All of lore.kernel.org
 help / color / mirror / Atom feed
From: Feng Wu <feng.wu@intel.com>
To: pbonzini@redhat.com, rkrcmar@redhat.com
Cc: linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
	Feng Wu <feng.wu@intel.com>
Subject: [PATCH v3 2/4] KVM: x86: Use vector-hashing to deliver lowest-priority interrupts
Date: Wed, 20 Jan 2016 09:42:55 +0800	[thread overview]
Message-ID: <1453254177-103002-3-git-send-email-feng.wu@intel.com> (raw)
In-Reply-To: <1453254177-103002-1-git-send-email-feng.wu@intel.com>

Use vector-hashing to deliver lowest-priority interrupts, As an
example, modern Intel CPUs in server platform use this method to
handle lowest-priority interrupts.

Signed-off-by: Feng Wu <feng.wu@intel.com>
---
v3:
- Fix a bug for sparse topologies, in that case, vcpu_id is not equal
to the return value got by kvm_get_vcpu().
- Remove unnecessary check in fast irq delivery patch.
- print a error message only once for each guest when we find hardware
  disabled LAPIC during interrupt injection.

 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/irq_comm.c         | 27 +++++++++++++++++----
 arch/x86/kvm/lapic.c            | 52 ++++++++++++++++++++++++++++++++++++++---
 arch/x86/kvm/lapic.h            |  2 ++
 arch/x86/kvm/x86.c              |  9 +++++++
 arch/x86/kvm/x86.h              |  1 +
 6 files changed, 85 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 44adbb8..5054810 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -754,6 +754,8 @@ struct kvm_arch {
 
 	bool irqchip_split;
 	u8 nr_reserved_ioapic_pins;
+
+	int disabled_lapic_found;
 };
 
 struct kvm_vm_stat {
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 8fc89ef..062e907 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -34,6 +34,7 @@
 #include "lapic.h"
 
 #include "hyperv.h"
+#include "x86.h"
 
 static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
 			   struct kvm *kvm, int irq_source_id, int level,
@@ -55,8 +56,10 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
 int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 		struct kvm_lapic_irq *irq, unsigned long *dest_map)
 {
-	int i, r = -1;
+	int i, r = -1, idx = 0;
 	struct kvm_vcpu *vcpu, *lowest = NULL;
+	unsigned long dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)];
+	unsigned int dest_vcpus = 0;
 
 	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
 			kvm_lowest_prio_delivery(irq)) {
@@ -67,6 +70,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map))
 		return r;
 
+	memset(dest_vcpu_bitmap, 0, sizeof(dest_vcpu_bitmap));
+
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		if (!kvm_apic_present(vcpu))
 			continue;
@@ -80,13 +85,25 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 				r = 0;
 			r += kvm_apic_set_irq(vcpu, irq, dest_map);
 		} else if (kvm_lapic_enabled(vcpu)) {
-			if (!lowest)
-				lowest = vcpu;
-			else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
-				lowest = vcpu;
+			if (!kvm_vector_hashing_enabled()) {
+				if (!lowest)
+					lowest = vcpu;
+				else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
+					lowest = vcpu;
+			} else {
+				__set_bit(i, dest_vcpu_bitmap);
+				dest_vcpus++;
+			}
 		}
 	}
 
+	if (dest_vcpus != 0) {
+		idx = kvm_vector_2_index(irq->vector, dest_vcpus,
+					 dest_vcpu_bitmap, KVM_MAX_VCPUS);
+
+		lowest = kvm_get_vcpu(kvm, idx - 1);
+	}
+
 	if (lowest)
 		r = kvm_apic_set_irq(lowest, irq, dest_map);
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 36591fa..e1a449da 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -675,6 +675,22 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 	}
 }
 
+int kvm_vector_2_index(u32 vector, u32 dest_vcpus,
+		       const unsigned long *bitmap, u32 bitmap_size)
+{
+	u32 mod;
+	int i, idx = 0;
+
+	mod = vector % dest_vcpus;
+
+	for (i = 0; i <= mod; i++) {
+		idx = find_next_bit(bitmap, bitmap_size, idx) + 1;
+		BUG_ON(idx > bitmap_size);
+	}
+
+	return idx;
+}
+
 bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 		struct kvm_lapic_irq *irq, int *r, unsigned long *dest_map)
 {
@@ -727,21 +743,51 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 
 		dst = map->logical_map[cid];
 
-		if (kvm_lowest_prio_delivery(irq)) {
+		if (!kvm_lowest_prio_delivery(irq))
+			goto set_irq;
+
+		if (!kvm_vector_hashing_enabled()) {
 			int l = -1;
 			for_each_set_bit(i, &bitmap, 16) {
 				if (!dst[i])
 					continue;
 				if (l < 0)
 					l = i;
-				else if (kvm_apic_compare_prio(dst[i]->vcpu, dst[l]->vcpu) < 0)
+				else if (kvm_apic_compare_prio(dst[i]->vcpu,
+							dst[l]->vcpu) < 0)
 					l = i;
 			}
-
 			bitmap = (l >= 0) ? 1 << l : 0;
+		} else {
+			int idx = 0;
+			unsigned int dest_vcpus = 0;
+
+			dest_vcpus = hweight16(bitmap);
+			if (dest_vcpus == 0)
+				goto out;
+
+			idx = kvm_vector_2_index(irq->vector,
+				dest_vcpus, &bitmap, 16);
+
+			/*
+			 * We may find a hardware disabled LAPIC here, if that
+			 * is the case, print out a error message once for each
+			 * guest and return.
+			 */
+			if (!dst[idx-1] &&
+				(kvm->arch.disabled_lapic_found == 0)) {
+				kvm->arch.disabled_lapic_found = 1;
+				printk(KERN_ERR
+					"Disabled LAPIC found during irq injection\n");
+				goto out;
+			}
+
+			bitmap = 0;
+			__set_bit(idx-1, &bitmap);
 		}
 	}
 
