[PATCH v2] Fix for Bug #221 -- Issue concerning bigger routing tables

[PATCH v2] Fix for Bug #221 -- Issue concerning bigger routing tables

[Martin Schitter]

v2 includes some additional small changes/fixes.

[PATCH v2 1/3] Fix handling of netlink multipart route dumps.
[PATCH v2 2/3] Timekeeping: Resolving Route Dependencies
[PATCH v2 3/3] Optimize route dependency solver.

[PATCH v2 1/3] Fix handling of netlink multipart route dumps.

[Martin Schitter]

This patch adds a `nl_collect` function to store all datagram
chunks of a multipart route dump in one single interim buffer
for further processing and dependency resolution.
---
 netlink.c | 79 +++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 56 insertions(+), 23 deletions(-)

diff --git a/netlink.c b/netlink.c
index 225b666..650a6fd 100644
--- a/netlink.c
+++ b/netlink.c
@@ -229,6 +229,51 @@ static struct nlmsghdr *nl_next(int s, char *buf, struct nlmsghdr *nh, ssize_t *
 		/* NOLINTNEXTLINE(readability-inconsistent-ifelse-braces) */\
 		} else
 
+/**
+ * nl_collect() - Collect all respose Datagrams of a netlink multi part dump
+ * @s:      Netlink socket
+ * @buf:    Buffer for responses (at least NLBUFSIZ long)
+ * @buflen: Buffer size.
+ * @seq:    Sequence number of request we're getting responses for
+ *
+ * Return: Length of collected responses in bytes or error code < 0
+ */
+int nl_collect(int s, char *buf, size_t buflen, uint32_t seq)
+{
+    size_t collected = 0;
+    struct nlmsghdr *nh;
+    ssize_t n;
+    int res;
+    const struct nlmsghdr* tail;
+
+    #define NLMSG_DONE_SIZE NLMSG_LENGTH(4)
+
+    while(collected + NLBUFSIZ < buflen){
+        nh = nl_next(s, &buf[collected], NULL, &n);
+        debug("collect: add chunk of size n=%ld at offset=%ld, seq=%d nlmsg_len=%d",
+            n, collected, seq, ((const struct nlmsghdr *)&buf[collected])->nlmsg_len);
+        res = nl_status(nh, n, seq);
+        if (res < 0) /* error */
+            return res;
+        collected += n;
+
+        /* look for NLMSG_DONE -- it's ussualy transmitted in a seperate datagram,
+         * but in some rare cases also placed at the end of a multipart chunk.*/
+        tail = (const struct nlmsghdr*)&buf[collected - NLMSG_DONE_SIZE];
+        if (res == 0 || (
+            collected >= NLMSG_DONE_SIZE
+            && (tail = (const struct nlmsghdr*)&buf[collected - NLMSG_DONE_SIZE])
+            && NLMSG_OK(tail, NLMSG_DONE_SIZE)
+            && (nl_status(tail, NLMSG_DONE_SIZE, seq) == 0))
+        ) {
+            debug("collected: %ld", collected);
+            return collected;
+        }
+    }
+    err("netlink: Too many routes to duplicate");
+    return -E2BIG;
+}
+
 /**
  * nl_do() - Send netlink "do" request, and wait for acknowledgement
  * @s:		Netlink socket
@@ -553,21 +598,21 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
 		.rta.rta_len	  = RTA_LENGTH(sizeof(unsigned int)),
 		.ifi		  = ifi_src,
 	};
-	ssize_t nlmsgs_size, left, status;
+	ssize_t nlmsgs_size, left, status = 0;
 	unsigned dup_routes = 0;
 	struct nlmsghdr *nh;
-	char buf[NLBUFSIZ];
+	char buf[NLBUFSIZ * 8];
 	uint32_t seq;
 	unsigned i;
 
 	seq = nl_send(s_src, &req, RTM_GETROUTE, NLM_F_DUMP, sizeof(req));
 
-	/* nl_foreach() will step through multiple response datagrams,
-	 * which we don't want here because we need to have all the
-	 * routes in the buffer at once.
-	 */
-	nh = nl_next(s_src, buf, NULL, &nlmsgs_size);
-	for (left = nlmsgs_size;
+	/* collect all the chunks of a multi part dump in one buffer.*/
+	nlmsgs_size = nl_collect(s_src, buf, sizeof(buf), seq);
+	if (nlmsgs_size < 0)
+	    return nlmsgs_size;
+
+	for (nh = (struct nlmsghdr *)buf, left = nlmsgs_size;
 	     NLMSG_OK(nh, left) && (status = nl_status(nh, left, seq)) > 0;
 	     nh = NLMSG_NEXT(nh, left)) {
 		struct rtmsg *rtm = (struct rtmsg *)NLMSG_DATA(nh);
@@ -648,24 +693,12 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
 			dup_routes++;
 	}
 
