[PATCH 4/4] kvm-s390: streamline memslot handling - v6

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Christian Ehrhardt <ehrhardt@xxxxxxxxxxxxxxxxxx>

*updates in v6*
- ensure the wait_on_bit waiter is notified
- move the reset of requests to kvm_vcpu_release to drop them early

*updates in v5*
- ensure dropping vcpu all requests while freeing a vcpu

*updates in v4*
- kickout only scheduled vcpus (its superfluous and wait might hang forever on
  not running vcpus)

*updates in v3*
- handling the mmu reload vcpu request can now be handled inside the sigp
  handling avoiding an addtional exit
- kvm_arch_set_memory_region now waits for kicked vcpu's to consume the request
  bit it set to ensure that after the kvm_arch_set_memory_region call all vcpus
  use the updated memory information

*updates in v2*
- added optimization to skip (addtional) kickout of vcpu's that had the request
  already set.

This patch relocates the variables kvm-s390 uses to track guest mem addr/size.
As discussed dropping the variables at struct kvm_arch level allows to use the
common vcpu->request based mechanism to reload guest memory if e.g. changes
via set_memory_region.
The kick mechanism introduced in this series is used to ensure running vcpus
leave guest state to catch the update.


Signed-off-by: Christian Ehrhardt <ehrhardt@xxxxxxxxxxxxxxxxxx>
---

[diffstat]
 arch/s390/include/asm/kvm_host.h |    4 --
 arch/s390/kvm/gaccess.h          |   23 ++++++++-------
 arch/s390/kvm/intercept.c        |    6 ++--
 arch/s390/kvm/kvm-s390.c         |   57 ++++++++++++++++-----------------------
 arch/s390/kvm/kvm-s390.h         |   36 +++++++++++++++++++++++-
 arch/s390/kvm/sigp.c             |    4 +-
 virt/kvm/kvm_main.c              |    4 ++
 7 files changed, 81 insertions(+), 53 deletions(-)

[diff]
Index: kvm/arch/s390/kvm/gaccess.h
===================================================================
--- kvm.orig/arch/s390/kvm/gaccess.h
+++ kvm/arch/s390/kvm/gaccess.h
@@ -1,7 +1,7 @@
 /*
  * gaccess.h -  access guest memory
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -16,13 +16,14 @@
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
 #include <asm/uaccess.h>
+#include "kvm-s390.h"
 
 static inline void __user *__guestaddr_to_user(struct kvm_vcpu *vcpu,
 					       unsigned long guestaddr)
 {
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if (guestaddr < 2 * PAGE_SIZE)
 		guestaddr += prefix;
@@ -158,8 +159,8 @@ static inline int copy_to_guest(struct k
 				const void *from, unsigned long n)
 {
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if ((guestdest < 2 * PAGE_SIZE) && (guestdest + n > 2 * PAGE_SIZE))
 		goto slowpath;
@@ -209,8 +210,8 @@ static inline int copy_from_guest(struct
 				  unsigned long guestsrc, unsigned long n)
 {
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE))
 		goto slowpath;
@@ -244,8 +245,8 @@ static inline int copy_to_guest_absolute
 					 unsigned long guestdest,
 					 const void *from, unsigned long n)
 {
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if (guestdest + n > memsize)
 		return -EFAULT;
@@ -262,8 +263,8 @@ static inline int copy_from_guest_absolu
 					   unsigned long guestsrc,
 					   unsigned long n)
 {
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if (guestsrc + n > memsize)
 		return -EFAULT;
Index: kvm/arch/s390/kvm/intercept.c
===================================================================
--- kvm.orig/arch/s390/kvm/intercept.c
+++ kvm/arch/s390/kvm/intercept.c
@@ -1,7 +1,7 @@
 /*
  * intercept.c - in-kernel handling for sie intercepts
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -166,9 +166,9 @@ static int handle_validity(struct kvm_vc
 
 	vcpu->stat.exit_validity++;
 	if ((viwhy == 0x37) && (vcpu->arch.sie_block->prefix
-		<= vcpu->kvm->arch.guest_memsize - 2*PAGE_SIZE)){
+		<= kvm_s390_vcpu_get_memsize(vcpu) - 2*PAGE_SIZE)) {
 		rc = fault_in_pages_writeable((char __user *)
-			 vcpu->kvm->arch.guest_origin +
+			 vcpu->arch.sie_block->gmsor +
 			 vcpu->arch.sie_block->prefix,
 			 2*PAGE_SIZE);
 		if (rc)
Index: kvm/arch/s390/kvm/kvm-s390.c
===================================================================
--- kvm.orig/arch/s390/kvm/kvm-s390.c
+++ kvm/arch/s390/kvm/kvm-s390.c
@@ -1,7 +1,7 @@
 /*
  * s390host.c --  hosting zSeries kernel virtual machines
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -10,6 +10,7 @@
  *    Author(s): Carsten Otte <cotte@xxxxxxxxxx>
  *               Christian Borntraeger <borntraeger@xxxxxxxxxx>
  *               Heiko Carstens <heiko.carstens@xxxxxxxxxx>
+ *               Christian Ehrhardt <ehrhardt@xxxxxxxxxx>
  */
 
