[net-next PATCH v3 0/3] net: reserve ports for applications using fixed port numbers

[net-next PATCH v3 0/3] net: reserve ports for applications using fixed port numbers

[Octavian Purdila]

This patch series is based on Amerigo's v2 but it now uses a bitmap
for port reservation.

I've ran a while (1) { bind(0) } test (with ip_local_port_range
1024 65000) to see if there is any performance difference between the
two approaches (ranges vs bitmap). I could not detect any significant
difference, both cases scored in 2.76s +/- 0.01 on my setup.

I've based this patch series on current net-next, but it contains a
significant non networking part. Please let me know if I should handle
this differently.

Octavian Purdila (3):
  sysctl: refactor integer handling proc code
  sysctl: add proc_dobitmap
  net: reserve ports for applications using fixed port numbers

 Documentation/networking/ip-sysctl.txt |   12 +
 drivers/infiniband/core/cma.c          |    7 +-
 include/linux/sysctl.h                 |    2 +
 include/net/ip.h                       |    6 +
 kernel/sysctl.c                        |  374 +++++++++++++++++++-------------
 net/ipv4/inet_connection_sock.c        |    5 +
 net/ipv4/inet_hashtables.c             |    2 +
 net/ipv4/sysctl_net_ipv4.c             |    7 +
 net/ipv4/udp.c                         |    3 +-
 net/sctp/socket.c                      |    2 +
 10 files changed, 264 insertions(+), 156 deletions(-)

[net-next PATCH v3 1/3] sysctl: refactor integer handling proc code

[Octavian Purdila]

As we are about to add another integer handling proc function a little
bit of cleanup is in order: add a few helper functions to improve code
readability and decrease code duplication.

In the process a bug is fixed as well: if the user specifies a number
with more then 20 digits it will be interpreted as two integers
(e.g. 10000...13 will be interpreted as 100.... and 13).

Signed-off-by: Octavian Purdila <opurdila@ixiacom.com>
Cc: WANG Cong <amwang@redhat.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
---
 kernel/sysctl.c |  298 +++++++++++++++++++++++++++----------------------------
 1 files changed, 144 insertions(+), 154 deletions(-)

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 8a68b24..b0f9618 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2039,8 +2039,98 @@ int proc_dostring(struct ctl_table *table, int write,
 			       buffer, lenp, ppos);
 }
 
+static int proc_skip_wspace(char __user **buf, size_t *size)
+{
+	char c;
+
+	while (*size) {
+		if (get_user(c, *buf))
+			return -EFAULT;
+		if (!isspace(c))
+			break;
+		(*size)--; (*buf)++;
+	}
+
+	return 0;
+}
+
+#define TMPBUFLEN 22
+static int proc_get_next_ulong(char __user **buf, size_t *size,
+			       unsigned long *val, bool *neg)
+{
+	int len;
+	char *p, tmp[TMPBUFLEN];
+	int err;
+
+	err = proc_skip_wspace(buf, size);
+	if (err)
+		return err;
+	if (!*size)
+		return -EINVAL;
+
+	len = *size;
+	if (len > TMPBUFLEN-1)
+		len = TMPBUFLEN-1;
+
+	if (copy_from_user(tmp, *buf, len))
+		return -EFAULT;
+
+	tmp[len] = 0;
+	p = tmp;
+	if (*p == '-' && *size > 1) {
+		*neg = 1;
+		p++;
+	} else
+		*neg = 0;
+	if (*p < '0' || *p > '9')
+		return -EINVAL;
+
+	*val = simple_strtoul(p, &p, 0);
+
+	len = p - tmp;
+	if (((len < *size) && *p && !isspace(*p)) ||
+	    /* We don't know if the next char is whitespace thus we may accept
+	     * invalid integers (e.g. 1234...a) or two integers instead of one
+	     * (e.g. 123...1). So lets not allow such large numbers. */
+	    len == TMPBUFLEN - 1)
+		return -EINVAL;
 