-	if (!NLMSG_OK(nh, left)) {
-		/* Process any remaining datagrams in a different
-		 * buffer so we don't overwrite the first one.
-		 */
-		char tail[NLBUFSIZ];
-		unsigned extra = 0;
-
-		nl_foreach_oftype(nh, status, s_src, tail, seq, RTM_NEWROUTE)
-			extra++;
-
-		if (extra) {
-			err("netlink: Too many routes to duplicate");
-			return -E2BIG;
-		}
-	}
+	/* status should be 0 (=NLMSG_DONE) */
 	if (status < 0)
 		return status;
 
+	debug("found %d routes in dump", dup_routes);
+
 	/* Routes might have dependencies between each other, and the kernel
 	 * processes RTM_NEWROUTE messages sequentially. For n routes, we might
 	 * need to send the requests up to n times to get all of them inserted.
-- 
2.53.0

[PATCH v2 2/3] Timekeeping: Resolving Route Dependencies

[Martin Schitter]

---
 netlink.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/netlink.c b/netlink.c
index 650a6fd..65cc5d7 100644
--- a/netlink.c
+++ b/netlink.c
@@ -18,6 +18,7 @@
 #include <errno.h>
 #include <sys/types.h>
 #include <limits.h>
+#include <time.h>
 #include <unistd.h>
 #include <signal.h>
 #include <stdlib.h>
@@ -604,6 +605,7 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
 	char buf[NLBUFSIZ * 8];
 	uint32_t seq;
 	unsigned i;
+	struct timespec start, now;
 
 	seq = nl_send(s_src, &req, RTM_GETROUTE, NLM_F_DUMP, sizeof(req));
 
@@ -706,6 +708,7 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
 	 * can safely ignore that and repeat the requests. This avoids the need
 	 * to calculate dependencies: let the kernel do that.
 	 */
+	clock_gettime(CLOCK_MONOTONIC, &start);
 	for (i = 0; i < dup_routes; i++) {
 		for (nh = (struct nlmsghdr *)buf, left = nlmsgs_size;
 		     NLMSG_OK(nh, left);
@@ -724,6 +727,9 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
 				return rc;
 		}
 	}
+	clock_gettime(CLOCK_MONOTONIC, &now);
+	debug("route dependency handling time: %f s",
+	    (now.tv_sec - start.tv_sec) + (now.tv_nsec - start.tv_nsec)/1.0e9);
 
 	return 0;
 }
-- 
2.53.0

[PATCH v2 3/3] Optimize route dependency solver.

[Martin Schitter]

Avoid retransmitting routes that explicitly got reported as already
existing.

Never make more resolution attempts than there are still unresolved
dependency errors.

In the context of my current mesh network with ~700 route entries
these changes reduce the required processing time from 5.5s to 15ms.
---
 netlink.c | 26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

diff --git a/netlink.c b/netlink.c
index 65cc5d7..0e1c82a 100644
--- a/netlink.c
+++ b/netlink.c
@@ -703,13 +703,12 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
 