+set_irq:
 	for_each_set_bit(i, &bitmap, 16) {
 		if (!dst[i])
 			continue;
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 41bdb35..d864601 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -175,4 +175,6 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu);
 
 bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
 			struct kvm_vcpu **dest_vcpu);
+int kvm_vector_2_index(u32 vector, u32 dest_vcpus,
+		       const unsigned long *bitmap, u32 bitmap_size);
 #endif
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4244c2b..47daf77 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -123,6 +123,9 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
 unsigned int __read_mostly lapic_timer_advance_ns = 0;
 module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
 
+bool __read_mostly enable_vector_hashing = 1;
+module_param(enable_vector_hashing, bool, S_IRUGO);
+
 static bool __read_mostly backwards_tsc_observed = false;
 
 #define KVM_NR_SHARED_MSRS 16
@@ -8370,6 +8373,12 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
 	return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set);
 }
 
+bool kvm_vector_hashing_enabled(void)
+{
+	return enable_vector_hashing;
+}
+EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index f2afa5f..04bd0f9 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -179,6 +179,7 @@ int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data);
 int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
 bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
 					  int page_num);
+bool kvm_vector_hashing_enabled(void);
 
 #define KVM_SUPPORTED_XCR0     (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \
 				| XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \
-- 
2.1.0

  parent reply	other threads:[~2016-01-20  2:02 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-01-20  1:42 [PATCH v3 0/4] VT-d posted-interrupts follow ups Feng Wu
2016-01-20  1:42 ` [PATCH v3 1/4] KVM: Recover IRTE to remapped mode if the interrupt is not single-destination Feng Wu
2016-01-21  3:05   ` Yang Zhang
2016-01-21  3:14     ` Wu, Feng
2016-01-21  3:34       ` Yang Zhang
2016-01-21  4:42         ` Wu, Feng
2016-01-21  4:54           ` Tian, Kevin
2016-01-21  4:59           ` Yang Zhang
2016-01-21  5:07             ` Wu, Feng
2016-01-21  5:35               ` Yang Zhang
2016-01-21  5:41                 ` Wu, Feng
2016-01-21  5:44                   ` Yang Zhang
2016-01-21 16:35                     ` rkrcmar
2016-01-22  2:03                       ` Yang Zhang
2016-01-22 13:31                         ` rkrcmar
2016-01-25  1:49                           ` Yang Zhang
2016-01-25 13:59                             ` rkrcmar
2016-01-26  1:44                               ` Yang Zhang
2016-01-26 18:22                                 ` rkrcmar
2016-01-27  2:07                                   ` Yang Zhang
2016-01-27 15:05                                     ` rkrcmar
2016-01-21 16:19   ` Radim Krčmář
2016-01-22  1:49     ` Wu, Feng
2016-01-22 13:05       ` Radim Krcmár
2016-01-25 12:22         ` Paolo Bonzini
2016-01-25 12:26           ` Wu, Feng
2016-01-25 12:38             ` Paolo Bonzini
2016-01-25 12:48               ` Wu, Feng
2016-01-25 14:05             ` Radim Krcmár
2016-01-26  0:57               ` Wu, Feng
2016-01-20  1:42 ` Feng Wu [this message]
2016-01-21  5:23   ` [PATCH v3 2/4] KVM: x86: Use vector-hashing to deliver lowest-priority interrupts Yang Zhang
2016-01-21  5:33     ` Wu, Feng
2016-01-21  5:42       ` Yang Zhang
2016-01-21  5:46         ` Wu, Feng
2016-01-21  5:57           ` Yang Zhang
2016-01-21  6:02             ` Wu, Feng
2016-01-21  6:07               ` Yang Zhang
2016-01-21 17:21       ` rkrcmar
2016-01-22  2:01         ` Wu, Feng
2016-01-22  4:00         ` Yang Zhang
2016-01-22 13:49           ` rkrcmar
2016-01-21 19:49   ` Radim Krčmář
2016-01-22  5:12     ` Wu, Feng
2016-01-22 14:01       ` Radim Krcmár
2016-01-25 12:25         ` Paolo Bonzini
2016-01-25 15:20           ` Radim Krcmár
2016-01-25 16:14             ` Paolo Bonzini
2016-01-26  1:10               ` Wu, Feng
2016-01-20  1:42 ` [PATCH v3 3/4] KVM: x86: Add lowest-priority support for vt-d posted-interrupts Feng Wu
2016-01-21 20:16   ` Radim Krčmář
2016-01-22  5:12     ` Wu, Feng
2016-01-22 14:07       ` Radim Krcmár
2016-01-20  1:42 ` [PATCH v3 4/4] KVM/VMX: Add host irq information in trace event when updating IRTE for posted interrupts Feng Wu
2016-01-21 20:19   ` Radim Krčmář

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1453254177-103002-3-git-send-email-feng.wu@intel.com \
    --to=feng.wu@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=rkrcmar@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.