| To: | Ronghua Zhang <rz5b@xxxxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: synchronization between bottom half and user context |
| From: | jamal <hadi@xxxxxxxxxx> |
| Date: | Wed, 4 Dec 2002 07:51:34 -0500 (EST) |
| Cc: | <netdev@xxxxxxxxxxx> |
| In-reply-to: | <Pine.LNX.4.44.0212030038030.1334-100000@xxxxxxxxxxxxxxxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Tue, 3 Dec 2002, Ronghua Zhang wrote: > Can someone tell me when lock should be used to synchronize bh and user > context? > > For examle: in tcp_accept(), lock_sock() is called to avoid any change > made by net_bh during its operation. But if tcp_accept() is called, it's > impossilbe that net_bh is also executing. (i think this is true for UP, > what about SMP?), then why need lock_sock()? > to serialize packets towards the socket; The linux network stack is threaded, you can have upto n packets to the same socket coming up the stack in parallel on an n-SMP machine; think of that and the fact that TCP data must be sequenced. cheers, jamal |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: [patch] Change Networking mibs to use kmalloc_percpu -- 3/3, Ravikiran G Thirumalai |
|---|---|
| Next by Date: | Re: Patch resubmission: RFC2863 operstatus for 2.5.49, jamal |
| Previous by Thread: | synchronization between bottom half and user context, Ronghua Zhang |
| Next by Thread: | Re: synchronization between bottom half and user context, Ronghua Zhang |
| Indexes: | [Date] [Thread] [Top] [All Lists] |