Skip to contentSkip to conversation

Linux: FIFO-based event channel ABI

PATCH Superseded David Vrabel 3 participants 21 messages Oct 2, 2013

Subsystems (3)

v5 of 9 Superseded Latest is v9 →

lore
Share & tools
lore
#0 lore raw

v5 cover Linux: FIFO-based event channel ABI

This is the complete Linux guest-side implementation of the FIFO-based event channel ABI described in this design document:

http://xenbits.xen.org/people/dvrabel/event-channels-F.pdf

Refer also to the Xen series.

Note that __startup_pirq() was never ideal as failure when binding a PIRQ to an event channel cannot be propagated to the calling driver since the irq_startup callback cannot return an error. This series adds another (very unlikely) failure point to __startup_pirq().

I have a half-bakedpatch series to refactor when PIRQs are setup and torn down but this won't be ready for a while and I do not think this is a prerequisite for applying the FIFO-based ABI series.

Patch 1 is a obvious refactoring of common code.

Patch 2-6 prepare for supporting multiple ABIs.

Patch 7 adds the low-level evtchn_ops hooks.

Patch 8-9 add an additional hook for ABI-specific per-port setup (used for expanding the event array as more event are bound).

Patch 10 allows many more event channels to be supported by altering how the event channel to irq map is allocated. Note that other factors limit the number of supported IRQs (IRQs is 8192 + 64 * NR_CPUS).

Patch 11 is some trival refactoring.

Patch 12 removes a limit on the number of event channels supported by the xen-evtchn driver.

Patch 13 adds the hypervisor ABI.

Patches 14-15 Set the priority of VIRQ_TIMER events to the highest.

Patch 16 adds the FIFO-based ABI implementation.

Changes in v5 (v4 not posted):

- Set priority of VIRQ_TIMER.
- Remove NR_EVENT_CHANNELS limit from xen-evtchn driver.
- Licence drivers/xen/events/fifo.c under a dual MIT/GPLv2.

Changes in v3:

- Support suspend/resume by reinitializing the control blocks on resume.
- Only init control block if one does not exist (should fix CPU hotplug).

David

#1 lore raw

PATCH v5 1/16 xen/events: refactor retrigger_dynirq() and resend_irq_on_evtchn()

From: David Vrabel <[email protected]>

These two function did the same thing with different parameters, put the common bits in retrigger_evtchn().

This changes the return value of resend_irq_on_evtchn() but the only caller (in arch/ia64/xen/irq_xen.c) ignored the return value so this is fine.

---
 drivers/xen/events.c |   27 +++++++++------------------
 1 files changed, 9 insertions(+), 18 deletions(-)
drivers/xen/events.c +9 -18
index 4035e83..ddcdbb5 100644
@@ -1558,13 +1558,13 @@ static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 	return rebind_irq_to_cpu(data->irq, tcpu);
 }
 
-int resend_irq_on_evtchn(unsigned int irq)
+static int retrigger_evtchn(int evtchn)
 {
-	int masked, evtchn = evtchn_from_irq(irq);
+	int masked;
 	struct shared_info *s = HYPERVISOR_shared_info;
 
 	if (!VALID_EVTCHN(evtchn))
-		return 1;
+		return 0;
 
 	masked = sync_test_and_set_bit(evtchn, BM(s->evtchn_mask));
 	sync_set_bit(evtchn, BM(s->evtchn_pending));
@@ -1574,6 +1574,11 @@ int resend_irq_on_evtchn(unsigned int irq)
 	return 1;
 }
 
+int resend_irq_on_evtchn(unsigned int irq)
+{
+	return retrigger_evtchn(evtchn_from_irq(irq));
+}
+
 static void enable_dynirq(struct irq_data *data)
 {
 	int evtchn = evtchn_from_irq(data->irq);
@@ -1608,21 +1613,7 @@ static void mask_ack_dynirq(struct irq_data *data)
 
 static int retrigger_dynirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(data->irq);
-	struct shared_info *sh = HYPERVISOR_shared_info;
-	int ret = 0;
-
-	if (VALID_EVTCHN(evtchn)) {
-		int masked;
-
-		masked = sync_test_and_set_bit(evtchn, BM(sh->evtchn_mask));
-		sync_set_bit(evtchn, BM(sh->evtchn_pending));
-		if (!masked)
-			unmask_evtchn(evtchn);
-		ret = 1;
-	}
-
-	return ret;
+	return retrigger_evtchn(evtchn_from_irq(data->irq));
 }
 
 static void restore_pirqs(void)
Signature · 1 line
1.7.2.5
#2 lore raw

Re: [PATCH 01/16] xen/events: refactor retrigger_dynirq() and resend_irq_on_evtchn()

Quoted 10 lines · David Vrabel

From: David Vrabel <[email protected]>

These two function did the same thing with different parameters, put the common bits in retrigger_evtchn().

This changes the return value of resend_irq_on_evtchn() but the only caller (in arch/ia64/xen/irq_xen.c) ignored the return value so this is fine.

Hm, I thought I acked it?

Quoted 63 lines
---
 drivers/xen/events.c |   27 +++++++++------------------
 1 files changed, 9 insertions(+), 18 deletions(-)
drivers/xen/events.c +9 -18
index 4035e83..ddcdbb5 100644
@@ -1558,13 +1558,13 @@ static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 	return rebind_irq_to_cpu(data->irq, tcpu);
 }
 
-int resend_irq_on_evtchn(unsigned int irq)
+static int retrigger_evtchn(int evtchn)
 {
-	int masked, evtchn = evtchn_from_irq(irq);
+	int masked;
 	struct shared_info *s = HYPERVISOR_shared_info;
 
 	if (!VALID_EVTCHN(evtchn))
-		return 1;
+		return 0;
 
 	masked = sync_test_and_set_bit(evtchn, BM(s->evtchn_mask));
 	sync_set_bit(evtchn, BM(s->evtchn_pending));
@@ -1574,6 +1574,11 @@ int resend_irq_on_evtchn(unsigned int irq)
 	return 1;
 }
 
+int resend_irq_on_evtchn(unsigned int irq)
+{
+	return retrigger_evtchn(evtchn_from_irq(irq));
+}
+
 static void enable_dynirq(struct irq_data *data)
 {
 	int evtchn = evtchn_from_irq(data->irq);
@@ -1608,21 +1613,7 @@ static void mask_ack_dynirq(struct irq_data *data)
 
 static int retrigger_dynirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(data->irq);
-	struct shared_info *sh = HYPERVISOR_shared_info;
-	int ret = 0;
-
-	if (VALID_EVTCHN(evtchn)) {
-		int masked;
-
-		masked = sync_test_and_set_bit(evtchn, BM(sh->evtchn_mask));
-		sync_set_bit(evtchn, BM(sh->evtchn_pending));
-		if (!masked)
-			unmask_evtchn(evtchn);
-		ret = 1;
-	}
-
-	return ret;
+	return retrigger_evtchn(evtchn_from_irq(data->irq));
 }
 
 static void restore_pirqs(void)
Signature · 1 line
1.7.2.5
#3 lore raw

Re: [PATCH 01/16] xen/events: refactor retrigger_dynirq() and resend_irq_on_evtchn()

Quoted 6 lines · Konrad Rzeszutek Wilk
Quoted 5 lines · David Vrabel

From: David Vrabel <[email protected]>

These two function did the same thing with different parameters, put the common bits in retrigger_evtchn().

Quoted 7 lines
Quoted 5 lines

This changes the return value of resend_irq_on_evtchn() but the only caller (in arch/ia64/xen/irq_xen.c) ignored the return value so this is fine.

Hm, I thought I acked it?

You said "Looks good to me" which wasn't official enough to add as a tag.

David

#4 lore raw

Re: [PATCH 01/16] xen/events: refactor retrigger_dynirq() and resend_irq_on_evtchn()

Quoted 11 lines · David Vrabel
Quoted 10 lines · Konrad Rzeszutek Wilk
Quoted 9 lines · David Vrabel

From: David Vrabel <[email protected]>

These two function did the same thing with different parameters, put the common bits in retrigger_evtchn().

This changes the return value of resend_irq_on_evtchn() but the only caller (in arch/ia64/xen/irq_xen.c) ignored the return value so this is fine.

Quoted 5 lines
Quoted 3 lines
Quoted 1 line

Hm, I thought I acked it?

You said "Looks good to me" which wasn't official enough to add as a tag.

