[Patch v10 0/3] net: reserve ports for applications using fixed port numbers

[Patch v10 0/3] net: reserve ports for applications using fixed port numbers

[Amerigo Wang]

Changes from the previous version:
- Use 'true' and 'false' for bool's;
- Fix some coding style problems;
- Allow appending lines to bitmap proc file so that it will be
  easier to add new bits.

------------------>

This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports 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.

There are still some miss behaviors with regard to proc parsing in odd
invalid cases (for "40000\0-40001" all is acknowledged but only 40000
is accepted) but they are not easy to fix without changing the current
"acknowledge how much we accepted" behavior.

Because of that and because the same issues are present in the
existing proc_dointvec code as well I don't think its worth holding
the actual feature (port reservation) after such petty error recovery
issues.

[Patch 1/3] sysctl: refactor integer handling proc code

[Amerigo Wang]

(Based on Octavian's work, and I modified a lot.)

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 also fixed: 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).

Behavior for EFAULT handling was changed as well. Previous to this
patch, when an EFAULT error occurred in the middle of a write
operation, although some of the elements were set, that was not
acknowledged to the user (by shorting the write and returning the
number of bytes accepted). EFAULT is now treated just like any other
errors by acknowledging the amount of bytes accepted.

Signed-off-by: Octavian Purdila <opurdila@ixiacom.com>
Signed-off-by: WANG Cong <amwang@redhat.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
---

Index: linux-2.6/kernel/sysctl.c
===================================================================
--- linux-2.6.orig/kernel/sysctl.c
+++ linux-2.6/kernel/sysctl.c
@@ -2040,8 +2040,122 @@ int proc_dostring(struct ctl_table *tabl
 			       buffer, lenp, ppos);
 }
 
+static size_t proc_skip_spaces(char **buf)
+{
+	size_t ret;
+	char *tmp = skip_spaces(*buf);
+	ret = tmp - *buf;
+	*buf = tmp;
+	return ret;
+}
+
+#define TMPBUFLEN 22
+/**
+ * proc_get_long - reads an ASCII formated integer from a user buffer
+ *
+ * @buf - a kernel buffer
+ * @size - size of the kernel buffer
+ * @val - this is where the number will be stored
+ * @neg - set to %TRUE if number is negative
+ * @perm_tr - a vector which contains the allowed trailers
+ * @perm_tr_len - size of the perm_tr vector
+ * @tr - pointer to store the trailer character
+ *
+ * In case of success 0 is returned and buf and size are updated with
+ * the amount of bytes read. If tr is non NULL and a trailing
+ * character exist (size is non zero after returning from this
+ * function) tr is updated with the trailing character.
+ */
+static int proc_get_long(char **buf, size_t *size,
+			  unsigned long *val, bool *neg,
+			  const char *perm_tr, unsigned perm_tr_len, char *tr)
+{
+	int len;
+	char *p, tmp[TMPBUFLEN];
+
+	if (!*size)
+		return -EINVAL;
+
+	len = *size;
+	if (len > TMPBUFLEN - 1)
+		len = TMPBUFLEN - 1;
+
+	memcpy(tmp, *buf, len);
+
+	tmp[len] = 0;
+	p = tmp;
+	if (*p == '-' && *size > 1) {
+		*neg = true;
+		p++;
+	} else
+		*neg = false;
+	if (!isdigit(*p))
+		return -EINVAL;
+
+	*val = simple_strtoul(p, &p, 0);
 
-static int do_proc_dointvec_conv(int *negp, unsigned long *lvalp,
+	len = p - tmp;
+
+	/* 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. */
+	if (len == TMPBUFLEN - 1)
+		return -EINVAL;
+
+	if (len < *size && perm_tr_len && !memchr(perm_tr, *p, perm_tr_len))
+		return -EINVAL;
+
+	if (tr && (len < *size))
+		*tr = *p;
+
+	*buf += len;
+	*size -= len;
+
+	return 0;
+}
+
+/**
+ * proc_put_long - coverts an integer to a decimal ASCII formated string
+ *
+ * @buf - the user buffer
+ * @size - the size of the user buffer
+ * @val - the integer to be converted
+ * @neg - sign of the number, %TRUE for negative
+ *
+ * In case of success 0 is returned and buf and size are updated with
+ * the amount of bytes read.
+ */
+static int proc_put_long(void __user **buf, size_t *size, unsigned long val,
+			  bool neg)
+{
+	int len;
+	char tmp[TMPBUFLEN], *p = tmp;
+
+	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_char(void __user **buf, size_t *size, char c)
+{
+	if (*size) {
+		char __user **buffer = (char __user **)buf;
+		if (put_user(c, *buffer))
+			return -EFAULT;
+		(*size)--, (*buffer)++;
+		*buf = *buffer;
+	}
+	return 0;
+}
+
+static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
 				 int *valp,
 				 int write, void *data)
 {
@@ -2050,33 +2164,31 @@ static int do_proc_dointvec_conv(int *ne
 	} else {
 		int val = *valp;
 		if (val < 0) {
-			*negp = -1;
+			*negp = true;
 			*lvalp = (unsigned long)-val;
 		} else {
-			*negp = 0;
+			*negp = false;
 			*lvalp = (unsigned long)val;
 		}
 	}
 	return 0;
 }
 
+static const char proc_wspace_sep[] = { ' ', '\t', '\n' };
+
 static int __do_proc_dointvec(void *tbl_data, 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)
 {
-#define TMPBUFLEN 21
-	int *i, vleft, first = 1, neg;
-	unsigned long lval;
-	size_t left, len;
+	int *i, vleft, first = 1, err = 0;
+	unsigned long page = 0;
+	size_t left;
+	char *kbuf;
 	
-	char buf[TMPBUFLEN], *p;
-	char __user *s = buffer;
-	
-	if (!tbl_data || !table->maxlen || !*lenp ||
-	    (*ppos && !write)) {
+	if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) {
 		*lenp = 0;
 		return 0;
 	}
@@ -2088,89 +2200,69 @@ static int __do_proc_dointvec(void *tbl_
 	if (!conv)
 		conv = do_proc_dointvec_conv;
 
+	if (write) {
+		if (left > PAGE_SIZE - 1)
+			left = PAGE_SIZE - 1;
+		page = __get_free_page(GFP_TEMPORARY);
+		kbuf = (char *) page;
+		if (!kbuf)
+			return -ENOMEM;
+		if (copy_from_user(kbuf, buffer, left)) {
+			err = -EFAULT;
+			goto free;
+		}
+		kbuf[left] = 0;
+	}
+
 	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;
+		unsigned long lval;
+		bool neg;
 
-			lval = simple_strtoul(p, &p, 0);
+		if (write) {
+			left -= proc_skip_spaces(&kbuf);
 
-			len = p-buf;
-			if ((len < left) && *p && !isspace(*p))
+			err = proc_get_long(&kbuf, &left, &lval, &neg,
+					     proc_wspace_sep,
+					     sizeof(proc_wspace_sep), NULL);
+			if (err)
 				break;
-			s += len;
-			left -= len;
-
-			if (conv(&neg, &lval, i, 1, data))
+			if (conv(&neg, &lval, i, 1, data)) {
+				err = -EINVAL;
 				break;
+			}
 		} else {
-			p = buf;
+			if (conv(&neg, &lval, i, 0, data)) {
+				err = -EINVAL;
+				break;
+			}
 			if (!first)
-				*p++ = '\t';
-	
-			if (conv(&neg, &lval, i, 0, data))
+				err = proc_put_char(&buffer, &left, '\t');
+			if (err)
+				break;
+			err = proc_put_long(&buffer, &left, lval, neg);
+			if (err)
 				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 && !first && left && !err)
+		err = proc_put_char(&buffer, &left, '\n');
+	if (write && !err)
+		left -= proc_skip_spaces(&kbuf);
+free:
 	if (write) {
-		while (left) {
-			char c;
-			if (get_user(c, s++))
-				return -EFAULT;
-			if (!isspace(c))
-				break;
-			left--;
-		}
+		free_page(page);
+		if (first)
+			return err ? : -EINVAL;
 	}
-	if (write && first)
-		return -EINVAL;
 	*lenp -= left;
 	*ppos += *lenp;
-	return 0;
-#undef TMPBUFLEN
+	return err;
 }
 
