
+		 *   - The queue was over-limit in the previous interval and
+		 *     when enqueuing it was possible that all queued data
+		 *     had been consumed.  This covers the case when queue
+		 *     may have becomes starved between completion processing
+		 *     running and next time enqueue was scheduled.
+		 *
+		 *     When queue is starved increase the limit by the amount
+		 *     of bytes both sent and completed in the last interval,
+		 *     plus any previous over-limit.
+		 */
+		limit += POSDIFF(completed, dql->prev_num_queued) +
+		     dql->prev_ovlimit;
+		dql->slack_start_time = jiffies;
+		dql->lowest_slack = UINT_MAX;
+	} else if (inprogress && prev_inprogress && !all_prev_completed) {
+		/*
+		 * Queue was not starved, check if the limit can be decreased.
+		 * A decrease is only considered if the queue has been busy in
+		 * the whole interval (the check above).
+		 *
+		 * If there is slack, the amount of execess data queued above
+		 * the the amount needed to prevent starvation, the queue limit
+		 * can be decreased.  To avoid hysteresis we consider the
+		 * minimum amount of slack found over several iterations of the
+		 * completion routine.
+		 */
+		unsigned int slack, slack_last_objs;
+
+		/*
+		 * Slack is the maximum of
+		 *   - The queue limit plus previous over-limit minus twice
+		 *     the number of objects completed.  Note that two times
+		 *     number of completed bytes is a basis for an upper bound
+		 *     of the limit.
+		 *   - Portion of objects in the last queuing operation that
+		 *     was not part of non-zero previous over-limit.  That is
+		 *     "round down" by non-overlimit portion of the last
+		 *     queueing operation.
+		 */
+		slack = POSDIFF(limit + dql->prev_ovlimit,
+		    2 * (completed - dql->num_completed));
+		slack_last_objs = dql->prev_ovlimit ?
+		    POSDIFF(dql->prev_last_obj_cnt, dql->prev_ovlimit) : 0;
+
+		slack = max(slack, slack_last_objs);
+
+		if (slack < dql->lowest_slack)
+			dql->lowest_slack = slack;
+
+		if (time_after(jiffies,
+			       dql->slack_start_time + dql->slack_hold_time)) {
+			limit = POSDIFF(limit, dql->lowest_slack);
+			dql->slack_start_time = jiffies;
+			dql->lowest_slack = UINT_MAX;
+		}
+	}
+
+	/* Enforce bounds on limit */
+	limit = clamp(limit, dql->min_limit, dql->max_limit);
+
+	if (limit != dql->limit) {
+		dql->limit = limit;
+		ovlimit = 0;
+	}
+
+	dql->adj_limit = limit + completed;
+	dql->prev_ovlimit = ovlimit;
+	dql->prev_last_obj_cnt = dql->last_obj_cnt;
+	dql->num_completed = completed;
+	dql->prev_num_queued = num_queued;
+}
+EXPORT_SYMBOL(dql_completed);
+
+void dql_reset(struct dql *dql)
+{
+	/* Reset all dynamic values */
+	dql->limit = 0;
+	dql->num_queued = 0;
+	dql->num_completed = 0;
+	dql->last_obj_cnt = 0;
+	dql->prev_num_queued = 0;
+	dql->prev_last_obj_cnt = 0;
+	dql->prev_ovlimit = 0;
+	dql->lowest_slack = UINT_MAX;
+	dql->slack_start_time = jiffies;
+}
+EXPORT_SYMBOL(dql_reset);
+
+int dql_init(struct dql *dql, unsigned hold_time)
+{
+	dql->max_limit = DQL_MAX_LIMIT;
+	dql->min_limit = 0;
+	dql->slack_hold_time = hold_time;
+	dql_reset(dql);
+	return 0;
+}
+EXPORT_SYMBOL(dql_init);

lcd-domains/scripts/Kbuild.liblcd

@@ -39,6 +39,8 @@ lib-y += $(addprefix liblcd/lib/, \
 	crc16.o \
 	parser.o \
 	cmdline.o \
+	dynamic_queue_limits.o \
+	checksum.o \
 	)
 
 lib-y += $(addprefix liblcd/mm/, \