It is in the Linux kernel, see Documentation/SubmittingPatches:

13) When to use Acked-by: and Cc:

The Signed-off-by: tag indicates that the signer was involved in the development of the patch, or that he/she was in the patch's delivery path.

If a person was not directly involved in the preparation or handling of a patch but wishes to signify and record their approval of it then they can arrange to have an Acked-by: line added to the patch's changelog.

Acked-by: is often used by the maintainer of the affected code when that maintainer neither contributed to nor forwarded the patch.

Acked-by: is not as formal as Signed-off-by:. It is a record that the acker has at least reviewed the patch and has indicated acceptance. Hence patch mergers will sometimes manually convert an acker's "yep, looks good to me" into an Acked-by:.

Quoted 2 lines

David

#5 lore raw

Re: [PATCH 01/16] xen/events: refactor retrigger_dynirq() and resend_irq_on_evtchn()

Quoted 12 lines · Konrad Rzeszutek Wilk
Quoted 11 lines · David Vrabel
Quoted 10 lines · Konrad Rzeszutek Wilk
Quoted 9 lines · David Vrabel

From: David Vrabel <[email protected]>

These two function did the same thing with different parameters, put the common bits in retrigger_evtchn().

This changes the return value of resend_irq_on_evtchn() but the only caller (in arch/ia64/xen/irq_xen.c) ignored the return value so this is fine.

Quoted 7 lines
Quoted 5 lines
Quoted 3 lines
Quoted 1 line

Hm, I thought I acked it?

You said "Looks good to me" which wasn't official enough to add as a tag.

It is in the Linux kernel, see Documentation/SubmittingPatches:

I don't think it's sensible to interpret potentially ambiguous language into a standard tag, regardless of what other Linux maintainers may do.
This has gone wrong in the past. If you want a tag added you should
write it out in full (which you still haven't done).

David

#6 lore raw

PATCH v5 2/16 xen/events: remove unnecessary init_evtchn_cpu_bindings()

In reply to David Vrabel

From: David Vrabel <[email protected]>

Because the guest-side binding of an event to a VCPU (i.e., setting the local per-cpu masks) is always explicitly done after an event channel is bound to a port, there is no need to initialize all possible events as bound to VCPU 0 at start of day or after a resume.

---
 drivers/xen/events.c |   22 ----------------------
 1 files changed, 0 insertions(+), 22 deletions(-)
drivers/xen/events.c +0 -22
index ddcdbb5..1e2c74b 100644
@@ -334,24 +334,6 @@ static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu)
 	info_for_irq(irq)->cpu = cpu;
 }
 
-static void init_evtchn_cpu_bindings(void)
-{
-	int i;
-#ifdef CONFIG_SMP
-	struct irq_info *info;
-
-	/* By default all event channels notify CPU#0. */
-	list_for_each_entry(info, &xen_irq_list_head, list) {
-		struct irq_desc *desc = irq_to_desc(info->irq);
-		cpumask_copy(desc->irq_data.affinity, cpumask_of(0));
-	}
-#endif
-
-	for_each_possible_cpu(i)
-		memset(per_cpu(cpu_evtchn_mask, i),
-		       (i == 0) ? ~0 : 0, NR_EVENT_CHANNELS/8);
-}
-
 static inline void clear_evtchn(int port)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
@@ -1778,8 +1760,6 @@ void xen_irq_resume(void)
 	unsigned int cpu, evtchn;
 	struct irq_info *info;
 
-	init_evtchn_cpu_bindings();
-
 	/* New event-channel space is not 'live' yet. */
 	for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
 		mask_evtchn(evtchn);
@@ -1890,8 +1870,6 @@ void __init xen_init_IRQ(void)
 	for (i = 0; i < NR_EVENT_CHANNELS; i++)
 		evtchn_to_irq[i] = -1;
 
-	init_evtchn_cpu_bindings();
-
 	/* No event channels are 'live' right now. */
 	for (i = 0; i < NR_EVENT_CHANNELS; i++)
 		mask_evtchn(i);
Signature · 1 line
1.7.2.5
#7 lore raw

PATCH v5 3/16 xen/events: introduce test_and_set_mask

In reply to David Vrabel

From: Wei Liu <[email protected]>

---
 drivers/xen/events.c |   11 ++++++++---
 1 files changed, 8 insertions(+), 3 deletions(-)
drivers/xen/events.c +8 -3
index 1e2c74b..359e983 100644
@@ -352,6 +352,12 @@ static inline int test_evtchn(int port)
 	return sync_test_bit(port, BM(&s->evtchn_pending[0]));
 }
 
+static inline int test_and_set_mask(int port)
+{
+	struct shared_info *s = HYPERVISOR_shared_info;
+	return sync_test_and_set_bit(port, BM(&s->evtchn_mask[0]));
+}
+
 
 /**
  * notify_remote_via_irq - send event to remote end of event channel via irq
@@ -1493,7 +1499,6 @@ void rebind_evtchn_irq(int evtchn, int irq)
 /* Rebind an evtchn so that it gets delivered to a specific cpu */
 static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 {
-	struct shared_info *s = HYPERVISOR_shared_info;
 	struct evtchn_bind_vcpu bind_vcpu;
 	int evtchn = evtchn_from_irq(irq);
 	int masked;
@@ -1516,7 +1521,7 @@ static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 	 * Mask the event while changing the VCPU binding to prevent
 	 * it being delivered on an unexpected VCPU.
 	 */
-	masked = sync_test_and_set_bit(evtchn, BM(s->evtchn_mask));
+	masked = test_and_set_mask(evtchn);
 
 	/*
 	 * If this fails, it usually just indicates that we're dealing with a
@@ -1548,7 +1553,7 @@ static int retrigger_evtchn(int evtchn)
 	if (!VALID_EVTCHN(evtchn))
 		return 0;
 
-	masked = sync_test_and_set_bit(evtchn, BM(s->evtchn_mask));
+	masked = test_and_set_mask(evtchn);
 	sync_set_bit(evtchn, BM(s->evtchn_pending));
 	if (!masked)
 		unmask_evtchn(evtchn);
Signature · 1 line
1.7.2.5
#8 lore raw

PATCH v5 4/16 xen/events: replace raw bit ops with functions

In reply to David Vrabel

From: Wei Liu <[email protected]>

---
 drivers/xen/events.c |    3 +--
 1 files changed, 1 insertions(+), 2 deletions(-)
drivers/xen/events.c +1 -2
index 359e983..fec5da4 100644
@@ -1548,13 +1548,12 @@ static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 static int retrigger_evtchn(int evtchn)
 {
 	int masked;
-	struct shared_info *s = HYPERVISOR_shared_info;
 
 	if (!VALID_EVTCHN(evtchn))
 		return 0;
 
 	masked = test_and_set_mask(evtchn);
-	sync_set_bit(evtchn, BM(s->evtchn_pending));
+	set_evtchn(evtchn);
 	if (!masked)
 		unmask_evtchn(evtchn);
 
Signature · 1 line
1.7.2.5
#9 lore raw

PATCH v5 5/16 xen/events: move drivers/xen/events.c into drivers/xen/events/

In reply to David Vrabel

From: David Vrabel <[email protected]>

events.c will be split into multiple files so move it into its own directory.

---
 drivers/xen/Makefile              |    3 ++-
 drivers/xen/events/Makefile       |    1 +
 drivers/xen/{ => events}/events.c |    0
 3 files changed, 3 insertions(+), 1 deletions(-)
 create mode 100644 drivers/xen/events/Makefile
 rename drivers/xen/{ => events}/events.c (100%)
drivers/xen/Makefile +2 -1
index 14fe79d..d75c811 100644
@@ -2,7 +2,8 @@ ifeq ($(filter y, $(CONFIG_ARM) $(CONFIG_ARM64)),)
 obj-$(CONFIG_HOTPLUG_CPU)		+= cpu_hotplug.o
 endif
 obj-$(CONFIG_X86)			+= fallback.o
-obj-y	+= grant-table.o features.o events.o balloon.o manage.o
+obj-y	+= grant-table.o features.o balloon.o manage.o
+obj-y	+= events/
 obj-y	+= xenbus/
 
 nostackp := $(call cc-option, -fno-stack-protector)
drivers/xen/events/Makefile new file +1 -0
new file mode 100644
index 0000000..86fd7c1
@@ -0,0 +1 @@
+obj-y += events.o
drivers/xen/events/events.c renamed from drivers/xen/events.c +0 -0
similarity index 100%
rename from drivers/xen/events.c
rename to drivers/xen/events/events.c
Signature · 1 line
1.7.2.5
#10 lore raw

PATCH v5 6/16 xen/events: move 2-level specific code into its own file

In reply to David Vrabel

From: David Vrabel <[email protected]>

In preparation for alternative event channel ABIs, move all the functions accessing the shared data structures into their own file.