 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)
 {
@@ -2238,8 +2330,8 @@ struct do_proc_dointvec_minmax_conv_para
 	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;
@@ -2252,10 +2344,10 @@ static int do_proc_dointvec_minmax_conv(
 	} else {
 		int val = *valp;
 		if (val < 0) {
-			*negp = -1;
+			*negp = true;
 			*lvalp = (unsigned long)-val;
 		} else {
-			*negp = 0;
+			*negp = false;
 			*lvalp = (unsigned long)val;
 		}
 	}
@@ -2295,102 +2387,78 @@ static int __do_proc_doulongvec_minmax(v
 				     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;
-	
-	if (!data || !table->maxlen || !*lenp ||
-	    (*ppos && !write)) {
+	unsigned long *i, *min, *max;
+	int vleft, first = 1, err = 0;
+	unsigned long page = 0;
+	size_t left;
+	char *kbuf;
+
+	if (!data || !table->maxlen || !*lenp || (*ppos && !write)) {
 		*lenp = 0;
 		return 0;
 	}
-	
+
 	i = (unsigned long *) data;
 	min = (unsigned long *) table->extra1;
 	max = (unsigned long *) table->extra2;
 	vleft = table->maxlen / sizeof(unsigned long);
 	left = *lenp;
-	
+
+	if (write) {
+		if (left > PAGE_SIZE - 1)
+			left = PAGE_SIZE - 1;
+		page = __get_free_page(GFP_TEMPORARY);
+		kbuf = (char *) page;
+		if (!kbuf)
+			return -ENOMEM;
+		if (copy_from_user(kbuf, buffer, left)) {
+			err = -EFAULT;
+			goto free;
+		}
+		kbuf[left] = 0;
+	}
+
 	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;
+
+			left -= proc_skip_spaces(&kbuf);
+
+			err = proc_get_long(&kbuf, &left, &val, &neg,
+					     proc_wspace_sep,
+					     sizeof(proc_wspace_sep), NULL);
+			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;
+			val = convdiv * (*i) / convmul;
 			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;
+				err = proc_put_char(&buffer, &left, '\t');
+			err = proc_put_long(&buffer, &left, val, false);
+			if (err)
+				break;
 		}
 	}
 
-	if (!write && !first && left) {
-		if(put_user('\n', s))
-			return -EFAULT;
-		left--, s++;
-	}
+	if (!write && !first && left && !err)
+		err = proc_put_char(&buffer, &left, '\n');
+	if (write && !err)
+		left -= proc_skip_spaces(&kbuf);
+free:
 	if (write) {
-		while (left) {
-			char c;
-			if (get_user(c, s++))
-				return -EFAULT;
-			if (!isspace(c))
-				break;
-			left--;
-		}
+		free_page(page);
+		if (first)
+			return err ? : -EINVAL;
 	}
-	if (write && first)
-		return -EINVAL;
 	*lenp -= left;
 	*ppos += *lenp;
-	return 0;
-#undef TMPBUFLEN
+	return err;
 }
 
 static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
@@ -2451,7 +2519,7 @@ int proc_doulongvec_ms_jiffies_minmax(st
 }
 
 
-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)
 {
@@ -2463,10 +2531,10 @@ static int do_proc_dointvec_jiffies_conv
 		int val = *valp;
 		unsigned long lval;
 		if (val < 0) {
-			*negp = -1;
+			*negp = true;
 			lval = (unsigned long)-val;
 		} else {
-			*negp = 0;
+			*negp = false;
 			lval = (unsigned long)val;
 		}
 		*lvalp = lval / HZ;
@@ -2474,7 +2542,7 @@ static int do_proc_dointvec_jiffies_conv
 	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)
 {
@@ -2486,10 +2554,10 @@ static int do_proc_dointvec_userhz_jiffi
 		int val = *valp;
 		unsigned long lval;
 		if (val < 0) {
-			*negp = -1;
+			*negp = true;
 			lval = (unsigned long)-val;
 		} else {
-			*negp = 0;
+			*negp = false;
 			lval = (unsigned long)val;
 		}
 		*lvalp = jiffies_to_clock_t(lval);
@@ -2497,7 +2565,7 @@ static int do_proc_dointvec_userhz_jiffi
 	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)
 {
@@ -2507,10 +2575,10 @@ static int do_proc_dointvec_ms_jiffies_c
 		int val = *valp;
 		unsigned long lval;
 		if (val < 0) {
-			*negp = -1;
+			*negp = true;
 			lval = (unsigned long)-val;
 		} else {
-			*negp = 0;
+			*negp = false;
 			lval = (unsigned long)val;
 		}
 		*lvalp = jiffies_to_msecs(lval);

[Patch 2/3] sysctl: add proc_do_large_bitmap

[Amerigo Wang]

From: Octavian Purdila <opurdila@ixiacom.com>

The new function can be used to read/write large bitmaps via /proc. A
comma separated range format is used for compact output and input
(e.g. 1,3-4,10-10).

Writing into the file will first reset the bitmap then update it
based on the given input.

Signed-off-by: Octavian Purdila <opurdila@ixiacom.com>
Signed-off-by: WANG Cong <amwang@redhat.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
---

Index: linux-2.6/include/linux/sysctl.h
===================================================================
--- linux-2.6.orig/include/linux/sysctl.h
+++ linux-2.6/include/linux/sysctl.h
@@ -980,6 +980,8 @@ extern int proc_doulongvec_minmax(struct
 				  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_do_large_bitmap(struct ctl_table *, int,
+				void __user *, size_t *, loff_t *);
 
 /*
  * Register a set of sysctl names by calling register_sysctl_table
Index: linux-2.6/kernel/sysctl.c
===================================================================
--- linux-2.6.orig/kernel/sysctl.c
+++ linux-2.6/kernel/sysctl.c
@@ -2049,6 +2049,16 @@ static size_t proc_skip_spaces(char **bu
 	return ret;
 }
 
+static void proc_skip_char(char **buf, size_t *size, const char v)
+{
+	while (*size) {
+		if (**buf != v)
+			break;
+		(*size)--;
+		(*buf)++;
+	}
+}
+
 #define TMPBUFLEN 22
 /**
  * proc_get_long - reads an ASCII formated integer from a user buffer
@@ -2675,6 +2685,157 @@ static int proc_do_cad_pid(struct ctl_ta
 	return 0;
 }
 