 	/* Routes might have dependencies between each other, and the kernel
 	 * processes RTM_NEWROUTE messages sequentially. For n routes, we might
-	 * need to send the requests up to n times to get all of them inserted.
-	 * Routes that have been already inserted will return -EEXIST, but we
-	 * can safely ignore that and repeat the requests. This avoids the need
-	 * to calculate dependencies: let the kernel do that.
+	 * need to send the requests up to n times in the worst case to get all
+	 * of them inserted.
 	 */
 	clock_gettime(CLOCK_MONOTONIC, &start);
-	for (i = 0; i < dup_routes; i++) {
+	for (i = dup_routes; i > 0; i--) {
+	    unsigned int dep_errors = 0;
 		for (nh = (struct nlmsghdr *)buf, left = nlmsgs_size;
 		     NLMSG_OK(nh, left);
 		     nh = NLMSG_NEXT(nh, left)) {
@@ -722,10 +721,23 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
 			rc = nl_do(s_dst, nh, RTM_NEWROUTE,
 				   (flags & ~NLM_F_DUMP_FILTERED) | NLM_F_CREATE,
 				   nh->nlmsg_len);
-			if (rc < 0 && rc != -EEXIST &&
-			    rc != -ENETUNREACH && rc != -EHOSTUNREACH)
+
+			if ( rc == -EEXIST) {
+			    /* Exclude existing routes from further retry attempts */
+			    nh->nlmsg_type = NLMSG_NOOP;
+			    continue;
+			}
+			if ( rc == -ENETUNREACH || rc == -EHOSTUNREACH){
+			    dep_errors++;
+			    continue;
+			}
+			if (rc < 0)
 				return rc;
 		}
+		debug("route dependency errors: %d", dep_errors);
+		/* Avoid having much more resolution attempts than
+		 * there are still unresolved dependency errors */
+		i = MIN(i, dep_errors++);
 	}
 	clock_gettime(CLOCK_MONOTONIC, &now);
 	debug("route dependency handling time: %f s",
-- 
2.53.0

Re: [PATCH v2 1/3] Fix handling of netlink multipart route dumps.

[Stefano Brivio]

Here's my review, sorry for the delay.

I have mostly coding style remarks on this patch, and more substantial
comments in the following patches.

Conceptually, though, this patch entirely makes sense to me.

On Tue,  8 Sep 2026 18:13:12 +0000
Martin Schitter <ms+git@mur.at> wrote:

> This patch adds a `nl_collect` function to store all datagram
> chunks of a multipart route dump in one single interim buffer
> for further processing and dependency resolution.

Here, and in following patches: missing Signed-off-by: tag (see
CONTRIBUTING.md).

> ---
>  netlink.c | 79 +++++++++++++++++++++++++++++++++++++++----------------
>  1 file changed, 56 insertions(+), 23 deletions(-)
> 
> diff --git a/netlink.c b/netlink.c
> index 225b666..650a6fd 100644
> --- a/netlink.c
> +++ b/netlink.c
> @@ -229,6 +229,51 @@ static struct nlmsghdr *nl_next(int s, char *buf, struct nlmsghdr *nh, ssize_t *
>  		/* NOLINTNEXTLINE(readability-inconsistent-ifelse-braces) */\
>  		} else
>  
> +/**
> + * nl_collect() - Collect all respose Datagrams of a netlink multi part dump

Nits: 'response', 'datagrams'.

> + * @s:      Netlink socket
> + * @buf:    Buffer for responses (at least NLBUFSIZ long)
> + * @buflen: Buffer size.

"Buffer size"

> + * @seq:    Sequence number of request we're getting responses for
> + *
> + * Return: Length of collected responses in bytes or error code < 0

Exceedingly minor, but for consistency (I strongly believe in boring
code and comments): "length", ", negative error code" (see e.g.
nl_do()).

> + */
> +int nl_collect(int s, char *buf, size_t buflen, uint32_t seq)

Cppcheck (try 'make cppcheck') says:

netlink.c:242:5: style: The function 'nl_collect' should have static linkage since it is not used outside of its translation unit. [staticFunction]
int nl_collect(int s, char *buf, size_t buflen, uint32_t seq)
    ^

> +{
> +    size_t collected = 0;

Coding style: we use tabs, see CONTRIBUTING.md. It's essentially the
same coding style as the Linux kernel with the "netdev" variants.

> +    struct nlmsghdr *nh;

Cppcheck reports that:

netlink.c:245:22: style: The scope of the variable 'nh' can be reduced. [variableScope]
    struct nlmsghdr *nh;
                     ^

and also:

netlink.c:245:22: style: Variable 'nh' can be declared as pointer to const [constVariablePointer]
    struct nlmsghdr *nh;
                     ^

> +    ssize_t n;
> +    int res;
> +    const struct nlmsghdr* tail;

...and we also align variable declarations from the longest to the
shortest (see references in CONTRIBUTING.md).

Coding style: "struct nlmsghdr *tail".

Same here for these two:

netlink.c:247:9: style: The scope of the variable 'res' can be reduced. [variableScope]
    int res;
        ^
netlink.c:248:28: style: The scope of the variable 'tail' can be reduced. [variableScope]
    const struct nlmsghdr* tail;
                           ^

> +
> +    #define NLMSG_DONE_SIZE NLMSG_LENGTH(4)

It's just a header with no data, right? Shouldn't it be 0? Am I missing
something?