-static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
+	*buf += len; *size -= len;
+
+	return 0;
+}
+
+static int proc_put_ulong(char __user **buf, size_t *size, unsigned long val,
+			  bool neg, bool first)
+{
+	int len;
+	char tmp[TMPBUFLEN], *p = tmp;
+
+	if (!first)
+		*p++ = '\t';
+	sprintf(p, "%s%lu", neg ? "-" : "", val);
+	len = strlen(tmp);
+	if (len > *size)
+		len = *size;
+	if (copy_to_user(*buf, tmp, len))
+		return -EFAULT;
+	*size -= len;
+	*buf += len;
+	return 0;
+}
+#undef TMPBUFLEN
+
+static int proc_put_newline(char __user **buf, size_t *size)
+{
+	if (*size) {
+		if (put_user('\n', *buf))
+			return -EFAULT;
+		(*size)--, (*buf)++;
+	}
+	return 0;
+}
+
+static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
 				 int *valp,
 				 int write, void *data)
 {
@@ -2049,7 +2139,7 @@ static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
 	} else {
 		int val = *valp;
 		if (val < 0) {
-			*negp = -1;
+			*negp = 1;
 			*lvalp = (unsigned long)-val;
 		} else {
 			*negp = 0;
@@ -2060,19 +2150,15 @@ static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
 }
 
 static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
-		  int write, void __user *buffer,
+		  int write, void __user *_buffer,
 		  size_t *lenp, loff_t *ppos,
-		  int (*conv)(int *negp, unsigned long *lvalp, int *valp,
+		  int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
 			      int write, void *data),
 		  void *data)
 {
-#define TMPBUFLEN 21
-	int *i, vleft, first = 1, neg;
-	unsigned long lval;
-	size_t left, len;
-	
-	char buf[TMPBUFLEN], *p;
-	char __user *s = buffer;
+	int *i, vleft, first = 1, err = 0;
+	size_t left;
+	char __user *buffer = (char __user *) _buffer;
 	
 	if (!tbl_data || !table->maxlen || !*lenp ||
 	    (*ppos && !write)) {
@@ -2088,88 +2174,39 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
 		conv = do_proc_dointvec_conv;
 
 	for (; left && vleft--; i++, first=0) {
-		if (write) {
-			while (left) {
-				char c;
-				if (get_user(c, s))
-					return -EFAULT;
-				if (!isspace(c))
-					break;
-				left--;
-				s++;
-			}
-			if (!left)
-				break;
-			neg = 0;
-			len = left;
-			if (len > sizeof(buf) - 1)
-				len = sizeof(buf) - 1;
-			if (copy_from_user(buf, s, len))
-				return -EFAULT;
-			buf[len] = 0;
-			p = buf;
-			if (*p == '-' && left > 1) {
-				neg = 1;
-				p++;
-			}
-			if (*p < '0' || *p > '9')
-				break;
-
-			lval = simple_strtoul(p, &p, 0);
+		unsigned long lval;
+		bool neg;
 
-			len = p-buf;
-			if ((len < left) && *p && !isspace(*p))
+		if (write) {
+			err = proc_get_next_ulong(&buffer, &left, &lval, &neg);
+			if (err)
 				break;
-			s += len;
-			left -= len;
-
 			if (conv(&neg, &lval, i, 1, data))
 				break;
 		} else {
-			p = buf;
-			if (!first)
-				*p++ = '\t';
-	
 			if (conv(&neg, &lval, i, 0, data))
 				break;
-
-			sprintf(p, "%s%lu", neg ? "-" : "", lval);
-			len = strlen(buf);
-			if (len > left)
-				len = left;
-			if(copy_to_user(s, buf, len))
-				return -EFAULT;
-			left -= len;
-			s += len;
-		}
-	}
-
-	if (!write && !first && left) {
-		if(put_user('\n', s))
-			return -EFAULT;
-		left--, s++;
-	}
-	if (write) {
-		while (left) {
-			char c;
-			if (get_user(c, s++))
-				return -EFAULT;
-			if (!isspace(c))
+			err = proc_put_ulong(&buffer, &left, lval, neg, first);
+			if (err)
 				break;
-			left--;
 		}
 	}
-	if (write && first)
-		return -EINVAL;
+
+	if (!write && !first && left && !err)
+		err = proc_put_newline(&buffer, &left);
+	if (write && !err)
+		err = proc_skip_wspace(&buffer, &left);
+	if (err == -EFAULT /* do we really need to check for -EFAULT? */ ||
+	    (write && first))
+		return err ? : -EINVAL;
 	*lenp -= left;
 	*ppos += *lenp;
 	return 0;
-#undef TMPBUFLEN
 }
 