+/**
+ * proc_do_large_bitmap - read/write from/to a large 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
+ *
+ * The bitmap is stored at table->data and the bitmap length (in bits)
+ * in table->maxlen.
+ *
+ * We use a range comma separated format (e.g. 1,3-4,10-10) so that
+ * large bitmaps may be represented in a compact manner. Writing into
+ * the file will clear the bitmap then update it with the given input.
+ *
+ * Returns 0 on success.
+ */
+int proc_do_large_bitmap(struct ctl_table *table, int write,
+			 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int err = 0;
+	bool first = 1;
+	size_t left = *lenp;
+	unsigned long bitmap_len = table->maxlen;
+	unsigned long *bitmap = (unsigned long *) table->data;
+	unsigned long *tmp_bitmap = NULL;
+	char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c;
+
+	if (!bitmap_len || !left || (*ppos && !write)) {
+		*lenp = 0;
+		return 0;
+	}
+
+	if (write) {
+		unsigned long page = 0;
+		char *kbuf;
+
+		if (left > PAGE_SIZE - 1)
+			left = PAGE_SIZE - 1;
+
+		page = __get_free_page(GFP_TEMPORARY);
+		kbuf = (char *) page;
+		if (!kbuf)
+			return -ENOMEM;
+		if (copy_from_user(kbuf, buffer, left)) {
+			free_page(page);
+			return -EFAULT;
+                }
+		kbuf[left] = 0;
+
+		tmp_bitmap = kzalloc(BITS_TO_LONGS(bitmap_len) * sizeof(unsigned long),
+				     GFP_KERNEL);
+		if (!tmp_bitmap) {
+			free_page(page);
+			return -ENOMEM;
+		}
+		proc_skip_char(&kbuf, &left, '\n');
+		while (!err && left) {
+			unsigned long val_a, val_b;
+			bool neg;
+
+			err = proc_get_long(&kbuf, &left, &val_a, &neg, tr_a,
+					     sizeof(tr_a), &c);
+			if (err)
+				break;
+			if (val_a >= bitmap_len || neg) {
+				err = -EINVAL;
+				break;
+			}
+
+			val_b = val_a;
+			if (left) {
+				kbuf++;
+				left--;
+			}
+
+			if (c == '-') {
+				err = proc_get_long(&kbuf, &left, &val_b,
+						     &neg, tr_b, sizeof(tr_b),
+						     &c);
+				if (err)
+					break;
+				if (val_b >= bitmap_len || neg ||
+				    val_a > val_b) {
+					err = -EINVAL;
+					break;
+				}
+				if (left) {
+					kbuf++;
+					left--;
+				}
+			}
+
+			while (val_a <= val_b)
+				set_bit(val_a++, tmp_bitmap);
+
+			first = 0;
+			proc_skip_char(&kbuf, &left, '\n');
+		}
+		free_page(page);
+	} else {
+		unsigned long bit_a, bit_b = 0;
+
+		while (left) {
+			bit_a = find_next_bit(bitmap, bitmap_len, bit_b);
+			if (bit_a >= bitmap_len)
+				break;
+			bit_b = find_next_zero_bit(bitmap, bitmap_len,
+						   bit_a + 1) - 1;
+
+			if (!first) {
+				err = proc_put_char(&buffer, &left, ',');
+				if (err)
+					break;
+			}
+			err = proc_put_long(&buffer, &left, bit_a, false);
+			if (err)
+				break;
+			if (bit_a != bit_b) {
+				err = proc_put_char(&buffer, &left, '-');
+				if (err)
+					break;
+				err = proc_put_long(&buffer, &left, bit_b, false);
+				if (err)
+					break;
+			}
+
+			first = 0; bit_b++;
+		}
+		if (!err)
+			err = proc_put_char(&buffer, &left, '\n');
+	}
+
+	if (!err) {
+		if (write) {
+			if (*ppos)
+				bitmap_or(bitmap, bitmap, tmp_bitmap, bitmap_len);
+			else
+				memcpy(bitmap, tmp_bitmap,
+					BITS_TO_LONGS(bitmap_len) * sizeof(unsigned long));
+		}
+		kfree(tmp_bitmap);
+		*lenp -= left;
+		*ppos += *lenp;
+		return 0;
+	} else {
+		kfree(tmp_bitmap);
+		return err;
+	}
+}
+
 #else /* CONFIG_PROC_FS */
 
 int proc_dostring(struct ctl_table *table, int write,

[Patch 3/3] net: reserve ports for applications using fixed port numbers

[Amerigo Wang]

(Dropped the infiniband part, because Tetsuo modified the related code,
I will send a separate patch for it once this is accepted.)

This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports 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>
Cc: Eric W. Biederman <ebiederm@xmission.com>
---

Index: linux-2.6/Documentation/networking/ip-sysctl.txt
===================================================================
--- linux-2.6.orig/Documentation/networking/ip-sysctl.txt
+++ linux-2.6/Documentation/networking/ip-sysctl.txt
@@ -588,6 +588,37 @@ 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 - list of comma separated ranges
+	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.
+
+	The format used for both input and output is a comma separated
+	list of ranges (e.g. "1,2-4,10-10" for ports 1, 2, 3, 4 and
+	10). Writing to the file will clear all previously reserved
+	ports and update the current list with the one given in the
+	input.
+
+	Note that ip_local_port_range and ip_local_reserved_ports
+	settings are independent and both are considered by the kernel
+	when determining which ports are available for automatic port
+	assignments.
+
+	You can reserve ports which are not in the current
+	ip_local_port_range, e.g.:
+
+	$ cat /proc/sys/net/ipv4/ip_local_port_range
+	32000	61000
+	$ cat /proc/sys/net/ipv4/ip_local_reserved_ports
+	8080,9148
+
+	although this is redundant. However such a setting is useful
+	if later the port range is changed to a value that will
+	include the reserved ports.
+
+	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.
Index: linux-2.6/include/net/ip.h
===================================================================
--- linux-2.6.orig/include/net/ip.h
+++ linux-2.6/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;
+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;
 
Index: linux-2.6/net/ipv4/af_inet.c
===================================================================
--- linux-2.6.orig/net/ipv4/af_inet.c
+++ linux-2.6/net/ipv4/af_inet.c
@@ -1552,9 +1552,13 @@ static int __init inet_init(void)
 
 	BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb));
 
+	sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
+	if (!sysctl_local_reserved_ports)
+		goto out;
+
 	rc = proto_register(&tcp_prot, 1);
 	if (rc)
-		goto out;
+		goto out_free_reserved_ports;
 
 	rc = proto_register(&udp_prot, 1);
 	if (rc)
@@ -1653,6 +1657,8 @@ out_unregister_udp_proto:
 	proto_unregister(&udp_prot);
 out_unregister_tcp_proto:
 	proto_unregister(&tcp_prot);
+out_free_reserved_ports:
+	kfree(sysctl_local_reserved_ports);
 	goto out;
 }
 
Index: linux-2.6/net/ipv4/inet_connection_sock.c
===================================================================
--- linux-2.6.orig/net/ipv4/inet_connection_sock.c
+++ linux-2.6/net/ipv4/inet_connection_sock.c
@@ -37,6 +37,9 @@ struct local_ports sysctl_local_ports __
 	.range = { 32768, 61000 },
 };
 
+unsigned long *sysctl_local_reserved_ports;
+EXPORT_SYMBOL(sysctl_local_reserved_ports);
+
 void inet_get_local_port_range(int *low, int *high)
 {
 	unsigned seq;
@@ -108,6 +111,8 @@ 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 +135,7 @@ again:
 			break;
 		next:
 			spin_unlock(&head->lock);
+		next_nolock:
 			if (++rover > high)
 				rover = low;
 		} while (--remaining > 0);
Index: linux-2.6/net/ipv4/inet_hashtables.c
===================================================================
--- linux-2.6.orig/net/ipv4/inet_hashtables.c
+++ linux-2.6/net/ipv4/inet_hashtables.c
@@ -456,6 +456,8 @@ int __inet_hash_connect(struct inet_time
 		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);
Index: linux-2.6/net/ipv4/sysctl_net_ipv4.c
===================================================================
--- linux-2.6.orig/net/ipv4/sysctl_net_ipv4.c
+++ linux-2.6/net/ipv4/sysctl_net_ipv4.c
@@ -299,6 +299,13 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= ipv4_local_port_range,
 	},
+	{
+		.procname	= "ip_local_reserved_ports",
+		.data		= NULL, /* initialized in sysctl_ipv4_init */
+		.maxlen		= 65536,
+		.mode		= 0644,
+		.proc_handler	= proc_do_large_bitmap,
+	},
 #ifdef CONFIG_IP_MULTICAST
 	{
 		.procname	= "igmp_max_memberships",
@@ -736,6 +743,16 @@ static __net_initdata struct pernet_oper
 static __init int sysctl_ipv4_init(void)
 {
 	struct ctl_table_header *hdr;
+	struct ctl_table *i;
+
+	for (i = ipv4_table; i->procname; i++) {
+		if (strcmp(i->procname, "ip_local_reserved_ports") == 0) {
+			i->data = sysctl_local_reserved_ports;
+			break;
+		}
+	}
+	if (!i->procname)
+		return -EINVAL;
 
 	hdr = register_sysctl_paths(net_ipv4_ctl_path, ipv4_table);
 	if (hdr == NULL)
Index: linux-2.6/net/ipv4/udp.c
===================================================================
--- linux-2.6.orig/net/ipv4/udp.c
+++ linux-2.6/net/ipv4/udp.c
@@ -233,7 +233,8 @@ int udp_lib_get_port(struct sock *sk, un
 			 */
 			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);
Index: linux-2.6/net/sctp/socket.c
===================================================================
--- linux-2.6.orig/net/sctp/socket.c
+++ linux-2.6/net/sctp/socket.c
@@ -5436,6 +5436,8 @@ static long sctp_get_port_local(struct s
 			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);