 #include <linux/compiler.h>
@@ -278,16 +279,10 @@ static void kvm_s390_vcpu_initial_reset(
 	vcpu->arch.sie_block->gbea = 1;
 }
 
-/* The current code can have up to 256 pages for virtio */
-#define VIRTIODESCSPACE (256ul * 4096ul)
-
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH);
-	vcpu->arch.sie_block->gmslm = vcpu->kvm->arch.guest_memsize +
-				      vcpu->kvm->arch.guest_origin +
-				      VIRTIODESCSPACE - 1ul;
-	vcpu->arch.sie_block->gmsor = vcpu->kvm->arch.guest_origin;
+	set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests);
 	vcpu->arch.sie_block->ecb   = 2;
 	vcpu->arch.sie_block->eca   = 0xC1002001U;
 	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
@@ -493,8 +488,9 @@ rerun_vcpu:
 	kvm_s390_handle_vcpu_requests(vcpu, VCPUREQUESTLVL_VCPURUN);
 
 	/* verify, that memory has been registered */
-	if (!vcpu->kvm->arch.guest_memsize) {
+	if (!vcpu->arch.sie_block->gmslm) {
 		vcpu_put(vcpu);
+		VCPU_EVENT(vcpu, 3, "%s", "no memory registered to run vcpu");
 		return -EINVAL;
 	}
 
@@ -677,6 +673,12 @@ long kvm_arch_vcpu_ioctl(struct file *fi
 	return -EINVAL;
 }
 
+static int wait_bit_schedule(void *word)
+{
+	schedule();
+	return 0;
+}
+
 /* Section: memory related */
 int kvm_arch_set_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
@@ -684,6 +686,7 @@ int kvm_arch_set_memory_region(struct kv
 				int user_alloc)
 {
 	int i;
+	struct kvm_vcpu *vcpu;
 
 	/* A few sanity checks. We can have exactly one memory slot which has
 	   to start at guest virtual zero and which has to be located at a
@@ -692,7 +695,7 @@ int kvm_arch_set_memory_region(struct kv
 	   vmas. It is okay to mmap() and munmap() stuff in this slot after
 	   doing this call at any time */
 
-	if (mem->slot || kvm->arch.guest_memsize)
+	if (mem->slot)
 		return -EINVAL;
 
 	if (mem->guest_phys_addr)
@@ -707,36 +710,24 @@ int kvm_arch_set_memory_region(struct kv
 	if (!user_alloc)
 		return -EINVAL;
 
-	/* lock all vcpus */
+	/* request update of sie control block for all available vcpus */
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		if (!kvm->vcpus[i])
+		vcpu = kvm->vcpus[i];
+		if (!vcpu)
+			continue;
+
+		if (!test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
 			continue;
-		if (!mutex_trylock(&kvm->vcpus[i]->mutex))
-			goto fail_out;
-	}
 
-	kvm->arch.guest_origin = mem->userspace_addr;
-	kvm->arch.guest_memsize = mem->memory_size;
+		if (vcpu->cpu == -1)
+			continue;
 
-	/* update sie control blocks, and unlock all vcpus */
-	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		if (kvm->vcpus[i]) {
-			kvm->vcpus[i]->arch.sie_block->gmsor =
-				kvm->arch.guest_origin;
-			kvm->vcpus[i]->arch.sie_block->gmslm =
-				kvm->arch.guest_memsize +
-				kvm->arch.guest_origin +
-				VIRTIODESCSPACE - 1ul;
-			mutex_unlock(&kvm->vcpus[i]->mutex);
-		}
+		kvm_s390_inject_sigp_stop(vcpu, ACTION_VCPUREQUEST_ON_STOP);
+		wait_on_bit(&vcpu->requests, KVM_REQ_MMU_RELOAD,
+			    wait_bit_schedule, TASK_UNINTERRUPTIBLE);
 	}
 
 	return 0;
-
-fail_out:
-	for (; i >= 0; i--)
-		mutex_unlock(&kvm->vcpus[i]->mutex);
-	return -EINVAL;
 }
 
 void kvm_arch_flush_shadow(struct kvm *kvm)
Index: kvm/arch/s390/kvm/kvm-s390.h
===================================================================
--- kvm.orig/arch/s390/kvm/kvm-s390.h
+++ kvm/arch/s390/kvm/kvm-s390.h
@@ -1,7 +1,7 @@
 /*
  * kvm_s390.h -  definition for kvm on s390
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -9,6 +9,7 @@
  *
  *    Author(s): Carsten Otte <cotte@xxxxxxxxxx>
  *               Christian Borntraeger <borntraeger@xxxxxxxxxx>
+ *               Christian Ehrhardt <ehrhardt@xxxxxxxxxx>
  */
 