 static int do_proc_dointvec(struct ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos,
-		  int (*conv)(int *negp, unsigned long *lvalp, int *valp,
+		  int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
 			      int write, void *data),
 		  void *data)
 {
@@ -2237,8 +2274,8 @@ struct do_proc_dointvec_minmax_conv_param {
 	int *max;
 };
 
-static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp, 
-					int *valp, 
+static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp,
+					int *valp,
 					int write, void *data)
 {
 	struct do_proc_dointvec_minmax_conv_param *param = data;
@@ -2251,7 +2288,7 @@ static int do_proc_dointvec_minmax_conv(int *negp, unsigned long *lvalp,
 	} else {
 		int val = *valp;
 		if (val < 0) {
-			*negp = -1;
+			*negp = 1;
 			*lvalp = (unsigned long)-val;
 		} else {
 			*negp = 0;
@@ -2289,17 +2326,15 @@ int proc_dointvec_minmax(struct ctl_table *table, int write,
 }
 
 static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write,
-				     void __user *buffer,
+				     void __user *_buffer,
 				     size_t *lenp, loff_t *ppos,
 				     unsigned long convmul,
 				     unsigned long convdiv)
 {
-#define TMPBUFLEN 21
-	unsigned long *i, *min, *max, val;
-	int vleft, first=1, neg;
-	size_t len, left;
-	char buf[TMPBUFLEN], *p;
-	char __user *s = buffer;
+	unsigned long *i, *min, *max;
+	int vleft, first = 1, err = 0;
+	size_t left;
+	char __user *buffer = (char __user *) _buffer;
 	
 	if (!data || !table->maxlen || !*lenp ||
 	    (*ppos && !write)) {
@@ -2314,82 +2349,37 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
 	left = *lenp;
 	
 	for (; left && vleft--; i++, min++, max++, first=0) {
+		unsigned long val;
+
 		if (write) {
-			while (left) {
-				char c;
-				if (get_user(c, s))
-					return -EFAULT;
-				if (!isspace(c))
-					break;
-				left--;
-				s++;
-			}
-			if (!left)
-				break;
-			neg = 0;
-			len = left;
-			if (len > TMPBUFLEN-1)
-				len = TMPBUFLEN-1;
-			if (copy_from_user(buf, s, len))
-				return -EFAULT;
-			buf[len] = 0;
-			p = buf;
-			if (*p == '-' && left > 1) {
-				neg = 1;
-				p++;
-			}
-			if (*p < '0' || *p > '9')
-				break;
-			val = simple_strtoul(p, &p, 0) * convmul / convdiv ;
-			len = p-buf;
-			if ((len < left) && *p && !isspace(*p))
+			bool neg;
+
+			err = proc_get_next_ulong(&buffer, &left, &val, &neg);
+			if (err)
 				break;
 			if (neg)
-				val = -val;
-			s += len;
-			left -= len;
-
-			if(neg)
 				continue;
 			if ((min && val < *min) || (max && val > *max))
 				continue;
 			*i = val;
 		} else {
-			p = buf;
-			if (!first)
-				*p++ = '\t';
-			sprintf(p, "%lu", convdiv * (*i) / convmul);
-			len = strlen(buf);
-			if (len > left)
-				len = left;
-			if(copy_to_user(s, buf, len))
-				return -EFAULT;
-			left -= len;
-			s += len;
-		}
-	}
-
-	if (!write && !first && left) {
-		if(put_user('\n', s))
-			return -EFAULT;
-		left--, s++;
-	}
-	if (write) {
-		while (left) {
-			char c;
-			if (get_user(c, s++))
-				return -EFAULT;
-			if (!isspace(c))
+			val = convdiv * (*i) / convmul;
+			err = proc_put_ulong(&buffer, &left, val, 0, first);
+			if (err)
 				break;
-			left--;
 		}
 	}
-	if (write && first)
-		return -EINVAL;
+
+	if (!write && !first && left && !err)
+		err = proc_put_newline(&buffer, &left);
+	if (write && !err)
+		err = proc_skip_wspace(&buffer, &left);
+	if (err == -EFAULT /* do we really need to check for -EFAULT? */ ||
+	    (write && first))
+		return err ? : -EINVAL;
 	*lenp -= left;
 	*ppos += *lenp;
 	return 0;
-#undef TMPBUFLEN
 }
 