Re: [Patch v10 0/3] net: reserve ports for applications using fixed port numbers

[Cong Wang]

(Adding Andrew into Cc, hope can hear from him.)

On 05/05/10 18:26, Amerigo Wang wrote:
> Changes from the previous version:
> - Use 'true' and 'false' for bool's;
> - Fix some coding style problems;
> - Allow appending lines to bitmap proc file so that it will be
>    easier to add new bits.
>
> ------------------>
>
> This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports 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.
>
> There are still some miss behaviors with regard to proc parsing in odd
> invalid cases (for "40000\0-40001" all is acknowledged but only 40000
> is accepted) but they are not easy to fix without changing the current
> "acknowledge how much we accepted" behavior.
>
> Because of that and because the same issues are present in the
> existing proc_dointvec code as well I don't think its worth holding
> the actual feature (port reservation) after such petty error recovery
> issues.
>
>

Re: [Patch v10 0/3] net: reserve ports for applications using fixed port numbers

[David Miller]

From: Amerigo Wang <amwang@redhat.com>
Date: Wed, 5 May 2010 06:26:34 -0400

> 
> Changes from the previous version:
> - Use 'true' and 'false' for bool's;
> - Fix some coding style problems;
> - Allow appending lines to bitmap proc file so that it will be
>   easier to add new bits.

Applied to net-next-2.6, thanks.

[Patch v9 0/3] net: reserve ports for applications using fixed port numbers

[Amerigo Wang]

Changes from the previous version:
- Dropped the infiniband part, because Tetsuo modified the related code,
  I will send a separate patch for it once this is accepted.
- Fixed some '\0' issues introduced by the previous version.
- Use copy_from_user(), instead of get_user().
- Use memchr().

------------------>

This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports 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.

There are still some miss behaviors with regard to proc parsing in odd
invalid cases (for "40000\0-40001" all is acknowledged but only 40000
is accepted) but they are not easy to fix without changing the current
"acknowledge how much we accepted" behavior.

Because of that and because the same issues are present in the
existing proc_dointvec code as well I don't think its worth holding
the actual feature (port reservation) after such petty error recovery
issues.

[Patch 3/3] net: reserve ports for applications using fixed port numbers

[Amerigo Wang]

(Dropped the infiniband part, because Tetsuo modified the related code,
I will send a separate patch for it once this is accepted.)

This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports 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>
Cc: Eric W. Biederman <ebiederm@xmission.com>
---

Index: linux-2.6/Documentation/networking/ip-sysctl.txt
===================================================================
--- linux-2.6.orig/Documentation/networking/ip-sysctl.txt
+++ linux-2.6/Documentation/networking/ip-sysctl.txt
@@ -588,6 +588,37 @@ 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 - list of comma separated ranges
+	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.
+
+	The format used for both input and output is a comma separated
+	list of ranges (e.g. "1,2-4,10-10" for ports 1, 2, 3, 4 and
+	10). Writing to the file will clear all previously reserved
+	ports and update the current list with the one given in the
+	input.
+
+	Note that ip_local_port_range and ip_local_reserved_ports
+	settings are independent and both are considered by the kernel
+	when determining which ports are available for automatic port
+	assignments.
+
+	You can reserve ports which are not in the current
+	ip_local_port_range, e.g.:
+
+	$ cat /proc/sys/net/ipv4/ip_local_port_range
+	32000	61000
+	$ cat /proc/sys/net/ipv4/ip_local_reserved_ports
+	8080,9148
+
+	although this is redundant. However such a setting is useful
+	if later the port range is changed to a value that will
+	include the reserved ports.
+
+	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.
Index: linux-2.6/include/net/ip.h
===================================================================
--- linux-2.6.orig/include/net/ip.h
+++ linux-2.6/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;
+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;
 
Index: linux-2.6/net/ipv4/af_inet.c
===================================================================
--- linux-2.6.orig/net/ipv4/af_inet.c
+++ linux-2.6/net/ipv4/af_inet.c
@@ -1552,9 +1552,13 @@ static int __init inet_init(void)
 
 	BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb));
 
+	sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
+	if (!sysctl_local_reserved_ports)
+		goto out;
+
 	rc = proto_register(&tcp_prot, 1);
 	if (rc)
-		goto out;
+		goto out_free_reserved_ports;
 
 	rc = proto_register(&udp_prot, 1);
 	if (rc)
@@ -1653,6 +1657,8 @@ out_unregister_udp_proto:
 	proto_unregister(&udp_prot);
 out_unregister_tcp_proto:
 	proto_unregister(&tcp_prot);
+out_free_reserved_ports:
+	kfree(sysctl_local_reserved_ports);
 	goto out;
 }
 
Index: linux-2.6/net/ipv4/inet_connection_sock.c
===================================================================
--- linux-2.6.orig/net/ipv4/inet_connection_sock.c
+++ linux-2.6/net/ipv4/inet_connection_sock.c
@@ -37,6 +37,9 @@ struct local_ports sysctl_local_ports __
 	.range = { 32768, 61000 },
 };
 
+unsigned long *sysctl_local_reserved_ports;
+EXPORT_SYMBOL(sysctl_local_reserved_ports);
+
 void inet_get_local_port_range(int *low, int *high)
 {
 	unsigned seq;
@@ -112,6 +115,8 @@ 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);
@@ -136,6 +141,7 @@ again:
 			break;
 		next:
 			spin_unlock(&head->lock);
+		next_nolock:
 			if (++rover > high)
 				rover = low;
 		} while (--remaining > 0);
Index: linux-2.6/net/ipv4/inet_hashtables.c
===================================================================
--- linux-2.6.orig/net/ipv4/inet_hashtables.c
+++ linux-2.6/net/ipv4/inet_hashtables.c
@@ -456,6 +456,8 @@ int __inet_hash_connect(struct inet_time
 		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);
Index: linux-2.6/net/ipv4/sysctl_net_ipv4.c
===================================================================
--- linux-2.6.orig/net/ipv4/sysctl_net_ipv4.c
+++ linux-2.6/net/ipv4/sysctl_net_ipv4.c
@@ -299,6 +299,13 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= ipv4_local_port_range,
 	},
+	{
+		.procname	= "ip_local_reserved_ports",
+		.data		= NULL, /* initialized in sysctl_ipv4_init */
+		.maxlen		= 65536,
+		.mode		= 0644,
+		.proc_handler	= proc_do_large_bitmap,
+	},
 #ifdef CONFIG_IP_MULTICAST
 	{
 		.procname	= "igmp_max_memberships",
@@ -736,6 +743,16 @@ static __net_initdata struct pernet_oper
 static __init int sysctl_ipv4_init(void)
 {
 	struct ctl_table_header *hdr;
+	struct ctl_table *i;
+
+	for (i = ipv4_table; i->procname; i++) {
+		if (strcmp(i->procname, "ip_local_reserved_ports") == 0) {
+			i->data = sysctl_local_reserved_ports;
+			break;
+		}
+	}
+	if (!i->procname)
+		return -EINVAL;
 
 	hdr = register_sysctl_paths(net_ipv4_ctl_path, ipv4_table);
 	if (hdr == NULL)
Index: linux-2.6/net/ipv4/udp.c
===================================================================
--- linux-2.6.orig/net/ipv4/udp.c
+++ linux-2.6/net/ipv4/udp.c
@@ -233,7 +233,8 @@ int udp_lib_get_port(struct sock *sk, un
 			 */
 			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);
Index: linux-2.6/net/sctp/socket.c
===================================================================
--- linux-2.6.orig/net/sctp/socket.c
+++ linux-2.6/net/sctp/socket.c
@@ -5436,6 +5436,8 @@ static long sctp_get_port_local(struct s
 			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);