---
 drivers/xen/events/Makefile          |    1 +
 drivers/xen/events/events.c          |  372 +---------------------------------
 drivers/xen/events/events_internal.h |   74 +++++++
 drivers/xen/events/n-level.c         |  322 +++++++++++++++++++++++++++++
 4 files changed, 408 insertions(+), 361 deletions(-)
 create mode 100644 drivers/xen/events/events_internal.h
 create mode 100644 drivers/xen/events/n-level.c
drivers/xen/events/Makefile +1 -0
index 86fd7c1..aea331e 100644
@@ -1 +1,2 @@
 obj-y += events.o
+obj-y += n-level.o
drivers/xen/events/events.c +11 -361

448 lines not on this page · raw message

drivers/xen/events/events_internal.h new file +74 -0

74 lines not on this page · raw message

drivers/xen/events/n-level.c new file +322 -0

322 lines not on this page · raw message

Signature · 1 line
1.7.2.5
#11 lore raw

PATCH v5 7/16 xen/events: add struct evtchn_ops for the low-level port operations

In reply to David Vrabel

From: David Vrabel <[email protected]>

evtchn_ops contains the low-level operations that access the shared data structures. This allows alternate ABIs to be supported.

---
 drivers/xen/events/events.c          |    4 ++
 drivers/xen/events/events_internal.h |   63 +++++++++++++++++++++++++++++----
 drivers/xen/events/n-level.c         |   32 +++++++++++++----
 3 files changed, 83 insertions(+), 16 deletions(-)
drivers/xen/events/events.c +4 -0
index 2700c12..8ecde63 100644
@@ -61,6 +61,8 @@
 
 #include "events_internal.h"
 
+const struct evtchn_ops *evtchn_ops;
+
 /*
  * This lock protects updates to the following mapping and reference-count
  * arrays. The lock does not need to be acquired to read the mapping tables.
@@ -1518,6 +1520,8 @@ void __init xen_init_IRQ(void)
 {
 	int i;
 
+	xen_evtchn_init_nlevel();
+
 	evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq),
 				    GFP_KERNEL);
 	BUG_ON(!evtchn_to_irq);
drivers/xen/events/events_internal.h +55 -8

76 lines not on this page · raw message

drivers/xen/events/n-level.c +24 -8
index b86a853..6e2804f 100644
@@ -39,43 +39,43 @@
 static DEFINE_PER_CPU(xen_ulong_t [NR_EVENT_CHANNELS/BITS_PER_EVTCHN_WORD],
 		      cpu_evtchn_mask);
 
-void xen_evtchn_port_bind_to_cpu(struct irq_info *info, int cpu)
+static void nlevel_bind_to_cpu(struct irq_info *info, unsigned cpu)
 {
 	clear_bit(info->evtchn, BM(per_cpu(cpu_evtchn_mask, info->cpu)));
 	set_bit(info->evtchn, BM(per_cpu(cpu_evtchn_mask, cpu)));
 }
 
-void clear_evtchn(int port)
+static void nlevel_clear_pending(unsigned port)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
 	sync_clear_bit(port, BM(&s->evtchn_pending[0]));
 }
 
-void set_evtchn(int port)
+static void nlevel_set_pending(unsigned port)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
 	sync_set_bit(port, BM(&s->evtchn_pending[0]));
 }
 
-int test_evtchn(int port)
+static bool nlevel_is_pending(unsigned port)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
 	return sync_test_bit(port, BM(&s->evtchn_pending[0]));
 }
 
-int test_and_set_mask(int port)
+static bool nlevel_test_and_set_mask(unsigned port)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
 	return sync_test_and_set_bit(port, BM(&s->evtchn_mask[0]));
 }
 
-void mask_evtchn(int port)
+static void nlevel_mask(unsigned port)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
 	sync_set_bit(port, BM(&s->evtchn_mask[0]));
 }
 
-void unmask_evtchn(int port)
+static void nlevel_unmask(unsigned port)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
 	unsigned int cpu = get_cpu();
@@ -141,7 +141,7 @@ static inline xen_ulong_t active_evtchns(unsigned int cpu,
  * a bitset of words which contain pending event bits.  The second
  * level is a bitset of pending events themselves.
  */
-void xen_evtchn_handle_events(int cpu)
+static void nlevel_handle_events(unsigned cpu)
 {
 	xen_ulong_t pending_words;
 	int start_word_idx, start_bit_idx;
@@ -320,3 +320,19 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
 
 	return IRQ_HANDLED;
 }
+
+static const struct evtchn_ops evtchn_ops_nlevel = {
+	.bind_to_cpu       = nlevel_bind_to_cpu,
+	.clear_pending     = nlevel_clear_pending,
+	.set_pending       = nlevel_set_pending,
+	.is_pending        = nlevel_is_pending,
+	.test_and_set_mask = nlevel_test_and_set_mask,
+	.mask              = nlevel_mask,
+	.unmask            = nlevel_unmask,
+	.handle_events     = nlevel_handle_events,
+};
+
+void __init xen_evtchn_init_nlevel(void)
+{
+	evtchn_ops = &evtchn_ops_nlevel;
+}
Signature · 1 line
1.7.2.5
#12 lore raw

PATCH v5 8/16 xen/events: allow setup of irq_info to fail

In reply to David Vrabel

From: David Vrabel <[email protected]>

The FIFO-based event ABI requires additional setup of newly bound events (it may need to expand the event array) and this setup may fail.

xen_irq_info_common_init() is a useful place to put this setup so allow this call to fail. This call and the other similar calls are renamed to be *_setup() to reflect that they may now fail.

This failure can only occur with new event channels not on rebind.

---
 drivers/xen/events/events.c |  156 +++++++++++++++++++++++++------------------
 1 files changed, 91 insertions(+), 65 deletions(-)
drivers/xen/events/events.c +91 -65
index 8ecde63..8f55a49 100644
@@ -99,7 +99,7 @@ struct irq_info *info_for_irq(unsigned irq)
 }
 
 /* Constructors for packed IRQ information. */
-static void xen_irq_info_common_init(struct irq_info *info,
+static int xen_irq_info_common_setup(struct irq_info *info,
 				     unsigned irq,
 				     enum xen_irq_type type,
 				     unsigned short evtchn,
@@ -116,45 +116,47 @@ static void xen_irq_info_common_init(struct irq_info *info,
 	evtchn_to_irq[evtchn] = irq;
 
 	irq_clear_status_flags(irq, IRQ_NOREQUEST|IRQ_NOAUTOEN);
+
+	return 0;
 }
 
-static void xen_irq_info_evtchn_init(unsigned irq,
+static int xen_irq_info_evtchn_setup(unsigned irq,
 				     unsigned short evtchn)
 {
 	struct irq_info *info = info_for_irq(irq);
 
-	xen_irq_info_common_init(info, irq, IRQT_EVTCHN, evtchn, 0);
+	return xen_irq_info_common_setup(info, irq, IRQT_EVTCHN, evtchn, 0);
 }
 
-static void xen_irq_info_ipi_init(unsigned cpu,
+static int xen_irq_info_ipi_setup(unsigned cpu,
 				  unsigned irq,
 				  unsigned short evtchn,
 				  enum ipi_vector ipi)
 {
 	struct irq_info *info = info_for_irq(irq);
 
-	xen_irq_info_common_init(info, irq, IRQT_IPI, evtchn, 0);
-
 	info->u.ipi = ipi;
 
 	per_cpu(ipi_to_irq, cpu)[ipi] = irq;
+
+	return xen_irq_info_common_setup(info, irq, IRQT_IPI, evtchn, 0);
 }
 
-static void xen_irq_info_virq_init(unsigned cpu,
+static int xen_irq_info_virq_setup(unsigned cpu,
 				   unsigned irq,
 				   unsigned short evtchn,
 				   unsigned short virq)
 {
 	struct irq_info *info = info_for_irq(irq);
 
-	xen_irq_info_common_init(info, irq, IRQT_VIRQ, evtchn, 0);
-
 	info->u.virq = virq;
 
 	per_cpu(virq_to_irq, cpu)[virq] = irq;
+
+	return xen_irq_info_common_setup(info, irq, IRQT_VIRQ, evtchn, 0);
 }
 
