login
Header Space

 
 

[PATCH 29 of 31] xen: short-cut for recursive event handling

Score:
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: Ingo Molnar <mingo@...>
Cc: LKML <linux-kernel@...>, Ian Campbell <ijc@...>
Date: Monday, March 17, 2008 - 7:37 pm

If an event comes in while events are currently being processed, then
just increment the counter and have the outer event loop reprocess the
pending events.  This prevents unbounded recursion on heavy event
loads (of course massive event storms will cause infinite loops).

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
---
 arch/x86/xen/events.c |   46 ++++++++++++++++++++++++++++++----------------
 1 file changed, 30 insertions(+), 16 deletions(-)

diff --git a/arch/x86/xen/events.c b/arch/x86/xen/events.c
--- a/arch/x86/xen/events.c
+++ b/arch/x86/xen/events.c
@@ -517,29 +517,43 @@
 	int cpu = get_cpu();
 	struct shared_info *s = HYPERVISOR_shared_info;
 	struct vcpu_info *vcpu_info = __get_cpu_var(xen_vcpu);
-	unsigned long pending_words;
+	static DEFINE_PER_CPU(unsigned, nesting_count);
+ 	unsigned count;
 
-	vcpu_info->evtchn_upcall_pending = 0;
+	do {
+		unsigned long pending_words;
 
-	/* NB. No need for a barrier here -- XCHG is a barrier on x86. */
-	pending_words = xchg(&vcpu_info->evtchn_pending_sel, 0);
-	while (pending_words != 0) {
-		unsigned long pending_bits;
-		int word_idx = __ffs(pending_words);
-		pending_words &= ~(1UL << word_idx);
+		vcpu_info->evtchn_upcall_pending = 0;
 
-		while ((pending_bits = active_evtchns(cpu, s, word_idx)) != 0) {
-			int bit_idx = __ffs(pending_bits);
-			int port = (word_idx * BITS_PER_LONG) + bit_idx;
-			int irq = evtchn_to_irq[port];
+		if (__get_cpu_var(nesting_count)++)
+			goto out;
 
-			if (irq != -1) {
-				regs->orig_ax = ~irq;
-				do_IRQ(regs);
+		/* NB. No need for a barrier here -- XCHG is a barrier on x86. */
+		pending_words = xchg(&vcpu_info->evtchn_pending_sel, 0);
+		while (pending_words != 0) {
+			unsigned long pending_bits;
+			int word_idx = __ffs(pending_words);
+			pending_words &= ~(1UL << word_idx);
+
+			while ((pending_bits = active_evtchns(cpu, s, word_idx)) != 0) {
+				int bit_idx = __ffs(pending_bits);
+				int port = (word_idx * BITS_PER_LONG) + bit_idx;
+				int irq = evtchn_to_irq[port];
+
+				if (irq != -1) {
+					regs->orig_ax = ~irq;
+					do_IRQ(regs);
+				}
 			}
 		}
-	}
 
+		BUG_ON(!irqs_disabled());
+
+		count = __get_cpu_var(nesting_count);
+		__get_cpu_var(nesting_count) = 0;
+	} while(count != 1);
+
+out:
 	put_cpu();
 }
 