By the way we tend to group all the defines that are generally valid
for a compilation unit towards the beginning of the relevant file (so
that they can be used in all the functions), see #define directives
earlier in netlink.c.

Exceptions are macros that are only relevant or valid for a given
function (see e.g. tap6_handler() in tap.c).

> +
> +    while(collected + NLBUFSIZ < buflen){

Coding style: space before {.

It's not really idiomatic to "do something as long as we have space"
and, with this structure, we won't stop on errors or mismatching
sequence numbers (see nl_status()).

Would there be a way to encode this as a loop on nl_status() perhaps? I
haven't tried but it would look cleaner and less bug-prone.

> +        nh = nl_next(s, &buf[collected], NULL, &n);
> +        debug("collect: add chunk of size n=%ld at offset=%ld, seq=%d nlmsg_len=%d",
> +            n, collected, seq, ((const struct nlmsghdr *)&buf[collected])->nlmsg_len);

At some point, we should get a netlink monitor (see
https://bugs.passt.top/show_bug.cgi?id=141) which might run this function
quite frequently at runtime, and having this as debug() message would
risk flooding debug logs and making them otherwise unusable.

We have rate-limited versions of logging functions, but they wouldn't
help debugging this function specifically, because once rate-limiting
kicks in, the messages might become entirely useless.

I think we could consider trace(). My preference would actually to drop
this altogether because it seems to be specific to some particular
phase of your development and not something of general relevance.

If we want to keep this for some reason: "collect" isn't very
descriptive (mind that it will just be printed among other messages
coming from completely different parts of the code). I would rather use
__func__.

> +        res = nl_status(nh, n, seq);
> +        if (res < 0) /* error */
> +            return res;

Looping on nl_status() directly would get rid of this.

> +        collected += n;
> +
> +        /* look for NLMSG_DONE -- it's ussualy transmitted in a seperate datagram,

usually, separate

> +         * but in some rare cases also placed at the end of a multipart chunk.*/

	* [...] chunk.
	*/

> +        tail = (const struct nlmsghdr*)&buf[collected - NLMSG_DONE_SIZE];

Cppcheck and clang-tidy (try also 'make clang-tidy') aren't
particularly impressed here. Cppcheck says:

netlink.c:266:22: style: Variable 'tail' is reassigned a value before the old one has been used. [redundantAssignment]
            && (tail = (const struct nlmsghdr*)&buf[collected - NLMSG_DONE_SIZE])
                     ^
netlink.c:263:14: note: tail is assigned
        tail = (const struct nlmsghdr*)&buf[collected - NLMSG_DONE_SIZE];
             ^
netlink.c:266:22: note: tail is overwritten
            && (tail = (const struct nlmsghdr*)&buf[collected - NLMSG_DONE_SIZE])
                     ^

and clang-tidy, more clearly, states:

/home/sbrivio/passt/netlink.c:263:9: error: Value stored to 'tail' is never read [clang-analyzer-deadcode.DeadStores,-warnings-as-errors]
  263 |         tail = (const struct nlmsghdr*)&buf[collected - NLMSG_DONE_SIZE];
      |         ^      ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/sbrivio/passt/netlink.c:263:9: note: Value stored to 'tail' is never read
  263 |         tail = (const struct nlmsghdr*)&buf[collected - NLMSG_DONE_SIZE];
      |         ^      ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

> +        if (res == 0 || (
> +            collected >= NLMSG_DONE_SIZE
> +            && (tail = (const struct nlmsghdr*)&buf[collected - NLMSG_DONE_SIZE])
> +            && NLMSG_OK(tail, NLMSG_DONE_SIZE)
> +            && (nl_status(tail, NLMSG_DONE_SIZE, seq) == 0))

For readability: could we perhaps split this into different 'if'
conditions with gotos dealing with specific errors (for example if
!NLMSG_OK(tail, NLMSG_DONE_SIZE), we should report error and return
early I guess)?

> +        ) {
> +            debug("collected: %ld", collected);

Same comments as the debug() call above.

