summaryrefslogtreecommitdiffstats
path: root/kernel/fork.c
diff options
context:
space:
mode:
authorEric W. Biederman <ebiederm@xmission.com>2006-03-31 02:31:42 -0800
committerLinus Torvalds <torvalds@g5.osdl.org>2006-03-31 12:19:00 -0800
commit92476d7fc0326a409ab1d3864a04093a6be9aca7 (patch)
treeea50a5a31522492d9915e0763a7adc6ac87c4fbc /kernel/fork.c
parent8c7904a00b06d2ee51149794b619e07369fcf9d4 (diff)
[PATCH] pidhash: Refactor the pid hash table
Simplifies the code, reduces the need for 4 pid hash tables, and makes the code more capable. In the discussions I had with Oleg it was felt that to a large extent the cleanup itself justified the work. With struct pid being dynamically allocated meant we could create the hash table entry when the pid was allocated and free the hash table entry when the pid was freed. Instead of playing with the hash lists when ever a process would attach or detach to a process. For myself the fact that it gave what my previous task_ref patch gave for free with simpler code was a big win. The problem is that if you hold a reference to struct task_struct you lock in 10K of low memory. If you do that in a user controllable way like /proc does, with an unprivileged but hostile user space application with typical resource limits of 1000 fds and 100 processes I can trigger the OOM killer by consuming all of low memory with task structs, on a machine wight 1GB of low memory. If I instead hold a reference to struct pid which holds a pointer to my task_struct, I don't suffer from that problem because struct pid is 2 orders of magnitude smaller. In fact struct pid is small enough that most other kernel data structures dwarf it, so simply limiting the number of referring data structures is enough to prevent exhaustion of low memory. This splits the current struct pid into two structures, struct pid and struct pid_link, and reduces our number of hash tables from PIDTYPE_MAX to just one. struct pid_link is the per process linkage into the hash tables and lives in struct task_struct. struct pid is given an indepedent lifetime, and holds pointers to each of the pid types. The independent life of struct pid simplifies attach_pid, and detach_pid, because we are always manipulating the list of pids and not the hash table. In addition in giving struct pid an indpendent life it makes the concept much more powerful. Kernel data structures can now embed a struct pid * instead of a pid_t and not suffer from pid wrap around problems or from keeping unnecessarily large amounts of memory allocated. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'kernel/fork.c')
-rw-r--r--kernel/fork.c16
1 files changed, 9 insertions, 7 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index b1341205be2..03975d0467f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1315,17 +1315,19 @@ long do_fork(unsigned long clone_flags,
{
struct task_struct *p;
int trace = 0;
- long pid = alloc_pidmap();
+ struct pid *pid = alloc_pid();
+ long nr;
- if (pid < 0)
+ if (!pid)
return -EAGAIN;
+ nr = pid->nr;
if (unlikely(current->ptrace)) {
trace = fork_traceflag (clone_flags);
if (trace)
clone_flags |= CLONE_PTRACE;
}
- p = copy_process(clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr, pid);
+ p = copy_process(clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr, nr);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
@@ -1352,7 +1354,7 @@ long do_fork(unsigned long clone_flags,
p->state = TASK_STOPPED;
if (unlikely (trace)) {
- current->ptrace_message = pid;
+ current->ptrace_message = nr;
ptrace_notify ((trace << 8) | SIGTRAP);
}
@@ -1362,10 +1364,10 @@ long do_fork(unsigned long clone_flags,
ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
}
} else {
- free_pidmap(pid);
- pid = PTR_ERR(p);
+ free_pid(pid);
+ nr = PTR_ERR(p);
}
- return pid;
+ return nr;
}
#ifndef ARCH_MIN_MMSTRUCT_ALIGN