[Patch v8 0/3] net: reserve ports for applications using fixed port numbers

[Amerigo Wang]

Changes from the previous version:
- Rename proc_{get,put}_ulong to proc_{get,put}_long();
- Fix potential dead loop problems in cma code.

------------->

This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports 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.

There are still some miss behaviors with regard to proc parsing in odd
invalid cases (for "40000\0-40001" all is acknowledged but only 40000
is accepted) but they are not easy to fix without changing the current
"acknowledge how much we accepted" behavior.

Because of that and because the same issues are present in the
existing proc_dointvec code as well I don't think its worth holding
the actual feature (port reservation) after such petty error recovery
issues.

[Patch 3/3] net: reserve ports for applications using fixed port numbers

[Amerigo Wang]

From: Octavian Purdila <opurdila@ixiacom.com>

This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports 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>
Cc: Eric W. Biederman <ebiederm@xmission.com>
---

Index: linux-2.6/Documentation/networking/ip-sysctl.txt
===================================================================
--- linux-2.6.orig/Documentation/networking/ip-sysctl.txt
+++ linux-2.6/Documentation/networking/ip-sysctl.txt
@@ -588,6 +588,37 @@ 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 - list of comma separated ranges
+	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.
+
+	The format used for both input and output is a comma separated
+	list of ranges (e.g. "1,2-4,10-10" for ports 1, 2, 3, 4 and
+	10). Writing to the file will clear all previously reserved
+	ports and update the current list with the one given in the
+	input.
+
+	Note that ip_local_port_range and ip_local_reserved_ports
+	settings are independent and both are considered by the kernel
+	when determining which ports are available for automatic port
+	assignments.
+
+	You can reserve ports which are not in the current
+	ip_local_port_range, e.g.:
+
+	$ cat /proc/sys/net/ipv4/ip_local_port_range
+	32000	61000
+	$ cat /proc/sys/net/ipv4/ip_local_reserved_ports
+	8080,9148
+
+	although this is redundant. However such a setting is useful
+	if later the port range is changed to a value that will
+	include the reserved ports.
+
+	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.
Index: linux-2.6/drivers/infiniband/core/cma.c
===================================================================
--- linux-2.6.orig/drivers/infiniband/core/cma.c
+++ linux-2.6/drivers/infiniband/core/cma.c
@@ -1980,6 +1980,8 @@ 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 (!ret && inet_is_reserved_local_port(port))
+			ret = -EAGAIN;
 	} while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL));
 
 	if (ret)
@@ -2995,11 +2997,19 @@ static void cma_remove_one(struct ib_dev
 static int __init cma_init(void)
 {
 	int ret, low, high, remaining;
+	int tries = 10;
 
-	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)) {
+		if (tries--)
+			goto again;
+		else
+			return -EBUSY;
+	}
 
 	cma_wq = create_singlethread_workqueue("rdma_cm");
 	if (!cma_wq)
Index: linux-2.6/include/net/ip.h
===================================================================
--- linux-2.6.orig/include/net/ip.h
+++ linux-2.6/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;
+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;
 
Index: linux-2.6/net/ipv4/af_inet.c
===================================================================
--- linux-2.6.orig/net/ipv4/af_inet.c
+++ linux-2.6/net/ipv4/af_inet.c
@@ -1552,9 +1552,13 @@ static int __init inet_init(void)
 
 	BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb));
 
+	sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
+	if (!sysctl_local_reserved_ports)
+		goto out;
+
 	rc = proto_register(&tcp_prot, 1);
 	if (rc)
-		goto out;
+		goto out_free_reserved_ports;
 
 	rc = proto_register(&udp_prot, 1);
 	if (rc)
@@ -1653,6 +1657,8 @@ out_unregister_udp_proto:
 	proto_unregister(&udp_prot);
 out_unregister_tcp_proto:
 	proto_unregister(&tcp_prot);
+out_free_reserved_ports:
+	kfree(sysctl_local_reserved_ports);
 	goto out;
 }
 
Index: linux-2.6/net/ipv4/inet_connection_sock.c
===================================================================
--- linux-2.6.orig/net/ipv4/inet_connection_sock.c
+++ linux-2.6/net/ipv4/inet_connection_sock.c
@@ -37,6 +37,9 @@ struct local_ports sysctl_local_ports __
 	.range = { 32768, 61000 },
 };
 
+unsigned long *sysctl_local_reserved_ports;
+EXPORT_SYMBOL(sysctl_local_reserved_ports);
+
 void inet_get_local_port_range(int *low, int *high)
 {
 	unsigned seq;
@@ -108,6 +111,8 @@ 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 +135,7 @@ again:
 			break;
 		next:
 			spin_unlock(&head->lock);
+		next_nolock:
 			if (++rover > high)
 				rover = low;
 		} while (--remaining > 0);
Index: linux-2.6/net/ipv4/inet_hashtables.c
===================================================================
--- linux-2.6.orig/net/ipv4/inet_hashtables.c
+++ linux-2.6/net/ipv4/inet_hashtables.c
@@ -456,6 +456,8 @@ int __inet_hash_connect(struct inet_time
 		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);
Index: linux-2.6/net/ipv4/sysctl_net_ipv4.c
===================================================================
--- linux-2.6.orig/net/ipv4/sysctl_net_ipv4.c
+++ linux-2.6/net/ipv4/sysctl_net_ipv4.c
@@ -299,6 +299,13 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= ipv4_local_port_range,
 	},
+	{
+		.procname	= "ip_local_reserved_ports",
+		.data		= NULL, /* initialized in sysctl_ipv4_init */
+		.maxlen		= 65536,
+		.mode		= 0644,
+		.proc_handler	= proc_do_large_bitmap,
+	},
 #ifdef CONFIG_IP_MULTICAST
 	{
 		.procname	= "igmp_max_memberships",
@@ -736,6 +743,16 @@ static __net_initdata struct pernet_oper
 static __init int sysctl_ipv4_init(void)
 {
 	struct ctl_table_header *hdr;
+	struct ctl_table *i;
+
+	for (i = ipv4_table; i->procname; i++) {
+		if (strcmp(i->procname, "ip_local_reserved_ports") == 0) {
+			i->data = sysctl_local_reserved_ports;
+			break;
+		}
+	}
+	if (!i->procname)
+		return -EINVAL;
 
 	hdr = register_sysctl_paths(net_ipv4_ctl_path, ipv4_table);
 	if (hdr == NULL)
Index: linux-2.6/net/ipv4/udp.c
===================================================================
--- linux-2.6.orig/net/ipv4/udp.c
+++ linux-2.6/net/ipv4/udp.c
@@ -233,7 +233,8 @@ int udp_lib_get_port(struct sock *sk, un
 			 */
 			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);
Index: linux-2.6/net/sctp/socket.c
===================================================================
--- linux-2.6.orig/net/sctp/socket.c
+++ linux-2.6/net/sctp/socket.c
@@ -5436,6 +5436,8 @@ static long sctp_get_port_local(struct s
 			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);

Re: [Patch 3/3] net: reserve ports for applications using fixed port numbers

[Tetsuo Handa]

Hello.