-static void xen_irq_info_pirq_init(unsigned irq,
+static int xen_irq_info_pirq_setup(unsigned irq,
 				   unsigned short evtchn,
 				   unsigned short pirq,
 				   unsigned short gsi,
@@ -163,12 +165,12 @@ static void xen_irq_info_pirq_init(unsigned irq,
 {
 	struct irq_info *info = info_for_irq(irq);
 
-	xen_irq_info_common_init(info, irq, IRQT_PIRQ, evtchn, 0);
-
 	info->u.pirq.pirq = pirq;
 	info->u.pirq.gsi = gsi;
 	info->u.pirq.domid = domid;
 	info->u.pirq.flags = flags;
+
+	return xen_irq_info_common_setup(info, irq, IRQT_PIRQ, evtchn, 0);
 }
 
 /*
@@ -516,6 +518,47 @@ int xen_irq_from_gsi(unsigned gsi)
 }
 EXPORT_SYMBOL_GPL(xen_irq_from_gsi);
 
+static void __unbind_from_irq(unsigned int irq)
+{
+	struct evtchn_close close;
+	int evtchn = evtchn_from_irq(irq);
+	struct irq_info *info = irq_get_handler_data(irq);
+
+	if (info->refcnt > 0) {
+		info->refcnt--;
+		if (info->refcnt != 0)
+			return;
+	}
+
+	if (VALID_EVTCHN(evtchn)) {
+		close.port = evtchn;
+		if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
+			BUG();
+
+		switch (type_from_irq(irq)) {
+		case IRQT_VIRQ:
+			per_cpu(virq_to_irq, cpu_from_evtchn(evtchn))
+				[virq_from_irq(irq)] = -1;
+			break;
+		case IRQT_IPI:
+			per_cpu(ipi_to_irq, cpu_from_evtchn(evtchn))
+				[ipi_from_irq(irq)] = -1;
+			break;
+		default:
+			break;
+		}
+
+		/* Closed ports are implicitly re-bound to VCPU0. */
+		bind_evtchn_to_cpu(evtchn, 0);
+
+		evtchn_to_irq[evtchn] = -1;
+	}
+
+	BUG_ON(info_for_irq(irq)->type == IRQT_UNBOUND);
+
+	xen_free_irq(irq);
+}
+
 /*
  * Do not make any assumptions regarding the relationship between the
  * IRQ number returned here and the Xen pirq argument.
@@ -531,6 +574,7 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 {
 	int irq = -1;
 	struct physdev_irq irq_op;
+	int ret;
 
 	mutex_lock(&irq_mapping_update_lock);
 
@@ -558,8 +602,13 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
 		goto out;
 	}
 
-	xen_irq_info_pirq_init(irq, 0, pirq, gsi, DOMID_SELF,
+	ret = xen_irq_info_pirq_setup(irq, 0, pirq, gsi, DOMID_SELF,
 			       shareable ? PIRQ_SHAREABLE : 0);
+	if (ret < 0) {
+		__unbind_from_irq(irq);
+		irq = ret;
+		goto out;
+	}
 
 	pirq_query_unmask(irq);
 	/* We try to use the handler with the appropriate semantic for the
@@ -619,7 +668,9 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 	irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_edge_irq,
 			name);
 
-	xen_irq_info_pirq_init(irq, 0, pirq, 0, domid, 0);
+	ret = xen_irq_info_pirq_setup(irq, 0, pirq, 0, domid, 0);
+	if (ret < 0)
+		goto error_irq;
 	ret = irq_set_msi_desc(irq, msidesc);
 	if (ret < 0)
 		goto error_irq;
@@ -627,8 +678,8 @@ out:
 	mutex_unlock(&irq_mapping_update_lock);
 	return irq;
 error_irq:
+	__unbind_from_irq(irq);
 	mutex_unlock(&irq_mapping_update_lock);
-	xen_free_irq(irq);
 	return ret;
 }
 #endif
@@ -698,9 +749,11 @@ int xen_pirq_from_irq(unsigned irq)
 	return pirq_from_irq(irq);
 }
 EXPORT_SYMBOL_GPL(xen_pirq_from_irq);
+
 int bind_evtchn_to_irq(unsigned int evtchn)
 {
 	int irq;
+	int ret;
 
 	mutex_lock(&irq_mapping_update_lock);
 
@@ -714,7 +767,12 @@ int bind_evtchn_to_irq(unsigned int evtchn)
 		irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
 					      handle_edge_irq, "event");
 
-		xen_irq_info_evtchn_init(irq, evtchn);
+		ret = xen_irq_info_evtchn_setup(irq, evtchn);
+		if (ret < 0) {
+			__unbind_from_irq(irq);
+			irq = ret;
+			goto out;
+		}
 	} else {
 		struct irq_info *info = info_for_irq(irq);
 		WARN_ON(info == NULL || info->type != IRQT_EVTCHN);
@@ -731,6 +789,7 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 {
 	struct evtchn_bind_ipi bind_ipi;
 	int evtchn, irq;
+	int ret;
 
 	mutex_lock(&irq_mapping_update_lock);
 
@@ -750,8 +809,12 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 			BUG();
 		evtchn = bind_ipi.port;
 
-		xen_irq_info_ipi_init(cpu, irq, evtchn, ipi);
-
+		ret = xen_irq_info_ipi_setup(cpu, irq, evtchn, ipi);
+		if (ret < 0) {
+			__unbind_from_irq(irq);
+			irq = ret;
+			goto out;
+		}
 		bind_evtchn_to_cpu(evtchn, cpu);
 	} else {
 		struct irq_info *info = info_for_irq(irq);
@@ -830,7 +893,12 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
 			evtchn = ret;
 		}
 
-		xen_irq_info_virq_init(cpu, irq, evtchn, virq);
+		ret = xen_irq_info_virq_setup(cpu, irq, evtchn, virq);
+		if (ret < 0) {
+			__unbind_from_irq(irq);
+			irq = ret;
+			goto out;
+		}
 
 		bind_evtchn_to_cpu(evtchn, cpu);
 	} else {
@@ -846,50 +914,8 @@ out:
 
 static void unbind_from_irq(unsigned int irq)
 {
-	struct evtchn_close close;
-	int evtchn = evtchn_from_irq(irq);
-	struct irq_info *info = irq_get_handler_data(irq);
-
-	if (WARN_ON(!info))
-		return;
-
 	mutex_lock(&irq_mapping_update_lock);
-
-	if (info->refcnt > 0) {
-		info->refcnt--;
-		if (info->refcnt != 0)
-			goto done;
-	}
-
-	if (VALID_EVTCHN(evtchn)) {
-		close.port = evtchn;
-		if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
-			BUG();
-
-		switch (type_from_irq(irq)) {
-		case IRQT_VIRQ:
-			per_cpu(virq_to_irq, cpu_from_evtchn(evtchn))
-				[virq_from_irq(irq)] = -1;
-			break;
-		case IRQT_IPI:
-			per_cpu(ipi_to_irq, cpu_from_evtchn(evtchn))
-				[ipi_from_irq(irq)] = -1;
-			break;
-		default:
-			break;
-		}
-
-		/* Closed ports are implicitly re-bound to VCPU0. */
-		bind_evtchn_to_cpu(evtchn, 0);
-
-		evtchn_to_irq[evtchn] = -1;
-	}
-
-	BUG_ON(info_for_irq(irq)->type == IRQT_UNBOUND);
-
-	xen_free_irq(irq);
-
- done:
+	__unbind_from_irq(irq);
 	mutex_unlock(&irq_mapping_update_lock);
 }
 
@@ -1137,7 +1163,7 @@ void rebind_evtchn_irq(int evtchn, int irq)
 	   so there should be a proper type */
 	BUG_ON(info->type == IRQT_UNBOUND);
 
-	xen_irq_info_evtchn_init(irq, evtchn);
+	xen_irq_info_evtchn_setup(irq, evtchn);
 
 	mutex_unlock(&irq_mapping_update_lock);
 
@@ -1312,7 +1338,7 @@ static void restore_cpu_virqs(unsigned int cpu)
 		evtchn = bind_virq.port;
 
 		/* Record the new mapping. */
-		xen_irq_info_virq_init(cpu, irq, evtchn, virq);
+		xen_irq_info_virq_setup(cpu, irq, evtchn, virq);
 		bind_evtchn_to_cpu(evtchn, cpu);
 	}
 }
@@ -1336,7 +1362,7 @@ static void restore_cpu_ipis(unsigned int cpu)
 		evtchn = bind_ipi.port;
 
 		/* Record the new mapping. */
-		xen_irq_info_ipi_init(cpu, irq, evtchn, ipi);
+		xen_irq_info_ipi_setup(cpu, irq, evtchn, ipi);
 		bind_evtchn_to_cpu(evtchn, cpu);
 	}
 }
Signature · 1 line
1.7.2.5
#13 lore raw

PATCH v5 9/16 xen/events: add a evtchn_op for port setup

In reply to David Vrabel

From: David Vrabel <[email protected]>

Add a hook for port-specific setup and call it from xen_irq_info_common_setup().

