Gavin Maltby wrote:
The call to preempt from sparc interrupt.s is to avoid interrupts running
endlessly on a cpu while pinning an interrupted thread (which could run
on another cpu if only we'd unpin it). In sparc new interrupts can be
queued at the pil we're servicing even while we are serviving preexisting
requests (new requests come in at traplevel 1 via vec_interrupt).
x86 does not require this check.
Sorry, I'm not familiar with Sparc platform.
As I known, cmnint routine will mask same or below level's interrupt by
calling psm_intr_enter.
Does it means sparc CPU don't mask the interrupt at same level?
That flag is t_astflag in the thread structure - you'll see it
checked in user_rtt for sparc and in lwp_rtt for x86.
Exactly how you get there is left as an exercise (ie it
is convoluted).
Yeah, after reading source code again, I know poke_cpu can cause other
CPU's preemption via a crosscall.
Finally, I found the entry point of rtt code for x86 platform:
http://cvs.opensolaris.org/source/xref/on/usr/src/uts/i86pc/ml/interrupt.s
536 ENTRY_NP2(cmnint, _interrupt)
537
538 INTR_PUSH
...........................
836 .intr_ret2:
837 movl CPU_SOFTINFO(%ebx), %edx
838 orl %edx, %edx
839 jz _sys_rtt ------------------------> entry point of rtt code
840 jmp dosoftint
841 SET_SIZE(cmnint)
842 SET_SIZE(_interrupt)
In _sys_rtt code, if it return to user mode with t_astflag set, that
will cause a AST trap:
1916 /*
1917 * Return to User.
1918 */
1919
1920 ALTENTRY(sys_rtt_syscall)
1921 /* check for an AST that's posted to the lwp */
1922 movl %gs:CPU_THREAD, %eax
1923 cli /* disable interrupts */
1924 cmpb $0, T_ASTFLAG(%eax) /* test for signal or AST flag
*/ --------------> t_astflag
1925 jne handle_ast
1926
............................................
1935
1936 handle_ast:
1937 /* Let trap() handle the AST */
1938 sti /* enable interrupts */
1939 movl $T_AST, REGOFF_TRAPNO(%esp) /* set trap type to AST */
1940 movl %esp, %eax
1941 pushl %gs:CPU_ID
1942 pushl $0
1943 pushl %eax
1944 call trap /* trap(rp, 0, cpuid) */
--------------->AST trap
1945 addl $12, %esp
1946 jmp _sys_rtt
At last, return-from-trap code will call preemt if cpu_runrun set.
But poke_cpu is just called for other cpu, not current thread's cpu.
For current thread's cpu or a UP system, the user preemptions only
happen when syscall, trap or interupt (typically, clock interrupt) return.
That's my understanding, is it right?
It seems AST trap is not only used for user preemtion but also for
process signal mechanism. Maybe I can work out how it work in folloing
days.
Anyway, your reply is valuable for me, thank you!
--
Cheers,
----------------------------------------------------------------------
Oliver Yang | OPG Engineering Operation | [EMAIL PROTECTED] | x82229
_______________________________________________
opensolaris-code mailing list
[email protected]
http://mail.opensolaris.org/mailman/listinfo/opensolaris-code