> --- linux-2.6.orig/drivers/infiniband/core/cma.c
> +++ linux-2.6/drivers/infiniband/core/cma.c
> @@ -1980,6 +1980,8 @@ 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 (!ret && inet_is_reserved_local_port(port))
> +			ret = -EAGAIN;
>  	} while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL));
>  
>  	if (ret)
> 
I think above part is wrong. Below program
--------------------
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/idr.h>

static DEFINE_IDR(idr);
static int idr_demo_init(void)
{
	int next_port = 65530;
	int port = 0;
	int ret = -EINTR;
	while (!signal_pending(current)) {
		msleep(1000);
		ret = idr_get_new_above(&idr, NULL, next_port, &port);
		printk(KERN_INFO "idr_get_new_above() = %d\n", ret);
		if (!ret) {
			/* Emulate inet_is_reserved_local_port(port) = true */
			printk(KERN_INFO "Port %u is reserved.\n", port);
			ret = -EAGAIN;
		}
		if (ret == -EAGAIN) {
			if (idr_pre_get(&idr, GFP_KERNEL)) {
				printk(KERN_INFO "idr_pre_get() succeeded.\n");
				continue;
			}
			printk(KERN_INFO "idr_pre_get() failed.\n");
			break;
		} else {
			printk(KERN_INFO "next_port=%u port=%u\n",
			       next_port, port);
			break;
		}
	}
	if (!ret)
		idr_remove(&idr, port);
	idr_destroy(&idr);
	return -EINVAL;
}
module_init(idr_demo_init);
MODULE_LICENSE("GPL");
--------------------
generated below output.

idr_get_new_above() = -11
idr_pre_get() succeeded.
idr_get_new_above() = 0
Port 65530 is reserved.
idr_pre_get() succeeded.
idr_get_new_above() = 0
Port 65531 is reserved.
idr_pre_get() succeeded.
idr_get_new_above() = 0
Port 65532 is reserved.
idr_pre_get() succeeded.
idr_get_new_above() = 0
Port 65533 is reserved.
idr_pre_get() succeeded.
idr_get_new_above() = 0
Port 65534 is reserved.
idr_pre_get() succeeded.
idr_get_new_above() = 0
Port 65535 is reserved.
idr_pre_get() succeeded.
idr_get_new_above() = 0
Port 65536 is reserved.
idr_pre_get() succeeded.
idr_get_new_above() = 0
Port 65537 is reserved.
idr_pre_get() succeeded.
idr_get_new_above() = 0
(...snipped...)

This result suggests that above loop will continue until idr_pre_get() fails
due to out of memory if all ports were reserved.

Also, if idr_get_new_above() returned 0, bind_list (which is a kmalloc()ed
pointer) is already installed into a free slot (see comment on
idr_get_new_above_int()). Thus, simply calling idr_get_new_above() again will
install the same pointer into multiple slots. I guess it will malfunction later.

Re: [Patch 3/3] net: reserve ports for applications using fixed port numbers

[Cong Wang]

Tetsuo Handa wrote:
> Hello.
> 
>> --- linux-2.6.orig/drivers/infiniband/core/cma.c
>> +++ linux-2.6/drivers/infiniband/core/cma.c
>> @@ -1980,6 +1980,8 @@ 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 (!ret && inet_is_reserved_local_port(port))
>> +			ret = -EAGAIN;
>>  	} while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL));
>>  
>>  	if (ret)
>>
> I think above part is wrong. Below program
...
> 
> This result suggests that above loop will continue until idr_pre_get() fails
> due to out of memory if all ports were reserved.
> 
> Also, if idr_get_new_above() returned 0, bind_list (which is a kmalloc()ed
> pointer) is already installed into a free slot (see comment on
> idr_get_new_above_int()). Thus, simply calling idr_get_new_above() again will
> install the same pointer into multiple slots. I guess it will malfunction later.

Thanks for testing!

How about:

+		if (!ret && inet_is_reserved_local_port(port))
+			ret = -EBUSY;

? So that it will break the loop and return error.

Re: [Patch 3/3] net: reserve ports for applications using fixed port numbers

[Cong Wang]

Cong Wang wrote:
> Tetsuo Handa wrote:
>> Hello.
>>
>>> --- linux-2.6.orig/drivers/infiniband/core/cma.c
>>> +++ linux-2.6/drivers/infiniband/core/cma.c
>>> @@ -1980,6 +1980,8 @@ 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 (!ret && inet_is_reserved_local_port(port))
>>> +			ret = -EAGAIN;
>>>  	} while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL));
>>>  
>>>  	if (ret)
>>>
>> I think above part is wrong. Below program
> ...
>> This result suggests that above loop will continue until idr_pre_get() fails
>> due to out of memory if all ports were reserved.
>>
>> Also, if idr_get_new_above() returned 0, bind_list (which is a kmalloc()ed
>> pointer) is already installed into a free slot (see comment on
>> idr_get_new_above_int()). Thus, simply calling idr_get_new_above() again will
>> install the same pointer into multiple slots. I guess it will malfunction later.
> 
> Thanks for testing!
> 
> How about:
> 
> +		if (!ret && inet_is_reserved_local_port(port))
> +			ret = -EBUSY;
> 
> ? So that it will break the loop and return error.
> 

Or use the similar trick:

 int tries = 10;
...

 if(!ret && inet_is_reserved_local_port(port)) {
   if (tries--)
     ret = -EAGAIN;
   else
     ret = -EBUSY;
 }

Any comments?

Re: [Patch 3/3] net: reserve ports for applications using fixed port numbers

[Tetsuo Handa]

Hello.

Adding Sean Hefty and Roland Dreier as drivers/infiniband/core/cma.c maintainer.

Cong Wang wrote:
> Cong Wang wrote:
> > Tetsuo Handa wrote:
> >> Hello.
> >>
> >>> --- linux-2.6.orig/drivers/infiniband/core/cma.c
> >>> +++ linux-2.6/drivers/infiniband/core/cma.c
> >>> @@ -1980,6 +1980,8 @@ 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 (!ret && inet_is_reserved_local_port(port))
> >>> +			ret = -EAGAIN;
> >>>  	} while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL));
> >>>  
> >>>  	if (ret)
> >>>
> >> I think above part is wrong. Below program
> > ...
> >> This result suggests that above loop will continue until idr_pre_get() fails
> >> due to out of memory if all ports were reserved.
> >>
> >> Also, if idr_get_new_above() returned 0, bind_list (which is a kmalloc()ed
> >> pointer) is already installed into a free slot (see comment on
> >> idr_get_new_above_int()). Thus, simply calling idr_get_new_above() again will
> >> install the same pointer into multiple slots. I guess it will malfunction later.
> > 
> > Thanks for testing!
> > 
> > How about:
> > 
> > +		if (!ret && inet_is_reserved_local_port(port))
> > +			ret = -EBUSY;
> > 
> > ? So that it will break the loop and return error.
> > 
> 
> Or use the similar trick:
> 
>  int tries = 10;
> ...
> 
>  if(!ret && inet_is_reserved_local_port(port)) {
>    if (tries--)
>      ret = -EAGAIN;
>    else
>      ret = -EBUSY;
>  }
> 
> Any comments?
> 
I don't like above change. Above change makes local port assignment from
"likely-succeed" (succeeds if one port is available from thousands of ports) to
"unlikely-succeed" (fail if randomly chosen port is already in use).
We should repeat for all ranges specified in /proc/sys/net/ipv4/ip_local_port_range .

cma_alloc_any_port() and cma_alloc_port() are almost identical.
Thus, I think we can call cma_alloc_port() from cma_alloc_any_port().