 static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
@@ -2450,7 +2440,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
 }
 
 
-static int do_proc_dointvec_jiffies_conv(int *negp, unsigned long *lvalp,
+static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp,
 					 int *valp,
 					 int write, void *data)
 {
@@ -2462,7 +2452,7 @@ static int do_proc_dointvec_jiffies_conv(int *negp, unsigned long *lvalp,
 		int val = *valp;
 		unsigned long lval;
 		if (val < 0) {
-			*negp = -1;
+			*negp = 1;
 			lval = (unsigned long)-val;
 		} else {
 			*negp = 0;
@@ -2473,7 +2463,7 @@ static int do_proc_dointvec_jiffies_conv(int *negp, unsigned long *lvalp,
 	return 0;
 }
 
-static int do_proc_dointvec_userhz_jiffies_conv(int *negp, unsigned long *lvalp,
+static int do_proc_dointvec_userhz_jiffies_conv(bool *negp, unsigned long *lvalp,
 						int *valp,
 						int write, void *data)
 {
@@ -2485,7 +2475,7 @@ static int do_proc_dointvec_userhz_jiffies_conv(int *negp, unsigned long *lvalp,
 		int val = *valp;
 		unsigned long lval;
 		if (val < 0) {
-			*negp = -1;
+			*negp = 1;
 			lval = (unsigned long)-val;
 		} else {
 			*negp = 0;
@@ -2496,7 +2486,7 @@ static int do_proc_dointvec_userhz_jiffies_conv(int *negp, unsigned long *lvalp,
 	return 0;
 }
 
-static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp,
+static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp,
 					    int *valp,
 					    int write, void *data)
 {
@@ -2506,7 +2496,7 @@ static int do_proc_dointvec_ms_jiffies_conv(int *negp, unsigned long *lvalp,
 		int val = *valp;
 		unsigned long lval;
 		if (val < 0) {
-			*negp = -1;
+			*negp = 1;
 			lval = (unsigned long)-val;
 		} else {
 			*negp = 0;
-- 
1.5.6.5

[net-next PATCH v3 2/3] sysctl: add proc_dobitmap

[Octavian Purdila]

The new function can be used to update bitmaps via /proc. Bits can be
set by writing positive values in the file and cleared by writing
negative values (e.g. 0 2 will set bits 1 and 3, -0 -2 will clear
them). Reading will show only the set bits.

Signed-off-by: Octavian Purdila <opurdila@ixiacom.com>
Cc: WANG Cong <amwang@redhat.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
---
 include/linux/sysctl.h |    2 +
 kernel/sysctl.c        |   76 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 78 insertions(+), 0 deletions(-)

diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 9f236cd..ba89bf2 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -985,6 +985,8 @@ extern int proc_doulongvec_minmax(struct ctl_table *, int,
 				  void __user *, size_t *, loff_t *);
 extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int,
 				      void __user *, size_t *, loff_t *);
+extern int proc_dobitmap(struct ctl_table *, int,
+			 void __user *, size_t *, loff_t *);
 
 /*
  * Register a set of sysctl names by calling register_sysctl_table
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b0f9618..b8959f4 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2596,6 +2596,82 @@ static int proc_do_cad_pid(struct ctl_table *table, int write,
 	return 0;
 }
 