The FIFO-based ABIs may need to perform additional setup (expanding the event array) before a bound event channel can start to receive events.

---
 drivers/xen/events/events.c          |    2 +-
 drivers/xen/events/events_internal.h |   12 ++++++++++++
 2 files changed, 13 insertions(+), 1 deletions(-)
drivers/xen/events/events.c +1 -1
index 8f55a49..cf1c7ba 100644
@@ -117,7 +117,7 @@ static int xen_irq_info_common_setup(struct irq_info *info,
 
 	irq_clear_status_flags(irq, IRQ_NOREQUEST|IRQ_NOAUTOEN);
 
-	return 0;
+	return xen_evtchn_port_setup(info);
 }
 
 static int xen_irq_info_evtchn_setup(unsigned irq,
drivers/xen/events/events_internal.h +12 -0
index ba88f57..3eb573a 100644
@@ -55,6 +55,7 @@ struct irq_info {
 #define PIRQ_SHAREABLE	(1 << 1)
 
 struct evtchn_ops {
+	int (*setup)(struct irq_info *info);
 	void (*bind_to_cpu)(struct irq_info *info, unsigned cpu);
 
 	void (*clear_pending)(unsigned port);
@@ -75,6 +76,17 @@ struct irq_info *info_for_irq(unsigned irq);
 unsigned cpu_from_irq(unsigned irq);
 unsigned cpu_from_evtchn(unsigned int evtchn);
 
+/*
+ * Do any ABI specific setup for a bound event channel before it can
+ * be unmasked and used.
+ */
+static inline int xen_evtchn_port_setup(struct irq_info *info)
+{
+	if (evtchn_ops->setup)
+		return evtchn_ops->setup(info);
+	return 0;
+}
+
 static inline void xen_evtchn_port_bind_to_cpu(struct irq_info *info,
 					       unsigned cpu)
 {
Signature · 1 line
1.7.2.5
#14 lore raw

PATCH v5 10/16 xen/events: Refactor evtchn_to_irq array to be dynamically allocated

In reply to David Vrabel

From: Malcolm Crossley <[email protected]>

Refactor static array evtchn_to_irq array to be dynamically allocated by implementing get and set functions for accesses to the array.

Two new port ops are added: max_channels (maximum supported number of event channels) and nr_channels (number of currently usable event channels). For the N-level ABI, these numbers are both the same as the shared data structure is a fixed size. For the FIFO ABI, these will be different as the event array is expanded dynamically.

This allows more than 65000 event channels so an unsigned short is no longer sufficient for an event channel port number and unsigned int is used instead.

---
 drivers/xen/events/events.c          |  158 ++++++++++++++++++++++++----------
 drivers/xen/events/events_internal.h |   18 ++++-
 drivers/xen/events/n-level.c         |   11 ++-
 3 files changed, 137 insertions(+), 50 deletions(-)
drivers/xen/events/events.c +112 -46
index cf1c7ba..734a957 100644
@@ -77,12 +77,16 @@ static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1};
 /* IRQ <-> IPI mapping */
 static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1};
 
-int *evtchn_to_irq;
+int **evtchn_to_irq;
 #ifdef CONFIG_X86
 static unsigned long *pirq_eoi_map;
 #endif
 static bool (*pirq_needs_eoi)(unsigned irq);
 
+#define EVTCHN_ROW(e)  (e / (PAGE_SIZE/sizeof(**evtchn_to_irq)))
+#define EVTCHN_COL(e)  (e % (PAGE_SIZE/sizeof(**evtchn_to_irq)))
+#define EVTCHN_PER_ROW (PAGE_SIZE / sizeof(**evtchn_to_irq))
+
 /* Xen will never allocate port zero for any purpose. */
 #define VALID_EVTCHN(chn)	((chn) != 0)
 
@@ -92,6 +96,61 @@ static struct irq_chip xen_pirq_chip;
 static void enable_dynirq(struct irq_data *data);
 static void disable_dynirq(struct irq_data *data);
 
+static void clear_evtchn_to_irq_row(unsigned row)
+{
+	unsigned col;
+
+	for (col = 0; col < EVTCHN_PER_ROW; col++)
+		evtchn_to_irq[row][col] = -1;
+}
+
+static void clear_evtchn_to_irq_all(void)
+{
+	unsigned row;
+
+	for (row = 0; row < EVTCHN_ROW(xen_evtchn_max_channels()); row++) {
+		if (evtchn_to_irq[row] == NULL)
+			continue;
+		clear_evtchn_to_irq_row(row);
+	}
+}
+
+static int set_evtchn_to_irq(unsigned evtchn, unsigned irq)
+{
+	unsigned row;
+	unsigned col;
+
+	if (evtchn >= xen_evtchn_max_channels())
+		return -EINVAL;
+
+	row = EVTCHN_ROW(evtchn);
+	col = EVTCHN_COL(evtchn);
+
+	if (evtchn_to_irq[row] == NULL) {
+		/* Unallocated irq entries return -1 anyway */
+		if (irq == -1)
+			return 0;
+
+		evtchn_to_irq[row] = (int *)get_zeroed_page(GFP_KERNEL);
+		if (evtchn_to_irq[row] == NULL)
+			return -ENOMEM;
+
+		clear_evtchn_to_irq_row(row);
+	}
+
+	evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)] = irq;
+	return 0;
+}
+
+int get_evtchn_to_irq(unsigned evtchn)
+{
+	if (evtchn >= xen_evtchn_max_channels())
+		return -1;
+	if (evtchn_to_irq[EVTCHN_ROW(evtchn)] == NULL)
+		return -1;
+	return evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)];
+}
+
 /* Get info for IRQ */
 struct irq_info *info_for_irq(unsigned irq)
 {
@@ -102,7 +161,7 @@ struct irq_info *info_for_irq(unsigned irq)
 static int xen_irq_info_common_setup(struct irq_info *info,
 				     unsigned irq,
 				     enum xen_irq_type type,
-				     unsigned short evtchn,
+				     unsigned evtchn,
 				     unsigned short cpu)
 {
 
@@ -113,7 +172,8 @@ static int xen_irq_info_common_setup(struct irq_info *info,
 	info->evtchn = evtchn;
 	info->cpu = cpu;
 
-	evtchn_to_irq[evtchn] = irq;
+	if (set_evtchn_to_irq(evtchn, irq))
+		return -ENOMEM;
 
 	irq_clear_status_flags(irq, IRQ_NOREQUEST|IRQ_NOAUTOEN);
 
@@ -121,7 +181,7 @@ static int xen_irq_info_common_setup(struct irq_info *info,
 }
 
 static int xen_irq_info_evtchn_setup(unsigned irq,
-				     unsigned short evtchn)
+				     unsigned evtchn)
 {
 	struct irq_info *info = info_for_irq(irq);
 
@@ -130,7 +190,7 @@ static int xen_irq_info_evtchn_setup(unsigned irq,
 
 static int xen_irq_info_ipi_setup(unsigned cpu,
 				  unsigned irq,
-				  unsigned short evtchn,
+				  unsigned evtchn,
 				  enum ipi_vector ipi)
 {
 	struct irq_info *info = info_for_irq(irq);
@@ -144,8 +204,8 @@ static int xen_irq_info_ipi_setup(unsigned cpu,
 
 static int xen_irq_info_virq_setup(unsigned cpu,
 				   unsigned irq,
-				   unsigned short evtchn,
-				   unsigned short virq)
+				   unsigned evtchn,
+				   unsigned virq)
 {
 	struct irq_info *info = info_for_irq(irq);
 