Sean and Roland, is below patch correct?
inet_is_reserved_local_port() is the new function proposed in this patchset.

---
 drivers/infiniband/core/cma.c |   68 ++++++++++++++----------------------------
 1 file changed, 23 insertions(+), 45 deletions(-)

--- linux-2.6.34-rc4.orig/drivers/infiniband/core/cma.c
+++ linux-2.6.34-rc4/drivers/infiniband/core/cma.c
@@ -79,7 +79,6 @@ static DEFINE_IDR(sdp_ps);
 static DEFINE_IDR(tcp_ps);
 static DEFINE_IDR(udp_ps);
 static DEFINE_IDR(ipoib_ps);
-static int next_port;
 
 struct cma_device {
 	struct list_head	list;
@@ -1970,47 +1969,31 @@ err1:
 
 static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv)
 {
-	struct rdma_bind_list *bind_list;
-	int port, ret, low, high;
-
-	bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL);
-	if (!bind_list)
-		return -ENOMEM;
-
-retry:
-	/* FIXME: add proper port randomization per like inet_csk_get_port */
-	do {
-		ret = idr_get_new_above(ps, bind_list, next_port, &port);
-	} while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL));
-
-	if (ret)
-		goto err1;
+	static unsigned int last_used_port;
+	int low, high, remaining;
+	unsigned int rover;
 
 	inet_get_local_port_range(&low, &high);
-	if (port > high) {
-		if (next_port != low) {
-			idr_remove(ps, port);
-			next_port = low;
-			goto retry;
+	remaining = (high - low) + 1;
+	rover = net_random() % remaining + low;
+	do {
+		rover++;
+		if ((rover < low) || (rover > high))
+			rover = low;
+		if (last_used_port != rover &&
+		    !inet_is_reserved_local_port(rover) &&
+		    !idr_find(ps, (unsigned short) rover) &&
+		    !cma_alloc_port(ps, id_priv, rover)) {
+			/*
+			 * Remember previously used port number in order to
+			 * avoid re-using same port immediately after it is
+			 * closed.
+			 */
+			last_used_port = rover;
+			return 0;
 		}
-		ret = -EADDRNOTAVAIL;
-		goto err2;
-	}
-
-	if (port == high)
-		next_port = low;
-	else
-		next_port = port + 1;
-
-	bind_list->ps = ps;
-	bind_list->port = (unsigned short) port;
-	cma_bind_port(bind_list, id_priv);
-	return 0;
-err2:
-	idr_remove(ps, port);
-err1:
-	kfree(bind_list);
-	return ret;
+	} while (--remaining > 0);
+	return -EADDRNOTAVAIL;
 }
 
 static int cma_use_port(struct idr *ps, struct rdma_id_private *id_priv)
@@ -2995,12 +2978,7 @@ static void cma_remove_one(struct ib_dev
 
 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);
-	remaining = (high - low) + 1;
-	next_port = ((unsigned int) next_port % remaining) + low;
+	int ret;
 
 	cma_wq = create_singlethread_workqueue("rdma_cm");
 	if (!cma_wq)

RE: [Patch 3/3] net: reserve ports for applications using fixed port numbers

[Sean Hefty]

>Sean and Roland, is below patch correct?
>inet_is_reserved_local_port() is the new function proposed in this patchset.

It looks correct to me.  I didn't test the patch series, but if I comment out
the call to inet_is_reserved_local_port() in the provided below, the changes
worked fine for me.

Acked-by: Sean Hefty <sean.hefty@intel.com>

[Patch v7 0/3] net: reserve ports for applications using fixed port numbers

[Amerigo Wang]

Changes from the previous version:
- Update to latest Linus' tree;
- Address Eric B.'s concern, copy the whole bitmap instead of set one by one.

------------->

This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports 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.

There are still some miss behaviors with regard to proc parsing in odd
invalid cases (for "40000\0-40001" all is acknowledged but only 40000
is accepted) but they are not easy to fix without changing the current
"acknowledge how much we accepted" behavior.

Because of that and because the same issues are present in the
existing proc_dointvec code as well I don't think its worth holding
the actual feature (port reservation) after such petty error recovery
issues.

[Patch 3/3] net: reserve ports for applications using fixed port numbers

[Amerigo Wang]

From: Octavian Purdila <opurdila@ixiacom.com>

This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports 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>
Cc: Eric W. Biederman <ebiederm@xmission.com>
---

Index: linux-2.6/Documentation/networking/ip-sysctl.txt
===================================================================
--- linux-2.6.orig/Documentation/networking/ip-sysctl.txt
+++ linux-2.6/Documentation/networking/ip-sysctl.txt
@@ -588,6 +588,37 @@ 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 - list of comma separated ranges
+	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.
+
+	The format used for both input and output is a comma separated
+	list of ranges (e.g. "1,2-4,10-10" for ports 1, 2, 3, 4 and
+	10). Writing to the file will clear all previously reserved
+	ports and update the current list with the one given in the
+	input.
+
+	Note that ip_local_port_range and ip_local_reserved_ports
+	settings are independent and both are considered by the kernel
+	when determining which ports are available for automatic port
+	assignments.
+
+	You can reserve ports which are not in the current
+	ip_local_port_range, e.g.:
+
+	$ cat /proc/sys/net/ipv4/ip_local_port_range
+	32000	61000
+	$ cat /proc/sys/net/ipv4/ip_local_reserved_ports
+	8080,9148
+
+	although this is redundant. However such a setting is useful
+	if later the port range is changed to a value that will
+	include the reserved ports.
+
+	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.
Index: linux-2.6/drivers/infiniband/core/cma.c
===================================================================
--- linux-2.6.orig/drivers/infiniband/core/cma.c
+++ linux-2.6/drivers/infiniband/core/cma.c
@@ -1980,6 +1980,8 @@ 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)
@@ -2996,10 +2998,13 @@ 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)
Index: linux-2.6/include/net/ip.h
===================================================================
--- linux-2.6.orig/include/net/ip.h
+++ linux-2.6/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;
+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;
 
Index: linux-2.6/net/ipv4/af_inet.c
===================================================================
--- linux-2.6.orig/net/ipv4/af_inet.c
+++ linux-2.6/net/ipv4/af_inet.c
@@ -1552,9 +1552,13 @@ static int __init inet_init(void)
 
 	BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb));
 
+	sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
+	if (!sysctl_local_reserved_ports)
+		goto out;
+
 	rc = proto_register(&tcp_prot, 1);
 	if (rc)
-		goto out;
+		goto out_free_reserved_ports;
 
 	rc = proto_register(&udp_prot, 1);
 	if (rc)
@@ -1653,6 +1657,8 @@ out_unregister_udp_proto:
 	proto_unregister(&udp_prot);
 out_unregister_tcp_proto:
 	proto_unregister(&tcp_prot);
+out_free_reserved_ports:
+	kfree(sysctl_local_reserved_ports);
 	goto out;
 }
 
Index: linux-2.6/net/ipv4/inet_connection_sock.c
===================================================================
--- linux-2.6.orig/net/ipv4/inet_connection_sock.c
+++ linux-2.6/net/ipv4/inet_connection_sock.c
@@ -37,6 +37,9 @@ struct local_ports sysctl_local_ports __
 	.range = { 32768, 61000 },
 };
 