+/**
+ * proc_dobitmap - read/write from/to a bitmap
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ * @ppos: the current position in the file
+ *
+ * The bitmap is stored at table->data and the bitmap length (in bits)
+ * in table->maxlen. Reading from the proc file will show the set bits.
+ * Writing positive values sets the bits, negative values clears them
+ * (e.g. 0 2 sets the first and 3rd bit, -0 -2 clears them).
+ *
+ * Returns 0 on success.
+ */
+int proc_dobitmap(struct ctl_table *table, int write,
+		  void __user *_buffer, size_t *lenp, loff_t *ppos)
+{
+	bool first = 1;
+	unsigned long *bitmap = (unsigned long *) table->data;
+	unsigned long bitmap_len = table->maxlen;
+	int left = *lenp, err = 0;
+	char __user *buffer = (char __user *) _buffer;
+
+	if (!bitmap_len || !left || (*ppos && !write)) {
+		*lenp = 0;
+		return 0;
+	}
+
+	if (write) {
+		while (left) {
+			unsigned long val;
+			bool neg;
+
+			err = proc_get_next_ulong(&buffer, &left, &val, &neg);
+			if (err)
+				break;
+			if (val >= bitmap_len) {
+				err = -EINVAL;
+				break;
+			}
+			if (neg)
+				clear_bit(val, bitmap);
+			else
+				set_bit(val, bitmap);
+			first = 0;
+		}
+		if (!err)
+			err = proc_skip_wspace(&buffer, &left);
+	} else {
+		unsigned long bit = 0;
+
+		while (left) {
+			bit = find_next_bit(bitmap, bitmap_len, bit);
+			if (bit >= bitmap_len)
+				break;
+			err = proc_put_ulong(&buffer, &left, bit, 0, first);
+			if (err)
+				break;
+			first = 0; bit++;
+		}
+		if (!err)
+			err = proc_put_newline(&buffer, &left);
+	}
+
+	if (first && write && !err)
+		err = -EINVAL;
+	if (err == -EFAULT /* do we really need to check for -EFAULT? */ ||
+	    (write && first))
+		return err ? : -EINVAL;
+	*lenp -= left;
+	*ppos += *lenp;
+	return 0;
+}
+
 #else /* CONFIG_PROC_FS */
 
 int proc_dostring(struct ctl_table *table, int write,
-- 
1.5.6.5

[net-next PATCH v3 3/3] net: reserve ports for applications using fixed port numbers

[Octavian Purdila]

This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports
(bitmap type) which allows users to reserve ports for third-party
applications.

The reserved ports will not be used by automatic port assignments
(e.g. when calling connect() or bind() with port number 0). Explicit
port allocation behavior is unchanged.

Signed-off-by: Octavian Purdila <opurdila@ixiacom.com>
Signed-off-by: WANG Cong <amwang@redhat.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
---
 Documentation/networking/ip-sysctl.txt |   12 ++++++++++++
 drivers/infiniband/core/cma.c          |    7 ++++++-
 include/net/ip.h                       |    6 ++++++
 net/ipv4/inet_connection_sock.c        |    5 +++++
 net/ipv4/inet_hashtables.c             |    2 ++
 net/ipv4/sysctl_net_ipv4.c             |    7 +++++++
 net/ipv4/udp.c                         |    3 ++-
 net/sctp/socket.c                      |    2 ++
 8 files changed, 42 insertions(+), 2 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 2dc7a1d..23be7a4 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -564,6 +564,18 @@ ip_local_port_range - 2 INTEGERS
 	(i.e. by default) range 1024-4999 is enough to issue up to
 	2000 connections per second to systems supporting timestamps.
 
+ip_local_reserved_ports - BITMAP of 65536 ports
+	Specify the ports which are reserved for known third-party
+	applications. These ports will not be used by automatic port assignments
+	(e.g. when calling connect() or bind() with port number 0). Explicit
+	port allocation behavior is unchanged.
+
+	Reserving ports is done by writing positive numbers in this proc entry,
+	clearing them is done by writing negative numbers (e.g. 8080 reserves
+	port number, -8080 makes it available for automatic assignment again).
+
+	Default: Empty
+
 ip_nonlocal_bind - BOOLEAN
 	If set, allows processes to bind() to non-local IP addresses,
 	which can be quite useful - but may break some applications.
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index cc9b594..8248fc6 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1979,6 +1979,8 @@ retry:
 	/* FIXME: add proper port randomization per like inet_csk_get_port */
 	do {
 		ret = idr_get_new_above(ps, bind_list, next_port, &port);
+		if (inet_is_reserved_local_port(port))
+			ret = -EAGAIN;
 	} while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL));
 
 	if (ret)
@@ -2997,10 +2999,13 @@ static int __init cma_init(void)
 {
 	int ret, low, high, remaining;
 
