Date: Sat, 25 Mar 2017 23:18:13 -0700 From: Gleb Smirnoff <glebius@FreeBSD.org> To: Konstantin Belousov <kostikbel@gmail.com> Cc: Darren <darren780@yahoo.com>, "freebsd-current@freebsd.org" <freebsd-current@freebsd.org> Subject: Re: r315684 panic: sleepq_add: td 0xfffff80003c01a40 to sleep on wchan 0xfffff80006f0873c with sleeping prohibited Message-ID: <20170326061813.GB23308@FreeBSD.org> In-Reply-To: <20170325094529.GH43712@kib.kiev.ua> References: <1824572972.3096988.1490377215756.ref@mail.yahoo.com> <1824572972.3096988.1490377215756@mail.yahoo.com> <20170325010314.GG43712@kib.kiev.ua> <20170325033142.GA23308@FreeBSD.org> <20170325094529.GH43712@kib.kiev.ua>
index | next in thread | previous in thread | raw e-mail
[-- Attachment #1 --]
On Sat, Mar 25, 2017 at 11:45:29AM +0200, Konstantin Belousov wrote:
K> On Fri, Mar 24, 2017 at 08:31:42PM -0700, Gleb Smirnoff wrote:
K> > Darren,
K> >
K> > On Sat, Mar 25, 2017 at 03:03:14AM +0200, Konstantin Belousov wrote:
K> > K> On Fri, Mar 24, 2017 at 05:40:15PM +0000, Darren wrote:
K> > K> > I am getting this panic every hour to every couple of hours.
K> > K> >
K> > K> > FreeBSD asrock 12.0-CURRENT FreeBSD 12.0-CURRENT #0 r315684: Thu Mar 23 14:56:45 EDT 2017 darren@asrock:/usr/obj/usr/src/sys/GENERIC amd64
K> > K> > I manually typed out the following, apologize for any typos.
K> > K> >
K> > K> >
K> > K> > panic: sleepq_add: td 0xfffff80003c01a40 to sleep on wchan 0xfffff80006f0873c with sleeping prohibited
K> > K> > cpuid = 0
K> > K> > time = 1490372797
K> > K> > KDB: stack backtrace:
K> > K> > db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xfffffe0072e33690
K> > K> > vpanic() at vpanic+0x19c/frame 0xfffffe0072e33710
K> > K> > kassert_panic() at kassert_panic+0x126/frame 0xfffffe0072e33780
K> > K> > sleepq_add() at sleepq_add+0x34f/frame 0xfffffe0072337d0
K> > K> > _sleep() at _sleep+0x28d/frame 0xfffffe0072e33870
K> > K> > soclose() at soclose+0xda/frame 0xfffffe0072e338b0
K> > K> > _fdrop() at _fdrop+0x1a/frame 0xfffffe0072e338d0
K> > K> > sendfile_iodone() at sendfile_iodone+0x19d/frame 0xfffffe0072e33910
K> > K> > vnode_pager_generic_getpages_done_async() at vnode_pager_generic_getpages_done_async+037/frame 0xfffffe0072e33930
K> > K> > bufdone() at bufdone+0x64/frame 0xfffffe0072e33960
K> > K> > g_io_deliver() at g_io_deliver+0x276/frame 0xfffffe0072e339b0
K> > K> > g_io_deliver() at g_io_deliver+0x276/frame 0xfffffe0072e33a00
K> > K> > g_disk_done() at g_disk_done+0x104/frame 0xfffffe0072e33a40
K> > K> > xpt_done_process() at xpt_done_process+0x35f/frame 0xfffffe0072e33a80
K> > K> > xpt_done_direct() at ahci_ch_intr_direct+0xd5/frame 0xfffffe0072e33af0
K> > K> > ahci_itr() at ahci_intr+0x102/frame 0xfffffe0072e33b20
K> > K> > intr_event_execute_handlers() at intr_event_execute_handlers+0x99/frame 0xfffffe0072e33b60
K> > K> > ithread_loop() at ithread_loop+0xb6/frame 0xfffffe0072e33bb0
K> > K> > fork_exit() at fork_exit+0x84/frame 0xfffffe0072e33bf0
K> > K> > fork_trampoline() at fork_trampoline+0xe/frame 0xfffffe0072e33bf0
K> > K> > --- trap 0, rip = 0, rsp = 0, rbp = 0 ---
K> > K> > KDB: enter: panic
K> > K> > [ thread pid 12 tid 100038 ]
K> > K> > Stopped at kdb_enter+0x3b: movq $0,kdb_why
K> > K> > db>
K> > K>
K> > K> Indeed, the context where sendfile_iodone() is executed, cannot call fdrop().
