d/freebsd-nq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Follow up r313841 on powerpc

Browse Source 
Close a potential race in reading the CPU dtrace flags, where a thread can
start on one CPU, and partway through retrieving the flags be swapped out,
while another thread traps and sets the CPU_DTRACE_NOFAULT.  This could
cause the first thread to return without handling the fault.

Discussed with:	markj@
This commit is contained in:
Justin Hibbits 2017-06-09 20:26:42 +00:00
parent f67b5de754
commit 880870b41a
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
sys/cddl/dev/dtrace/powerpc/dtrace_subr.c
View File

@ -267,6 +267,7 @@ dtrace_gethrestime(void)
int int
dtrace_trap(struct trapframe *frame, u_int type) dtrace_trap(struct trapframe *frame, u_int type)
{ {
uint16_t nofault;
/* /*
* A trap can occur while DTrace executes a probe. Before * A trap can occur while DTrace executes a probe. Before
@ -277,7 +278,11 @@ dtrace_trap(struct trapframe *frame, u_int type)
* *
* Check if DTrace has enabled 'no-fault' mode: * Check if DTrace has enabled 'no-fault' mode:
*/ */
if ((cpu_core[curcpu].cpuc_dtrace_flags & CPU_DTRACE_NOFAULT) != 0) { sched_pin();
nofault = cpu_core[curcpu].cpuc_dtrace_flags & CPU_DTRACE_NOFAULT;
sched_unpin();
if (nofault) {
KASSERT((frame->srr1 & PSL_EE) == 0, ("interrupts enabled"));
/* /*
* There are only a couple of trap types that are expected. * There are only a couple of trap types that are expected.
* All the rest will be handled in the usual way. * All the rest will be handled in the usual way.