@@ -157,9 +217,9 @@ static int xen_irq_info_virq_setup(unsigned cpu,
 }
 
 static int xen_irq_info_pirq_setup(unsigned irq,
-				   unsigned short evtchn,
-				   unsigned short pirq,
-				   unsigned short gsi,
+				   unsigned evtchn,
+				   unsigned pirq,
+				   unsigned gsi,
 				   uint16_t domid,
 				   unsigned char flags)
 {
@@ -186,7 +246,7 @@ static unsigned int evtchn_from_irq(unsigned irq)
 
 unsigned irq_from_evtchn(unsigned int evtchn)
 {
-	return evtchn_to_irq[evtchn];
+	return get_evtchn_to_irq(evtchn);
 }
 EXPORT_SYMBOL_GPL(irq_from_evtchn);
 
@@ -232,7 +292,7 @@ unsigned cpu_from_irq(unsigned irq)
 
 unsigned int cpu_from_evtchn(unsigned int evtchn)
 {
-	int irq = evtchn_to_irq[evtchn];
+	int irq = get_evtchn_to_irq(evtchn);
 	unsigned ret = 0;
 
 	if (irq != -1)
@@ -258,7 +318,7 @@ static bool pirq_needs_eoi_flag(unsigned irq)
 
 static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu)
 {
-	int irq = evtchn_to_irq[chn];
+	int irq = get_evtchn_to_irq(chn);
 	struct irq_info *info = info_for_irq(irq);
 
 	BUG_ON(irq == -1);
@@ -381,6 +441,18 @@ static void xen_free_irq(unsigned irq)
 	irq_free_desc(irq);
 }
 
+static void xen_evtchn_close(unsigned port)
+{
+	struct evtchn_close close;
+
+	close.port = port;
+	if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
+		BUG();
+
+	/* Closed ports are implicitly re-bound to VCPU0. */
+	bind_evtchn_to_cpu(port, 0);
+}
+
 static void pirq_query_unmask(int irq)
 {
 	struct physdev_irq_status_query irq_status;
@@ -453,7 +525,13 @@ static unsigned int __startup_pirq(unsigned int irq)
 
 	pirq_query_unmask(irq);
 
-	evtchn_to_irq[evtchn] = irq;
+	rc = set_evtchn_to_irq(evtchn, irq);
+	if (rc != 0) {
+		pr_err("irq%d: Failed to set port to irq mapping (%d)\n",
+		       irq, rc);
+		xen_evtchn_close(evtchn);
+		return 0;
+	}
 	bind_evtchn_to_cpu(evtchn, 0);
 	info->evtchn = evtchn;
 
@@ -471,10 +549,9 @@ static unsigned int startup_pirq(struct irq_data *data)
 
 static void shutdown_pirq(struct irq_data *data)
 {
-	struct evtchn_close close;
 	unsigned int irq = data->irq;
 	struct irq_info *info = info_for_irq(irq);
-	int evtchn = evtchn_from_irq(irq);
+	unsigned evtchn = evtchn_from_irq(irq);
 
 	BUG_ON(info->type != IRQT_PIRQ);
 
@@ -482,13 +559,8 @@ static void shutdown_pirq(struct irq_data *data)
 		return;
 
 	mask_evtchn(evtchn);
-
-	close.port = evtchn;
-	if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
-		BUG();
-
-	bind_evtchn_to_cpu(evtchn, 0);
-	evtchn_to_irq[evtchn] = -1;
+	xen_evtchn_close(evtchn);
+	set_evtchn_to_irq(evtchn, -1);
 	info->evtchn = 0;
 }
 
@@ -520,7 +592,6 @@ EXPORT_SYMBOL_GPL(xen_irq_from_gsi);
 
 static void __unbind_from_irq(unsigned int irq)
 {
-	struct evtchn_close close;
 	int evtchn = evtchn_from_irq(irq);
 	struct irq_info *info = irq_get_handler_data(irq);
 
@@ -531,9 +602,7 @@ static void __unbind_from_irq(unsigned int irq)
 	}
 
 	if (VALID_EVTCHN(evtchn)) {
-		close.port = evtchn;
-		if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
-			BUG();
+		xen_evtchn_close(evtchn);
 
 		switch (type_from_irq(irq)) {
 		case IRQT_VIRQ:
@@ -548,10 +617,7 @@ static void __unbind_from_irq(unsigned int irq)
 			break;
 		}
 
-		/* Closed ports are implicitly re-bound to VCPU0. */
-		bind_evtchn_to_cpu(evtchn, 0);
-
-		evtchn_to_irq[evtchn] = -1;
+		set_evtchn_to_irq(evtchn, -1);
 	}
 
 	BUG_ON(info_for_irq(irq)->type == IRQT_UNBOUND);
@@ -755,9 +821,12 @@ int bind_evtchn_to_irq(unsigned int evtchn)
 	int irq;
 	int ret;
 
+	if (evtchn >= xen_evtchn_max_channels())
+		return -ENOMEM;
+
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = evtchn_to_irq[evtchn];
+	irq = get_evtchn_to_irq(evtchn);
 
 	if (irq == -1) {
 		irq = xen_allocate_irq_dynamic();
@@ -847,7 +916,7 @@ static int find_virq(unsigned int virq, unsigned int cpu)
 	int port, rc = -ENOENT;
 
 	memset(&status, 0, sizeof(status));
-	for (port = 0; port <= NR_EVENT_CHANNELS; port++) {
+	for (port = 0; port < xen_evtchn_max_channels(); port++) {
 		status.dom = DOMID_SELF;
 		status.port = port;
 		rc = HYPERVISOR_event_channel_op(EVTCHNOP_status, &status);
@@ -1017,7 +1086,7 @@ EXPORT_SYMBOL_GPL(unbind_from_irqhandler);
 
 int evtchn_make_refcounted(unsigned int evtchn)
 {
-	int irq = evtchn_to_irq[evtchn];
+	int irq = get_evtchn_to_irq(evtchn);
 	struct irq_info *info;
 
 	if (irq == -1)
@@ -1042,12 +1111,12 @@ int evtchn_get(unsigned int evtchn)
 	struct irq_info *info;
 	int err = -ENOENT;
 
-	if (evtchn >= NR_EVENT_CHANNELS)
+	if (evtchn >= xen_evtchn_max_channels())
 		return -EINVAL;
 
 	mutex_lock(&irq_mapping_update_lock);
 
-	irq = evtchn_to_irq[evtchn];
+	irq = get_evtchn_to_irq(evtchn);
 	if (irq == -1)
 		goto done;
 
@@ -1071,7 +1140,7 @@ EXPORT_SYMBOL_GPL(evtchn_get);
 
 void evtchn_put(unsigned int evtchn)
 {
-	int irq = evtchn_to_irq[evtchn];
+	int irq = get_evtchn_to_irq(evtchn);
 	if (WARN_ON(irq == -1))
 		return;
 	unbind_from_irq(irq);
@@ -1158,7 +1227,7 @@ void rebind_evtchn_irq(int evtchn, int irq)
 	mutex_lock(&irq_mapping_update_lock);
 
 	/* After resume the irq<->evtchn mappings are all cleared out */
-	BUG_ON(evtchn_to_irq[evtchn] != -1);
+	BUG_ON(get_evtchn_to_irq(evtchn) != -1);
 	/* Expect irq to have been bound before,
 	   so there should be a proper type */
 	BUG_ON(info->type == IRQT_UNBOUND);
@@ -1443,15 +1512,14 @@ void xen_irq_resume(void)
 	struct irq_info *info;
 
 	/* New event-channel space is not 'live' yet. */
-	for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
+	for (evtchn = 0; evtchn < xen_evtchn_nr_channels(); evtchn++)
 		mask_evtchn(evtchn);
 
 	/* No IRQ <-> event-channel mappings. */
 	list_for_each_entry(info, &xen_irq_list_head, list)
 		info->evtchn = 0; /* zap event-channel binding */
 
-	for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
-		evtchn_to_irq[evtchn] = -1;
+	clear_evtchn_to_irq_all();
 
 	for_each_possible_cpu(cpu) {
 		restore_cpu_virqs(cpu);
@@ -1548,14 +1616,12 @@ void __init xen_init_IRQ(void)
 
 	xen_evtchn_init_nlevel();
 
-	evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq),
-				    GFP_KERNEL);
+	evtchn_to_irq = kcalloc(EVTCHN_ROW(xen_evtchn_max_channels()),
+				sizeof(*evtchn_to_irq), GFP_KERNEL);
 	BUG_ON(!evtchn_to_irq);
-	for (i = 0; i < NR_EVENT_CHANNELS; i++)
-		evtchn_to_irq[i] = -1;
 