-	get_random_bytes(&next_port, sizeof next_port);
 	inet_get_local_port_range(&low, &high);
+again:
+	get_random_bytes(&next_port, sizeof next_port);
 	remaining = (high - low) + 1;
 	next_port = ((unsigned int) next_port % remaining) + low;
+	if (inet_is_reserved_local_port(next_port))
+		goto again;
 
 	cma_wq = create_singlethread_workqueue("rdma_cm");
 	if (!cma_wq)
diff --git a/include/net/ip.h b/include/net/ip.h
index fb63371..ada8589 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -184,6 +184,12 @@ extern struct local_ports {
 } sysctl_local_ports;
 extern void inet_get_local_port_range(int *low, int *high);
 
+extern unsigned long sysctl_local_reserved_ports[65536/8/sizeof(unsigned long)];
+static inline int inet_is_reserved_local_port(int port)
+{
+	return test_bit(port, sysctl_local_reserved_ports);
+}
+
 extern int sysctl_ip_default_ttl;
 extern int sysctl_ip_nonlocal_bind;
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 8da6429..febfc6c 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -37,6 +37,8 @@ struct local_ports sysctl_local_ports __read_mostly = {
 	.range = { 32768, 61000 },
 };
 
+unsigned long sysctl_local_reserved_ports[65536/BITS_PER_LONG];
+
 void inet_get_local_port_range(int *low, int *high)
 {
 	unsigned seq;
@@ -108,6 +110,8 @@ again:
 
 		smallest_size = -1;
 		do {
+			if (inet_is_reserved_local_port(rover))
+				goto next_nolock;
 			head = &hashinfo->bhash[inet_bhashfn(net, rover,
 					hashinfo->bhash_size)];
 			spin_lock(&head->lock);
@@ -130,6 +134,7 @@ again:
 			break;
 		next:
 			spin_unlock(&head->lock);
+		next_nolock:
 			if (++rover > high)
 				rover = low;
 		} while (--remaining > 0);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 2b79377..d3e160a 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -456,6 +456,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		local_bh_disable();
 		for (i = 1; i <= remaining; i++) {
 			port = low + (i + offset) % remaining;
+			if (inet_is_reserved_local_port(port))
+				continue;
 			head = &hinfo->bhash[inet_bhashfn(net, port,
 					hinfo->bhash_size)];
 			spin_lock(&head->lock);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 7e3712c..48ca149 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -298,6 +298,13 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= ipv4_local_port_range,
 	},
+	{
+		.procname	= "ip_local_reserved_ports",
+		.data		= sysctl_local_reserved_ports,
+		.maxlen		= 65536,
+		.mode		= 0644,
+		.proc_handler	= proc_dobitmap,
+	},
 #ifdef CONFIG_IP_MULTICAST
 	{
 		.procname	= "igmp_max_memberships",
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 4f7d212..705e032 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -232,7 +232,8 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 			 */
 			do {
 				if (low <= snum && snum <= high &&
-				    !test_bit(snum >> udptable->log, bitmap))
+				    !test_bit(snum >> udptable->log, bitmap) &&
+				    !inet_is_reserved_local_port(snum))
 					goto found;
 				snum += rand;
 			} while (snum != first);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index f6d1e59..1f839d0 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5432,6 +5432,8 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 			rover++;
 			if ((rover < low) || (rover > high))
 				rover = low;
+			if (inet_is_reserved_local_port(rover))
+				continue;
 			index = sctp_phashfn(rover);
 			head = &sctp_port_hashtable[index];
 			sctp_spin_lock(&head->lock);
-- 
1.5.6.5