+unsigned long *sysctl_local_reserved_ports;
+EXPORT_SYMBOL(sysctl_local_reserved_ports);
+
 void inet_get_local_port_range(int *low, int *high)
 {
 	unsigned seq;
@@ -108,6 +111,8 @@ 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 +135,7 @@ again:
 			break;
 		next:
 			spin_unlock(&head->lock);
+		next_nolock:
 			if (++rover > high)
 				rover = low;
 		} while (--remaining > 0);
Index: linux-2.6/net/ipv4/inet_hashtables.c
===================================================================
--- linux-2.6.orig/net/ipv4/inet_hashtables.c
+++ linux-2.6/net/ipv4/inet_hashtables.c
@@ -456,6 +456,8 @@ int __inet_hash_connect(struct inet_time
 		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);
Index: linux-2.6/net/ipv4/sysctl_net_ipv4.c
===================================================================
--- linux-2.6.orig/net/ipv4/sysctl_net_ipv4.c
+++ linux-2.6/net/ipv4/sysctl_net_ipv4.c
@@ -299,6 +299,13 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= ipv4_local_port_range,
 	},
+	{
+		.procname	= "ip_local_reserved_ports",
+		.data		= NULL, /* initialized in sysctl_ipv4_init */
+		.maxlen		= 65536,
+		.mode		= 0644,
+		.proc_handler	= proc_do_large_bitmap,
+	},
 #ifdef CONFIG_IP_MULTICAST
 	{
 		.procname	= "igmp_max_memberships",
@@ -736,6 +743,16 @@ static __net_initdata struct pernet_oper
 static __init int sysctl_ipv4_init(void)
 {
 	struct ctl_table_header *hdr;
+	struct ctl_table *i;
+
+	for (i = ipv4_table; i->procname; i++) {
+		if (strcmp(i->procname, "ip_local_reserved_ports") == 0) {
+			i->data = sysctl_local_reserved_ports;
+			break;
+		}
+	}
+	if (!i->procname)
+		return -EINVAL;
 
 	hdr = register_sysctl_paths(net_ipv4_ctl_path, ipv4_table);
 	if (hdr == NULL)
Index: linux-2.6/net/ipv4/udp.c
===================================================================
--- linux-2.6.orig/net/ipv4/udp.c
+++ linux-2.6/net/ipv4/udp.c
@@ -233,7 +233,8 @@ int udp_lib_get_port(struct sock *sk, un
 			 */
 			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);
Index: linux-2.6/net/sctp/socket.c
===================================================================
--- linux-2.6.orig/net/sctp/socket.c
+++ linux-2.6/net/sctp/socket.c
@@ -5436,6 +5436,8 @@ static long sctp_get_port_local(struct s
 			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);

Re: [Patch 3/3] net: reserve ports for applications using fixed port numbers

[Tetsuo Handa]

Hello.

Amerigo Wang wrote:
> Index: linux-2.6/drivers/infiniband/core/cma.c
> ===================================================================
> --- linux-2.6.orig/drivers/infiniband/core/cma.c
> +++ linux-2.6/drivers/infiniband/core/cma.c
> @@ -1980,6 +1980,8 @@ 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;

You should not overwrite ret with -EAGAIN when idr_get_new_above() returned
-ENOSPC. I don't know about idr, thus I don't know whether

		if (!ret && inet_is_reserved_local_port(port))
			ret = -EAGAIN;

is correct or not.

>  	} while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL));
>  
>  	if (ret)
> @@ -2996,10 +2998,13 @@ 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;
>  

You should not unconditionally "goto again;".
If all ports were reserved, it will loop forever (CPU stalls).

>  	cma_wq = create_singlethread_workqueue("rdma_cm");
>  	if (!cma_wq)


> Index: linux-2.6/net/sctp/socket.c
> ===================================================================
> --- linux-2.6.orig/net/sctp/socket.c
> +++ linux-2.6/net/sctp/socket.c
> @@ -5436,6 +5436,8 @@ static long sctp_get_port_local(struct s
>  			rover++;
>  			if ((rover < low) || (rover > high))
>  				rover = low;
> +			if (inet_is_reserved_local_port(rover))
> +				continue;

This one needs to be

			if (inet_is_reserved_local_port(rover))
				goto next_nolock;

>  			index = sctp_phashfn(rover);
>  			head = &sctp_port_hashtable[index];
>  			sctp_spin_lock(&head->lock);

 next:
			sctp_spin_unlock(&head->lock);
+next_nolock:
		} while (--remaining > 0);

otherwise, it will loop forever if all ports were reserved.

Re: [Patch 3/3] net: reserve ports for applications using fixed port numbers

[Cong Wang]

Tetsuo Handa wrote:
> Hello.
> 
> Amerigo Wang wrote:
>> Index: linux-2.6/drivers/infiniband/core/cma.c
>> ===================================================================
>> --- linux-2.6.orig/drivers/infiniband/core/cma.c
>> +++ linux-2.6/drivers/infiniband/core/cma.c
>> @@ -1980,6 +1980,8 @@ 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;
> 
> You should not overwrite ret with -EAGAIN when idr_get_new_above() returned
> -ENOSPC. I don't know about idr, thus I don't know whether
> 
> 		if (!ret && inet_is_reserved_local_port(port))
> 			ret = -EAGAIN;
> 
> is correct or not.

Hmm, good catch! I think it is correct.



> 
>>  	} while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL));
>>  
>>  	if (ret)
>> @@ -2996,10 +2998,13 @@ 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;
>>  
> 
> You should not unconditionally "goto again;".
> If all ports were reserved, it will loop forever (CPU stalls).
> 

Yeah, how about:

	int tries = 10;
	...
again:
	...
	if (inet_is_reserved_local_port(next_port)) {
		if (tries--)
			goto again;
		else
			return -EBUSY;
	}

?


>>  	cma_wq = create_singlethread_workqueue("rdma_cm");
>>  	if (!cma_wq)
> 
> 
>> Index: linux-2.6/net/sctp/socket.c
>> ===================================================================
>> --- linux-2.6.orig/net/sctp/socket.c
>> +++ linux-2.6/net/sctp/socket.c
>> @@ -5436,6 +5436,8 @@ static long sctp_get_port_local(struct s
>>  			rover++;
>>  			if ((rover < low) || (rover > high))
>>  				rover = low;
>> +			if (inet_is_reserved_local_port(rover))
>> +				continue;
> 
> This one needs to be
> 
> 			if (inet_is_reserved_local_port(rover))
> 				goto next_nolock;
> 
>>  			index = sctp_phashfn(rover);
>>  			head = &sctp_port_hashtable[index];
>>  			sctp_spin_lock(&head->lock);
> 
>  next:
> 			sctp_spin_unlock(&head->lock);
> +next_nolock:
> 		} while (--remaining > 0);
> 
> otherwise, it will loop forever if all ports were reserved.

Sorry, doesn't 'continue' jump to exactly where 'next_nolock' is??
Or I am missing something?


Thanks for your review!

Re: [Patch 3/3] net: reserve ports for applications using fixed port numbers

[Tetsuo Handa]

Cong Wang wrote:
> Tetsuo Handa wrote:
> >> Index: linux-2.6/net/sctp/socket.c
> >> ===================================================================
> >> --- linux-2.6.orig/net/sctp/socket.c
> >> +++ linux-2.6/net/sctp/socket.c
> >> @@ -5436,6 +5436,8 @@ static long sctp_get_port_local(struct s
> >>  			rover++;
> >>  			if ((rover < low) || (rover > high))
> >>  				rover = low;
> >> +			if (inet_is_reserved_local_port(rover))
> >> +				continue;
> > 
> > This one needs to be
> > 
> > 			if (inet_is_reserved_local_port(rover))
> > 				goto next_nolock;
> > 
> >>  			index = sctp_phashfn(rover);
> >>  			head = &sctp_port_hashtable[index];
> >>  			sctp_spin_lock(&head->lock);
> > 
> >  next:
> > 			sctp_spin_unlock(&head->lock);
> > +next_nolock:
> > 		} while (--remaining > 0);
> > 
> > otherwise, it will loop forever if all ports were reserved.
> 
> Sorry, doesn't 'continue' jump to exactly where 'next_nolock' is??
> Or I am missing something?

My misreading, sorry.