> +            return collected;
> +        }
> +    }
> +    err("netlink: Too many routes to duplicate");
> +    return -E2BIG;
> +}
> +
>  /**
>   * nl_do() - Send netlink "do" request, and wait for acknowledgement
>   * @s:		Netlink socket
> @@ -553,21 +598,21 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
>  		.rta.rta_len	  = RTA_LENGTH(sizeof(unsigned int)),
>  		.ifi		  = ifi_src,
>  	};
> -	ssize_t nlmsgs_size, left, status;
> +	ssize_t nlmsgs_size, left, status = 0;
>  	unsigned dup_routes = 0;
>  	struct nlmsghdr *nh;
> -	char buf[NLBUFSIZ];
> +	char buf[NLBUFSIZ * 8];

Reasonable, but perhaps it should be a #define just after #define
NLBUFSIZ.

If a change in a variable declaration changes its length (as
displayed), you should move it so that we keep the "reverse pyramid"
look.

>  	uint32_t seq;
>  	unsigned i;
>  
>  	seq = nl_send(s_src, &req, RTM_GETROUTE, NLM_F_DUMP, sizeof(req));
>  
> -	/* nl_foreach() will step through multiple response datagrams,
> -	 * which we don't want here because we need to have all the
> -	 * routes in the buffer at once.
> -	 */
> -	nh = nl_next(s_src, buf, NULL, &nlmsgs_size);
> -	for (left = nlmsgs_size;
> +	/* collect all the chunks of a multi part dump in one buffer.*/

/* Collect [...] buffer */

> +	nlmsgs_size = nl_collect(s_src, buf, sizeof(buf), seq);
> +	if (nlmsgs_size < 0)
> +	    return nlmsgs_size;
> +
> +	for (nh = (struct nlmsghdr *)buf, left = nlmsgs_size;
>  	     NLMSG_OK(nh, left) && (status = nl_status(nh, left, seq)) > 0;
>  	     nh = NLMSG_NEXT(nh, left)) {
>  		struct rtmsg *rtm = (struct rtmsg *)NLMSG_DATA(nh);
> @@ -648,24 +693,12 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
>  			dup_routes++;
>  	}
>  
> -	if (!NLMSG_OK(nh, left)) {
> -		/* Process any remaining datagrams in a different
> -		 * buffer so we don't overwrite the first one.
> -		 */
> -		char tail[NLBUFSIZ];
> -		unsigned extra = 0;
> -
> -		nl_foreach_oftype(nh, status, s_src, tail, seq, RTM_NEWROUTE)
> -			extra++;
> -
> -		if (extra) {
> -			err("netlink: Too many routes to duplicate");
> -			return -E2BIG;
> -		}
> -	}
> +	/* status should be 0 (=NLMSG_DONE) */

This comment is redundant: if status is not 0, then clearly we hit some
kind of issue.

>  	if (status < 0)
>  		return status;
>  
> +	debug("found %d routes in dump", dup_routes);

Same comments as debug() calls above.

> +
>  	/* Routes might have dependencies between each other, and the kernel
>  	 * processes RTM_NEWROUTE messages sequentially. For n routes, we might
>  	 * need to send the requests up to n times to get all of them inserted.

-- 
Stefano

Re: [PATCH v2 2/3] Timekeeping: Resolving Route Dependencies

[Stefano Brivio]

On Tue,  8 Sep 2026 18:13:13 +0000
Martin Schitter <ms+git@mur.at> wrote:

> ---
>  netlink.c | 6 ++++++
>  1 file changed, 6 insertions(+)
> 
> diff --git a/netlink.c b/netlink.c
> index 650a6fd..65cc5d7 100644
> --- a/netlink.c
> +++ b/netlink.c
> @@ -18,6 +18,7 @@
>  #include <errno.h>
>  #include <sys/types.h>
>  #include <limits.h>
> +#include <time.h>
>  #include <unistd.h>
>  #include <signal.h>
>  #include <stdlib.h>
> @@ -604,6 +605,7 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
>  	char buf[NLBUFSIZ * 8];
>  	uint32_t seq;
>  	unsigned i;
> +	struct timespec start, now;
>  
>  	seq = nl_send(s_src, &req, RTM_GETROUTE, NLM_F_DUMP, sizeof(req));
>  
> @@ -706,6 +708,7 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
>  	 * can safely ignore that and repeat the requests. This avoids the need
>  	 * to calculate dependencies: let the kernel do that.
>  	 */
> +	clock_gettime(CLOCK_MONOTONIC, &start);

This adds overhead (even if minimal) in a general case, but it's only
used for debug() messages.