Re: [net-next PATCH v3 0/3] net: reserve ports for applications using fixed port numbers

[Cong Wang]

Octavian Purdila wrote:
> This patch series is based on Amerigo's v2 but it now uses a bitmap
> for port reservation.
> 
> I've ran a while (1) { bind(0) } test (with ip_local_port_range
> 1024 65000) to see if there is any performance difference between the
> two approaches (ranges vs bitmap). I could not detect any significant
> difference, both cases scored in 2.76s +/- 0.01 on my setup.
> 
> I've based this patch series on current net-next, but it contains a
> significant non networking part. Please let me know if I should handle
> this differently.
> 
> Octavian Purdila (3):
>   sysctl: refactor integer handling proc code
>   sysctl: add proc_dobitmap
>   net: reserve ports for applications using fixed port numbers
> 

(Sorry for the delay, we are having Chinese new year here.)

Thanks for your work, Octavian!

Your patches look nice, but I don't have much time to review them today,
I will have a detailed look tomorrow.

Thanks.

Re: [net-next PATCH v3 0/3] net: reserve ports for applications using fixed port numbers

[Cong Wang]

Octavian Purdila wrote:
> This patch series is based on Amerigo's v2 but it now uses a bitmap
> for port reservation.
> 
> I've ran a while (1) { bind(0) } test (with ip_local_port_range
> 1024 65000) to see if there is any performance difference between the
> two approaches (ranges vs bitmap). I could not detect any significant
> difference, both cases scored in 2.76s +/- 0.01 on my setup.
> 
> I've based this patch series on current net-next, but it contains a
> significant non networking part. Please let me know if I should handle
> this differently.
> 
> Octavian Purdila (3):
>   sysctl: refactor integer handling proc code
>   sysctl: add proc_dobitmap
>   net: reserve ports for applications using fixed port numbers
> 
>  Documentation/networking/ip-sysctl.txt |   12 +
>  drivers/infiniband/core/cma.c          |    7 +-
>  include/linux/sysctl.h                 |    2 +
>  include/net/ip.h                       |    6 +
>  kernel/sysctl.c                        |  374 +++++++++++++++++++-------------
>  net/ipv4/inet_connection_sock.c        |    5 +
>  net/ipv4/inet_hashtables.c             |    2 +
>  net/ipv4/sysctl_net_ipv4.c             |    7 +
>  net/ipv4/udp.c                         |    3 +-
>  net/sctp/socket.c                      |    2 +
>  10 files changed, 264 insertions(+), 156 deletions(-)
> 

Hey, Octavian, typo in netdev list name...

Could you please fix it and resend? So that this will get more reviews.

Thanks!

Re: [net-next PATCH v3 0/3] net: reserve ports for applications using fixed port numbers

[Octavian Purdila]

On Monday 15 February 2010 14:39:30 you wrote:
> Octavian Purdila wrote:
> > This patch series is based on Amerigo's v2 but it now uses a bitmap
> > for port reservation.
> >
> > I've ran a while (1) { bind(0) } test (with ip_local_port_range
> > 1024 65000) to see if there is any performance difference between the
> > two approaches (ranges vs bitmap). I could not detect any significant
> > difference, both cases scored in 2.76s +/- 0.01 on my setup.
> >
> > I've based this patch series on current net-next, but it contains a
> > significant non networking part. Please let me know if I should handle
> > this differently.
> >
> > Octavian Purdila (3):
> >   sysctl: refactor integer handling proc code
> >   sysctl: add proc_dobitmap
> >   net: reserve ports for applications using fixed port numbers
> >
> >  Documentation/networking/ip-sysctl.txt |   12 +
> >  drivers/infiniband/core/cma.c          |    7 +-
> >  include/linux/sysctl.h                 |    2 +
> >  include/net/ip.h                       |    6 +
> >  kernel/sysctl.c                        |  374
> > +++++++++++++++++++------------- net/ipv4/inet_connection_sock.c        |
> >    5 +
> >  net/ipv4/inet_hashtables.c             |    2 +
> >  net/ipv4/sysctl_net_ipv4.c             |    7 +
> >  net/ipv4/udp.c                         |    3 +-
> >  net/sctp/socket.c                      |    2 +
> >  10 files changed, 264 insertions(+), 156 deletions(-)
> 
> Hey, Octavian, typo in netdev list name...
> 
> Could you please fix it and resend? So that this will get more reviews.
> 

Sorry for that. I've already spotted it and resent it. I plan to send a new 
take end of this day (GMT + 2) which will also address Eric's comments by 
allocating the bitmap at init time.