 	/* No event channels are 'live' right now. */
-	for (i = 0; i < NR_EVENT_CHANNELS; i++)
+	for (i = 0; i < xen_evtchn_nr_channels(); i++)
 		mask_evtchn(i);
 
 	pirq_needs_eoi = pirq_needs_eoi_flag;
drivers/xen/events/events_internal.h +16 -2
index 3eb573a..ecdcc6d 100644
@@ -35,7 +35,7 @@ struct irq_info {
 	int refcnt;
 	enum xen_irq_type type;	/* type */
 	unsigned irq;
-	unsigned short evtchn;	/* event channel */
+	unsigned int evtchn;	/* event channel */
 	unsigned short cpu;	/* cpu bound */
 
 	union {
@@ -55,6 +55,9 @@ struct irq_info {
 #define PIRQ_SHAREABLE	(1 << 1)
 
 struct evtchn_ops {
+	unsigned (*max_channels)(void);
+	unsigned (*nr_channels)(void);
+
 	int (*setup)(struct irq_info *info);
 	void (*bind_to_cpu)(struct irq_info *info, unsigned cpu);
 
@@ -70,12 +73,23 @@ struct evtchn_ops {
 
 extern const struct evtchn_ops *evtchn_ops;
 
-extern int *evtchn_to_irq;
+extern int **evtchn_to_irq;
+int get_evtchn_to_irq(unsigned int evtchn);
 
 struct irq_info *info_for_irq(unsigned irq);
 unsigned cpu_from_irq(unsigned irq);
 unsigned cpu_from_evtchn(unsigned int evtchn);
 
+static inline unsigned xen_evtchn_max_channels(void)
+{
+	return evtchn_ops->max_channels();
+}
+
+static inline unsigned xen_evtchn_nr_channels(void)
+{
+	return evtchn_ops->nr_channels();
+}
+
 /*
  * Do any ABI specific setup for a bound event channel before it can
  * be unmasked and used.
drivers/xen/events/n-level.c +9 -2
index 6e2804f..c4f6a06 100644
@@ -39,6 +39,11 @@
 static DEFINE_PER_CPU(xen_ulong_t [NR_EVENT_CHANNELS/BITS_PER_EVTCHN_WORD],
 		      cpu_evtchn_mask);
 
+static unsigned nlevel_max_channels(void)
+{
+	return NR_EVENT_CHANNELS;
+}
+
 static void nlevel_bind_to_cpu(struct irq_info *info, unsigned cpu)
 {
 	clear_bit(info->evtchn, BM(per_cpu(cpu_evtchn_mask, info->cpu)));
@@ -212,7 +217,7 @@ static void nlevel_handle_events(unsigned cpu)
 
 			/* Process port. */
 			port = (word_idx * BITS_PER_EVTCHN_WORD) + bit_idx;
-			irq = evtchn_to_irq[port];
+			irq = get_evtchn_to_irq(port);
 
 			if (irq != -1) {
 				desc = irq_to_desc(irq);
@@ -306,7 +311,7 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
 			int word_idx = i / BITS_PER_EVTCHN_WORD;
 			printk("  %d: event %d -> irq %d%s%s%s\n",
 			       cpu_from_evtchn(i), i,
-			       evtchn_to_irq[i],
+			       get_evtchn_to_irq(i),
 			       sync_test_bit(word_idx, BM(&v->evtchn_pending_sel))
 					     ? "" : " l2-clear",
 			       !sync_test_bit(i, BM(sh->evtchn_mask))
@@ -322,6 +327,8 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
 }
 
 static const struct evtchn_ops evtchn_ops_nlevel = {
+	.max_channels      = nlevel_max_channels,
+	.nr_channels       = nlevel_max_channels,
 	.bind_to_cpu       = nlevel_bind_to_cpu,
 	.clear_pending     = nlevel_clear_pending,
 	.set_pending       = nlevel_set_pending,
Signature · 1 line
1.7.2.5
#15 lore raw

PATCH v5 11/16 xen/events: add xen_evtchn_mask_all()

In reply to David Vrabel

From: David Vrabel <[email protected]>

---
 drivers/xen/events/events.c |   18 +++++++++++-------
 1 files changed, 11 insertions(+), 7 deletions(-)
drivers/xen/events/events.c +11 -7
index 734a957..3a154d9 100644
@@ -331,6 +331,14 @@ static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu)
 	info->cpu = cpu;
 }
 
+static void xen_evtchn_mask_all(void)
+{
+	unsigned evtchn;
+
+	for (evtchn = 0; evtchn < xen_evtchn_nr_channels(); evtchn++)
+		mask_evtchn(evtchn);
+}
+
 /**
  * notify_remote_via_irq - send event to remote end of event channel via irq
  * @irq: irq of event channel to send event to
@@ -1508,12 +1516,11 @@ EXPORT_SYMBOL_GPL(xen_test_irq_shared);
 
 void xen_irq_resume(void)
 {
-	unsigned int cpu, evtchn;
+	unsigned int cpu;
 	struct irq_info *info;
 
 	/* New event-channel space is not 'live' yet. */
-	for (evtchn = 0; evtchn < xen_evtchn_nr_channels(); evtchn++)
-		mask_evtchn(evtchn);
+	xen_evtchn_mask_all();
 
 	/* No IRQ <-> event-channel mappings. */
 	list_for_each_entry(info, &xen_irq_list_head, list)
@@ -1612,8 +1619,6 @@ void xen_callback_vector(void) {}
 
 void __init xen_init_IRQ(void)
 {
-	int i;
-
 	xen_evtchn_init_nlevel();
 
 	evtchn_to_irq = kcalloc(EVTCHN_ROW(xen_evtchn_max_channels()),
@@ -1621,8 +1626,7 @@ void __init xen_init_IRQ(void)
 	BUG_ON(!evtchn_to_irq);
 
 	/* No event channels are 'live' right now. */
-	for (i = 0; i < xen_evtchn_nr_channels(); i++)
-		mask_evtchn(i);
+	xen_evtchn_mask_all();
 
 	pirq_needs_eoi = pirq_needs_eoi_flag;
 
Signature · 1 line
1.7.2.5
#16 lore raw

PATCH v5 12/16 xen/evtchn: support more than 4096 ports

In reply to David Vrabel

From: David Vrabel <[email protected]>

Remove the check during unbind for NR_EVENT_CHANNELS as this limits support to less than 4096 ports.

---
 drivers/xen/evtchn.c |    4 ----
 1 files changed, 0 insertions(+), 4 deletions(-)
drivers/xen/evtchn.c +0 -4
index 8b3a69a..1b0fc44 100644
@@ -416,10 +416,6 @@ static long evtchn_ioctl(struct file *file,
 		if (copy_from_user(&unbind, uarg, sizeof(unbind)))
 			break;
 
-		rc = -EINVAL;
-		if (unbind.port >= NR_EVENT_CHANNELS)
-			break;
-
 		rc = -ENOTCONN;
 		evtchn = find_evtchn(u, unbind.port);
 		if (!evtchn)
Signature · 1 line
1.7.2.5
#17 lore raw

PATCH v5 13/16 xen/events: Add the hypervisor interface for the FIFO-based event channels

In reply to David Vrabel

From: David Vrabel <[email protected]>

Add the hypercall sub-ops and the structures for the shared data used in the FIFO-based event channel ABI.

The design document for this new ABI is available here:

http://xenbits.xen.org/people/dvrabel/event-channels-F.pdf

In summary, events are reported using a per-domain shared event array of event words. Each event word has PENDING, LINKED and MASKED bits and a LINK field for pointing to the next event in the event queue.

There are 16 event queues (with different priorities) per-VCPU.

Key advantages of this new ABI include:

- Support for over 100,000 events (2^17).
- 16 different event priorities.
- Improved fairness in event latency through the use of FIFOs.