K> >
K> > Can you please test the attached patch?
K> >
K> > --
K> > Totus tuus, Glebius.
K>
K> > Index: sys/kern/kern_sendfile.c
K> > ===================================================================
K> > --- sys/kern/kern_sendfile.c (revision 315926)
K> > +++ sys/kern/kern_sendfile.c (working copy)
K> > @@ -296,8 +296,9 @@ sendfile_iodone(void *arg, vm_page_t *pg, int coun
K> > CURVNET_RESTORE();
K> > }
K> >
K> > - /* XXXGL: curthread */
K> > - fdrop(sfio->sock_fp, curthread);
K> > + ACCEPT_LOCK();
K> > + SOCK_LOCK(so);
K> > + sorele(so);
K> > free(sfio, M_TEMP);
K> > }
K> >
K> > @@ -860,7 +861,9 @@ prepend_header:
K> > } else {
K> > sfio->sock_fp = sock_fp;
K> > sfio->npages = npages;
K> > - fhold(sock_fp);
K> > + SOCK_LOCK(so);
K> > + soref(so);
K> > + SOCK_UNLOCK(so);
K> > error = (*so->so_proto->pr_usrreqs->pru_send)
K> > (so, PRUS_NOTREADY, m, NULL, NULL, td);
K> > sendfile_iodone(sfio, NULL, 0, 0);
K>
K> With this patch, what prevents a close of the sfio->sock_fp file, which is
K> needed to get the pointer to socket ?
You are right, patch is unfinished. Here is better one.
--
Totus tuus, Glebius.
[-- Attachment #2 --]
Index: sys/kern/kern_sendfile.c
===================================================================
--- sys/kern/kern_sendfile.c (revision 315926)
+++ sys/kern/kern_sendfile.c (working copy)
@@ -80,7 +80,7 @@ struct sf_io {
volatile u_int nios;
u_int error;
int npages;
- struct file *sock_fp;
+ struct socket *so;
struct mbuf *m;
vm_page_t pa[];
};
@@ -255,7 +255,7 @@ static void
sendfile_iodone(void *arg, vm_page_t *pg, int count, int error)
{
struct sf_io *sfio = arg;
- struct socket *so;
+ struct socket *so = sfio->so;
for (int i = 0; i < count; i++)
if (pg[i] != bogus_page)
@@ -267,8 +267,6 @@ sendfile_iodone(void *arg, vm_page_t *pg, int coun
if (!refcount_release(&sfio->nios))
return;
- so = sfio->sock_fp->f_data;
-
if (sfio->error) {
struct mbuf *m;
@@ -296,8 +294,9 @@ sendfile_iodone(void *arg, vm_page_t *pg, int coun
CURVNET_RESTORE();
}
- /* XXXGL: curthread */
- fdrop(sfio->sock_fp, curthread);
+ ACCEPT_LOCK();
+ SOCK_LOCK(so);
+ sorele(so);
free(sfio, M_TEMP);
}
@@ -858,9 +857,11 @@ prepend_header:
error = (*so->so_proto->pr_usrreqs->pru_send)
(so, 0, m, NULL, NULL, td);
} else {
- sfio->sock_fp = sock_fp;
+ sfio->so = so;
sfio->npages = npages;
- fhold(sock_fp);
+ SOCK_LOCK(so);
+ soref(so);
+ SOCK_UNLOCK(so);
error = (*so->so_proto->pr_usrreqs->pru_send)
(so, PRUS_NOTREADY, m, NULL, NULL, td);
sendfile_iodone(sfio, NULL, 0, 0);
help
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20170326061813.GB23308>