Thanks,
tavi

Re: [net-next PATCH v3 0/3] net: reserve ports for applications using fixed port numbers

[Cong Wang]

Octavian Purdila wrote:
> On Monday 15 February 2010 14:39:30 you wrote:
>> Octavian Purdila wrote:
>>> This patch series is based on Amerigo's v2 but it now uses a bitmap
>>> for port reservation.
>>>
>>> I've ran a while (1) { bind(0) } test (with ip_local_port_range
>>> 1024 65000) to see if there is any performance difference between the
>>> two approaches (ranges vs bitmap). I could not detect any significant
>>> difference, both cases scored in 2.76s +/- 0.01 on my setup.
>>>
>>> I've based this patch series on current net-next, but it contains a
>>> significant non networking part. Please let me know if I should handle
>>> this differently.
>>>
>>> Octavian Purdila (3):
>>>   sysctl: refactor integer handling proc code
>>>   sysctl: add proc_dobitmap
>>>   net: reserve ports for applications using fixed port numbers
>>>
>>>  Documentation/networking/ip-sysctl.txt |   12 +
>>>  drivers/infiniband/core/cma.c          |    7 +-
>>>  include/linux/sysctl.h                 |    2 +
>>>  include/net/ip.h                       |    6 +
>>>  kernel/sysctl.c                        |  374
>>> +++++++++++++++++++------------- net/ipv4/inet_connection_sock.c        |
>>>    5 +
>>>  net/ipv4/inet_hashtables.c             |    2 +
>>>  net/ipv4/sysctl_net_ipv4.c             |    7 +
>>>  net/ipv4/udp.c                         |    3 +-
>>>  net/sctp/socket.c                      |    2 +
>>>  10 files changed, 264 insertions(+), 156 deletions(-)
>> Hey, Octavian, typo in netdev list name...
>>
>> Could you please fix it and resend? So that this will get more reviews.
>>
> 
> Sorry for that. I've already spotted it and resent it. I plan to send a new 
> take end of this day (GMT + 2) which will also address Eric's comments by 
> allocating the bitmap at init time.
> 

Ok, but I was not Cc'ed. :) Please keep me in Cc.

Thanks!

[net-next PATCH v3 0/3] net: reserve ports for applications using fixed port numbers

[Octavian Purdila]

(Resending to netdev since I've misspelled the email address. Apologies if you receive multiple copies)

This patch series is based on Amerigo's v2 but it now uses a bitmap
for port reservation.

I've ran a while (1) { bind(0) } test (with ip_local_port_range
1024 65000) to see if there is any performance difference between the
two approaches (ranges vs bitmap). I could not detect any significant
difference, both cases scored in 2.76s +/- 0.01 on my setup.

I've based this patch series on current net-next, but it contains a
significant non networking part. Please let me know if I should handle
this differently.

Octavian Purdila (3):
  sysctl: refactor integer handling proc code
  sysctl: add proc_dobitmap
  net: reserve ports for applications using fixed port numbers

 Documentation/networking/ip-sysctl.txt |   12 +
 drivers/infiniband/core/cma.c          |    7 +-
 include/linux/sysctl.h                 |    2 +
 include/net/ip.h                       |    6 +
 kernel/sysctl.c                        |  374 +++++++++++++++++++-------------
 net/ipv4/inet_connection_sock.c        |    5 +
 net/ipv4/inet_hashtables.c             |    2 +
 net/ipv4/sysctl_net_ipv4.c             |    7 +
 net/ipv4/udp.c                         |    3 +-
 net/sctp/socket.c                      |    2 +
 10 files changed, 264 insertions(+), 156 deletions(-)