---
 drivers/xen/events/n-level.c          |    8 ++--
 include/xen/interface/event_channel.h |   67 +++++++++++++++++++++++++++++++++
 include/xen/interface/xen.h           |    6 ---
 3 files changed, 71 insertions(+), 10 deletions(-)
drivers/xen/events/n-level.c +4 -4
index c4f6a06..5e92e9b 100644
@@ -36,12 +36,12 @@
 /* Find the first set bit in a evtchn mask */
 #define EVTCHN_FIRST_BIT(w) find_first_bit(BM(&(w)), BITS_PER_EVTCHN_WORD)
 
-static DEFINE_PER_CPU(xen_ulong_t [NR_EVENT_CHANNELS/BITS_PER_EVTCHN_WORD],
+static DEFINE_PER_CPU(xen_ulong_t [EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD],
 		      cpu_evtchn_mask);
 
 static unsigned nlevel_max_channels(void)
 {
-	return NR_EVENT_CHANNELS;
+	return EVTCHN_2L_NR_CHANNELS;
 }
 
 static void nlevel_bind_to_cpu(struct irq_info *info, unsigned cpu)
@@ -290,7 +290,7 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
 		       i % 8 == 0 ? "\n   " : " ");
 
 	printk("\nlocal cpu%d mask:\n   ", cpu);
-	for (i = (NR_EVENT_CHANNELS/BITS_PER_EVTCHN_WORD)-1; i >= 0; i--)
+	for (i = (EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD)-1; i >= 0; i--)
 		printk("%0*"PRI_xen_ulong"%s", (int)(sizeof(cpu_evtchn[0])*2),
 		       cpu_evtchn[i],
 		       i % 8 == 0 ? "\n   " : " ");
@@ -306,7 +306,7 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
 	}
 
 	printk("\npending list:\n");
-	for (i = 0; i < NR_EVENT_CHANNELS; i++) {
+	for (i = 0; i < EVTCHN_2L_NR_CHANNELS; i++) {
 		if (sync_test_bit(i, BM(sh->evtchn_pending))) {
 			int word_idx = i / BITS_PER_EVTCHN_WORD;
 			printk("  %d: event %d -> irq %d%s%s%s\n",
include/xen/interface/event_channel.h +67 -0

77 lines not on this page · raw message

include/xen/interface/xen.h +0 -6
index 53ec416..0cd5ca3 100644
@@ -281,12 +281,6 @@ struct multicall_entry {
 };
 DEFINE_GUEST_HANDLE_STRUCT(multicall_entry);
 
-/*
- * Event channel endpoints per domain:
- *  1024 if a long is 32 bits; 4096 if a long is 64 bits.
- */
-#define NR_EVENT_CHANNELS (sizeof(xen_ulong_t) * sizeof(xen_ulong_t) * 64)
-
 struct vcpu_time_info {
 	/*
 	 * Updates to the following values are preceded and followed
Signature · 1 line
1.7.2.5
#18 lore raw

PATCH v5 14/16 xen/events: allow event channel priority to be set

In reply to David Vrabel

From: David Vrabel <[email protected]>

Add xen_irq_set_priority() to set an event channels priority. This function will only work with event channel ABIs that support priority (i.e., the FIFO-based ABI).

---
 drivers/xen/events/events.c |   17 +++++++++++++++++
 include/xen/events.h        |    5 +++++
 2 files changed, 22 insertions(+), 0 deletions(-)
drivers/xen/events/events.c +17 -0
index 3a154d9..5551374 100644
@@ -1092,6 +1092,23 @@ void unbind_from_irqhandler(unsigned int irq, void *dev_id)
 }
 EXPORT_SYMBOL_GPL(unbind_from_irqhandler);
 
+/**
+ * xen_set_irq_priority() - set an event channel priority.
+ * @irq:irq bound to an event channel.
+ * @priority: priority between XEN_IRQ_PRIORITY_MAX and XEN_IRQ_PRIORITY_MIN.
+ */
+int xen_set_irq_priority(unsigned irq, unsigned priority)
+{
+	struct evtchn_set_priority set_priority;
+
+	set_priority.port = evtchn_from_irq(irq);
+	set_priority.priority = priority;
+
+	return HYPERVISOR_event_channel_op(EVTCHNOP_set_priority,
+					   &set_priority);
+}
+EXPORT_SYMBOL_GPL(xen_set_irq_priority);
+
 int evtchn_make_refcounted(unsigned int evtchn)
 {
 	int irq = get_evtchn_to_irq(evtchn);
include/xen/events.h +5 -0
index c9ea10e..d265d7e 100644
@@ -37,6 +37,11 @@ int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
  */
 void unbind_from_irqhandler(unsigned int irq, void *dev_id);
 
+#define XEN_IRQ_PRIORITY_MAX     EVTCHN_FIFO_PRIORITY_MAX
+#define XEN_IRQ_PRIORITY_DEFAULT EVTCHN_FIFO_PRIORITY_DEFAULT
+#define XEN_IRQ_PRIORITY_MIN     EVTCHN_FIFO_PRIORITY_MIN
+int xen_set_irq_priority(unsigned irq, unsigned priority);
+
 /*
  * Allow extra references to event channels exposed to userspace by evtchn
  */
Signature · 1 line
1.7.2.5
#19 lore raw

PATCH v5 15/16 xen/x86: set VIRQ_TIMER priority to maximum

In reply to David Vrabel

From: David Vrabel <[email protected]>

Commit bee980d9e (xen/events: Handle VIRQ_TIMER before any other hardirq in event loop) effectively made the VIRQ_TIMER the highest priority event when using the 2-level ABI.

Set the VIRQ_TIMER priority to the highest so this behaviour is retained when using the FIFO-based ABI.

---
 arch/x86/xen/time.c |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)
arch/x86/xen/time.c +1 -0
index ee36589..10e11c1 100644
@@ -447,6 +447,7 @@ void xen_setup_timer(int cpu)
 				      IRQF_NOBALANCING|IRQF_TIMER|
 				      IRQF_FORCE_RESUME,
 				      name, NULL);
+	(void)xen_set_irq_priority(irq, XEN_IRQ_PRIORITY_MAX);
 
 	memcpy(evt, xen_clockevent, sizeof(*evt));
 
Signature · 1 line
1.7.2.5
#20 lore raw

PATCH v5 16/16 xen/events: use the FIFO-based ABI if available

In reply to David Vrabel

From: David Vrabel <[email protected]>

Implement all the event channel port ops for the FIFO-based ABI.

If the hypervisor supports the FIFO-based ABI, enable it by initializing the control block for the boot VCPU and subsequent VCPUs as they are brought up and on resume. The event array is expanded as required when event ports are setup.

---
 drivers/xen/events/Makefile          |    1 +
 drivers/xen/events/events.c          |    9 +-
 drivers/xen/events/events_internal.h |    8 +
 drivers/xen/events/fifo.c            |  408 ++++++++++++++++++++++++++++++++++
 4 files changed, 425 insertions(+), 1 deletions(-)
 create mode 100644 drivers/xen/events/fifo.c
drivers/xen/events/Makefile +1 -0
index aea331e..74644d0 100644
@@ -1,2 +1,3 @@
 obj-y += events.o
+obj-y += fifo.o
 obj-y += n-level.o
drivers/xen/events/events.c +8 -1
index 5551374..5a5ac6c 100644
@@ -1538,6 +1538,7 @@ void xen_irq_resume(void)
 
 	/* New event-channel space is not 'live' yet. */
 	xen_evtchn_mask_all();
+	xen_evtchn_resume();
 
 	/* No IRQ <-> event-channel mappings. */
 	list_for_each_entry(info, &xen_irq_list_head, list)
@@ -1636,7 +1637,13 @@ void xen_callback_vector(void) {}
 
 void __init xen_init_IRQ(void)
 {
-	xen_evtchn_init_nlevel();
+	int ret;
+
+	ret = xen_evtchn_init_fifo();
+	if (ret < 0) {
+		printk(KERN_INFO "xen: falling back to n-level event channels");
+		xen_evtchn_init_nlevel();
+	}
 
 	evtchn_to_irq = kcalloc(EVTCHN_ROW(xen_evtchn_max_channels()),
 				sizeof(*evtchn_to_irq), GFP_KERNEL);
drivers/xen/events/events_internal.h +8 -0
index ecdcc6d..dcd1b47 100644
@@ -69,6 +69,7 @@ struct evtchn_ops {
 	void (*unmask)(unsigned port);
 
 	void (*handle_events)(unsigned cpu);
+	void (*resume)(void);
 };
 
 extern const struct evtchn_ops *evtchn_ops;
@@ -142,6 +143,13 @@ static inline void xen_evtchn_handle_events(unsigned cpu)
 	return evtchn_ops->handle_events(cpu);
 }
 
+static inline void xen_evtchn_resume(void)
+{
+	if (evtchn_ops->resume)
+		evtchn_ops->resume();
+}
+
 void xen_evtchn_init_nlevel(void);
+int xen_evtchn_init_fifo(void);
 
 #endif /* #ifndef __EVENTS_INTERNAL_H__ */
drivers/xen/events/fifo.c new file +408 -0

408 lines not on this page · raw message

Signature · 1 line
1.7.2.5