>  	for (i = 0; i < dup_routes; i++) {
>  		for (nh = (struct nlmsghdr *)buf, left = nlmsgs_size;
>  		     NLMSG_OK(nh, left);
> @@ -724,6 +727,9 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
>  				return rc;
>  		}
>  	}
> +	clock_gettime(CLOCK_MONOTONIC, &now);
> +	debug("route dependency handling time: %f s",
> +	    (now.tv_sec - start.tv_sec) + (now.tv_nsec - start.tv_nsec)/1.0e9);

And anyway, I'm not sure I see the value of this. Which other functions
should we profile? Does it help at all to do this once you're done
developing it?

I would suggest to simply drop this patch. I understand you needed that
for development but you already explain in the commit message for 3/3
how it improves thing, and that's all the documentation we possibly
need for the future, I think.

>  
>  	return 0;
>  }

-- 
Stefano

Re: [PATCH v2 3/3] Optimize route dependency solver.

[Stefano Brivio]

On Tue,  8 Sep 2026 18:13:14 +0000
Martin Schitter <ms+git@mur.at> wrote:

> Avoid retransmitting routes that explicitly got reported as already
> existing.

Oops. I feel a bit dumb now.

> Never make more resolution attempts than there are still unresolved
> dependency errors.
> 
> In the context of my current mesh network with ~700 route entries
> these changes reduce the required processing time from 5.5s to 15ms.

Ouch. Nice.

> ---
>  netlink.c | 26 +++++++++++++++++++-------
>  1 file changed, 19 insertions(+), 7 deletions(-)
> 
> diff --git a/netlink.c b/netlink.c
> index 65cc5d7..0e1c82a 100644
> --- a/netlink.c
> +++ b/netlink.c
> @@ -703,13 +703,12 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
>  
>  	/* Routes might have dependencies between each other, and the kernel
>  	 * processes RTM_NEWROUTE messages sequentially. For n routes, we might
> -	 * need to send the requests up to n times to get all of them inserted.
> -	 * Routes that have been already inserted will return -EEXIST, but we
> -	 * can safely ignore that and repeat the requests. This avoids the need
> -	 * to calculate dependencies: let the kernel do that.
> +	 * need to send the requests up to n times in the worst case to get all
> +	 * of them inserted.
>  	 */
>  	clock_gettime(CLOCK_MONOTONIC, &start);
> -	for (i = 0; i < dup_routes; i++) {
> +	for (i = dup_routes; i > 0; i--) {
> +	    unsigned int dep_errors = 0;
>  		for (nh = (struct nlmsghdr *)buf, left = nlmsgs_size;
>  		     NLMSG_OK(nh, left);
>  		     nh = NLMSG_NEXT(nh, left)) {
> @@ -722,10 +721,23 @@ int nl_route_dup(int s_src, unsigned int ifi_src,
>  			rc = nl_do(s_dst, nh, RTM_NEWROUTE,
>  				   (flags & ~NLM_F_DUMP_FILTERED) | NLM_F_CREATE,
>  				   nh->nlmsg_len);
> -			if (rc < 0 && rc != -EEXIST &&
> -			    rc != -ENETUNREACH && rc != -EHOSTUNREACH)
> +
> +			if ( rc == -EEXIST) {

Coding style: if (rc == -EEXIST) {

> +			    /* Exclude existing routes from further retry attempts */
> +			    nh->nlmsg_type = NLMSG_NOOP;
> +			    continue;
> +			}
> +			if ( rc == -ENETUNREACH || rc == -EHOSTUNREACH){

Coding style:

			if (rc == -ENETUNREACH || rc == -EHOSTUNREACH) {

> +			    dep_errors++;
> +			    continue;
> +			}
> +			if (rc < 0)
>  				return rc;
>  		}
> +		debug("route dependency errors: %d", dep_errors);

See my comments to debug() calls in 1/3.

> +		/* Avoid having much more resolution attempts than
> +		 * there are still unresolved dependency errors */
> +		i = MIN(i, dep_errors++);

It took me a while to understand how you do this, and I'm mostly
convinced it's correct, but I'm also convinced this is equivalent to a
much simpler implementation: stop when we get no errors at all for the
whole bunch.

That is, using dep_errors:

	for (i = 0; i < dup_routes; i++) {

		[...]

		if (!dep_errors) /* All inserted, done */
			break;
	}

...right?

>  	}
>  	clock_gettime(CLOCK_MONOTONIC, &now);
>  	debug("route dependency handling time: %f s",

-- 
Stefano