src/sys/netgraph/ng_socket.c, branch releng/10.2

MFC r263710, r273377, r273378, r273423 and r273455:

2014-10-27T14:38:00Z

- De-vnet hash sizes and hash masks. - Fix multiple issues related to arguments passed to SYSCTL macros. Sponsored by: Mellanox Technologies

In ng_getsockaddr() allocate memory prior to obtaining lock.

2012-02-16T14:44:52Z

Reported & tested by: Mykola Dzham

No need to optimise for a node with no hooks, my braino.

2012-02-13T13:07:56Z

Provide a findhook method for ng_socket(4). The node stores a

2012-01-23T16:43:13Z
hash with names of its hooks. It starts with size of 16, and grows when number of hooks reaches twice the current size. A failure to grow (memory is allocated with M_NOWAIT) isn't fatal, however. I used standard hash(9) function for the hash. With 25000 hooks named in the mpd (ports/net/mpd5) manner of "b%u", the distributions is the following: 72.1% entries consist of one element, 22.1% consist of two, 5.2% consist of three and 0.6% of four. Speedup in a synthetic test that creates 25000 hooks and then runs through a long cyclce dereferencing them in a random order is over 25 times.

In ng_socket(4) expose less kernel internals to userland. This commit

2012-01-23T15:39:45Z
breaks ABI, but makes probability of ABI breakage in future less.

Remove some disabled NOTYET code. Probability of enabling it is low,

2012-01-16T12:31:33Z
if anyone wants, he/she can take it from svn.

Mark all SYSCTL_NODEs static that have no corresponding SYSCTL_DECLs.

2011-11-07T15:43:11Z
The SYSCTL_NODE macro defines a list that stores all child-elements of that node. If there's no SYSCTL_DECL macro anywhere else, there's no reason why it shouldn't be static.

Mark MALLOC_DEFINEs static that have no corresponding MALLOC_DECLAREs.

2011-11-07T06:44:47Z
This means that their use is restricted to a single C file.

Second-to-last commit implementing Capsicum capabilities in the FreeBSD

2011-08-11T12:30:23Z
kernel for FreeBSD 9.0: Add a new capability mask argument to fget(9) and friends, allowing system call code to declare what capabilities are required when an integer file descriptor is converted into an in-kernel struct file *. With options CAPABILITIES compiled into the kernel, this enforces capability protection; without, this change is effectively a no-op. Some cases require special handling, such as mmap(2), which must preserve information about the maximum rights at the time of mapping in the memory map so that they can later be enforced in mprotect(2) -- this is done by narrowing the rights in the existing max_protection field used for similar purposes with file permissions. In namei(9), we assert that the code is not reached from within capability mode, as we're not yet ready to enforce namespace capabilities there. This will follow in a later commit. Update two capability names: CAP_EVENT and CAP_KEVENT become CAP_POST_KEVENT and CAP_POLL_KEVENT to more accurately indicate what they represent. Approved by: re (bz) Submitted by: jonathan Sponsored by: Google Inc

In ng_attach_cntl() first allocate things that may fail, and then

2011-07-14T18:38:10Z
do the rest of initialization. This simplifies code and fixes a double free in failure scenario. Reviewed by: bz