--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
[PATCH 00 of 31] x86: unification and xen updates, Jeremy Fitzhardinge, (Mon Mar 17, 7:36 pm)
[PATCH 13 of 31] x86/pgtable.h: demacro ptep_test_and_clear_..., Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 03 of 31] x86: convert pgalloc_64.h from macros to in..., Jeremy Fitzhardinge, (Mon Mar 17, 7:36 pm)
[PATCH 20 of 31] xen: unify pte operations on machine frames, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 01 of 31] xen: fix RMW when unmasking events, Jeremy Fitzhardinge, (Mon Mar 17, 7:36 pm)
[PATCH 31 of 31] xen: jump to iret fixup, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 05 of 31] x86: put paravirt stubs into common asm/pga..., Jeremy Fitzhardinge, (Mon Mar 17, 7:36 pm)
[PATCH 24 of 31] xen: add support for callbackops hypercall, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 28 of 31] xen: make sure retriggered events are set p..., Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 18 of 31] xen: unify pte operations, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 25 of 31] x86: only enable interrupts when kernel sta..., Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 09 of 31] x86: move all the pgd_list handling to one ..., Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 29 of 31] xen: short-cut for recursive event handling, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 22 of 31] x86: unify KERNEL_PGD_PTRS, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 10 of 31] x86: rename paravirt_alloc_pt etc after the..., Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 19 of 31] xen: use phys_addr_t when referring to phys..., Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 02 of 31] xen: fix UP setup of shared_info, Jeremy Fitzhardinge, (Mon Mar 17, 7:36 pm)
[PATCH 27 of 31] xen: implement a debug-interrupt handler, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 17 of 31] xen: make use of pte_t union, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 06 of 31] x86: move pte functions into common asm/pga..., Jeremy Fitzhardinge, (Mon Mar 17, 7:36 pm)
[PATCH 23 of 31] x86: unify pgd ctor/dtor, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 12 of 31] x86/pgtable.h: demacro ptep_set_access_flags, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 21 of 31] xen: make sure iret faults are trapped, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 14 of 31] x86/pgtable.h: demacro ptep_clear_flush_young, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 15 of 31] x86: demacro pgalloc paravirt stubs, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 04 of 31] x86: add common mm/pgtable.c, Jeremy Fitzhardinge, (Mon Mar 17, 7:36 pm)
[PATCH 08 of 31] x86: move pgalloc pud and pgd operations in..., Jeremy Fitzhardinge, (Mon Mar 17, 7:36 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Ingo Molnar, (Wed Mar 19, 3:05 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Ingo Molnar, (Wed Mar 19, 3:46 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Jeremy Fitzhardinge, (Wed Mar 19, 4:02 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Ingo Molnar, (Wed Mar 19, 4:09 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Jeremy Fitzhardinge, (Wed Mar 19, 5:12 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Ingo Molnar, (Wed Mar 19, 5:33 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Jeremy Fitzhardinge, (Wed Mar 19, 5:54 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Ingo Molnar, (Wed Mar 19, 6:00 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Jeremy Fitzhardinge, (Wed Mar 19, 5:58 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Ingo Molnar, (Wed Mar 19, 6:04 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Jeremy Fitzhardinge, (Wed Mar 19, 6:15 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Ingo Molnar, (Wed Mar 19, 7:52 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Jeremy Fitzhardinge, (Thu Mar 20, 4:24 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Ingo Molnar, (Fri Mar 21, 9:17 am)
Re: [PATCH 00 of 31] x86: unification and xen updates, Ingo Molnar, (Fri Mar 21, 10:35 am)
Re: [PATCH 00 of 31] x86: unification and xen updates, Jeremy Fitzhardinge, (Fri Mar 21, 11:15 am)
Re: [PATCH 00 of 31] x86: unification and xen updates, Ingo Molnar, (Fri Mar 21, 11:25 am)
Re: [PATCH 00 of 31] x86: unification and xen updates, Jeremy Fitzhardinge, (Fri Mar 21, 10:34 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Ian Campbell, (Wed Mar 19, 5:22 am)
Re: [PATCH 00 of 31] x86: unification and xen updates, Jeremy Fitzhardinge, (Wed Mar 19, 11:11 am)
Re: [PATCH 00 of 31] x86: unification and xen updates, Ingo Molnar, (Wed Mar 19, 3:07 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Jeremy Fitzhardinge, (Wed Mar 19, 3:19 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Ian Campbell, (Wed Mar 19, 12:50 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Jeremy Fitzhardinge, (Wed Mar 19, 2:45 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Zachary Amsden, (Tue Mar 18, 5:33 pm)
Re: [PATCH 00 of 31] x86: unification and xen updates, Jeremy Fitzhardinge, (Tue Mar 18, 5:37 pm)
[PATCH 30 of 31] xen: no need for domU to worry about MCE/MCA, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 26 of 31] xen: support sysenter/sysexit if hypervisor..., Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 11 of 31] x86: add pud_alloc for 4-level pagetables, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 16 of 31] xen: use appropriate pte types, Jeremy Fitzhardinge, (Mon Mar 17, 7:37 pm)
[PATCH 07 of 31] x86: move pmd functions into common asm/pga..., Jeremy Fitzhardinge, (Mon Mar 17, 7:36 pm)
speck-geostationary