 #ifndef ARCH_S390_KVM_S390_H
@@ -18,6 +19,9 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 
+/* The current code can have up to 256 pages for virtio */
+#define VIRTIODESCSPACE (256ul * 4096ul)
+
 typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
 
 /* negativ values are error codes, positive values for internal conditions */
@@ -54,6 +58,29 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
 
+static inline int kvm_s390_vcpu_get_memsize(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.sie_block->gmslm
+		- vcpu->arch.sie_block->gmsor
+		- VIRTIODESCSPACE + 1ul;
+}
+
+static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu)
+{
+	struct kvm_memory_slot *mem;
+
+	down_read(&vcpu->kvm->slots_lock);
+	mem = &vcpu->kvm->memslots[0];
+
+	vcpu->arch.sie_block->gmsor = mem->userspace_addr;
+	vcpu->arch.sie_block->gmslm =
+		mem->userspace_addr +
+		(mem->npages << PAGE_SHIFT) +
+		VIRTIODESCSPACE - 1ul;
+
+	up_read(&vcpu->kvm->slots_lock);
+}
+
 /* interception levels from which handle vcpu requests can be called */
 #define VCPUREQUESTLVL_SIGP		1
 #define VCPUREQUESTLVL_VCPURUN		2
@@ -65,6 +92,13 @@ static inline unsigned long kvm_s390_han
 	if (!vcpu->requests)
 		return 0;
 
+	/* requests that can be handled at all levels */
+	if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) {
+		smp_mb__after_clear_bit();
+		wake_up_bit(vcpu->requests, KVM_REQ_MMU_RELOAD);
+		kvm_s390_vcpu_set_mem(vcpu);
+	}
+
 	return vcpu->requests;
 }
 
Index: kvm/arch/s390/include/asm/kvm_host.h
===================================================================
--- kvm.orig/arch/s390/include/asm/kvm_host.h
+++ kvm/arch/s390/include/asm/kvm_host.h
@@ -1,7 +1,7 @@
 /*
  * asm-s390/kvm_host.h - definition for kernel virtual machines on s390
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -226,8 +226,6 @@ struct kvm_vm_stat {
 };
 
 struct kvm_arch{
-	unsigned long guest_origin;
-	unsigned long guest_memsize;
 	struct sca_block *sca;
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;
Index: kvm/arch/s390/kvm/sigp.c
===================================================================
--- kvm.orig/arch/s390/kvm/sigp.c
+++ kvm/arch/s390/kvm/sigp.c
@@ -202,9 +202,9 @@ static int __sigp_set_prefix(struct kvm_
 	/* make sure that the new value is valid memory */
 	address = address & 0x7fffe000u;
 	if ((copy_from_guest(vcpu, &tmp,
-		(u64) (address + vcpu->kvm->arch.guest_origin) , 1)) ||
+		(u64) (address + vcpu->arch.sie_block->gmsor) , 1)) ||
 	   (copy_from_guest(vcpu, &tmp, (u64) (address +
-			vcpu->kvm->arch.guest_origin + PAGE_SIZE), 1))) {
+			vcpu->arch.sie_block->gmsor + PAGE_SIZE), 1))) {
 		*reg |= SIGP_STAT_INVALID_PARAMETER;
 		return 1; /* invalid parameter */
 	}
Index: kvm/virt/kvm/kvm_main.c
===================================================================
--- kvm.orig/virt/kvm/kvm_main.c
+++ kvm/virt/kvm/kvm_main.c
@@ -1686,6 +1686,10 @@ static int kvm_vcpu_release(struct inode
 {
 	struct kvm_vcpu *vcpu = filp->private_data;
 
+	clear_bit(vcpu->requests, KVM_REQ_MMU_RELOAD);
+	smp_mb__after_clear_bit();
+	wake_up_bit(vcpu->requests, KVM_REQ_MMU_RELOAD);
+
 	kvm_put_kvm(vcpu->kvm);
 	return 0;
 }
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[Index of Archives]     [KVM ARM]     [KVM ia64]     [KVM ppc]     [Virtualization Tools]     [Spice Development]     [Libvirt]     [Libvirt Users]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite Questions]     [Linux Kernel]     [Linux SCSI]     [XFree86]
  Powered by Linux