From c395fe1d8e49a5aa03504fcacfb7c95b5a4c6e04 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Thu, 23 May 2019 16:35:07 +1000 Subject: KVM: PPC: Book3S HV: Avoid touching arch.mmu_ready in XIVE release functions Currently, kvmppc_xive_release() and kvmppc_xive_native_release() clear kvm->arch.mmu_ready and call kick_all_cpus_sync() as a way of ensuring that no vcpus are executing in the guest. However, future patches will change the mutex associated with kvm->arch.mmu_ready to a new mutex that nests inside the vcpu mutexes, making it difficult to continue to use this method. In fact, taking the vcpu mutex for a vcpu excludes execution of that vcpu, and we already take the vcpu mutex around the call to kvmppc_xive_[native_]cleanup_vcpu(). Once the cleanup function is done and we release the vcpu mutex, the vcpu can execute once again, but because we have cleared vcpu->arch.xive_vcpu, vcpu->arch.irq_type, vcpu->arch.xive_esc_vaddr and vcpu->arch.xive_esc_raddr, that vcpu will not be going into XIVE code any more. Thus, once we have cleaned up all of the vcpus, we are safe to clean up the rest of the XIVE state, and we don't need to use kvm->arch.mmu_ready to hold off vcpu execution. Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_xive_native.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) (limited to 'arch/powerpc/kvm/book3s_xive_native.c') diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 6a8e698c4b6e..da31dd05fd72 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -973,21 +973,10 @@ static void kvmppc_xive_native_release(struct kvm_device *dev) struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; int i; - int was_ready; - - debugfs_remove(xive->dentry); pr_devel("Releasing xive native device\n"); /* - * Clearing mmu_ready temporarily while holding kvm->lock - * is a way of ensuring that no vcpus can enter the guest - * until we drop kvm->lock. Doing kick_all_cpus_sync() - * ensures that any vcpu executing inside the guest has - * exited the guest. Once kick_all_cpus_sync() has finished, - * we know that no vcpu can be executing the XIVE push or - * pull code or accessing the XIVE MMIO regions. - * * Since this is the device release function, we know that * userspace does not have any open fd or mmap referring to * the device. Therefore there can not be any of the @@ -996,9 +985,8 @@ static void kvmppc_xive_native_release(struct kvm_device *dev) * connect_vcpu and set/clr_mapped functions also cannot * be being executed. */ - was_ready = kvm->arch.mmu_ready; - kvm->arch.mmu_ready = 0; - kick_all_cpus_sync(); + + debugfs_remove(xive->dentry); /* * We should clean up the vCPU interrupt presenters first. @@ -1007,12 +995,22 @@ static void kvmppc_xive_native_release(struct kvm_device *dev) /* * Take vcpu->mutex to ensure that no one_reg get/set ioctl * (i.e. kvmppc_xive_native_[gs]et_vp) can be being done. + * Holding the vcpu->mutex also means that the vcpu cannot + * be executing the KVM_RUN ioctl, and therefore it cannot + * be executing the XIVE push or pull code or accessing + * the XIVE MMIO regions. */ mutex_lock(&vcpu->mutex); kvmppc_xive_native_cleanup_vcpu(vcpu); mutex_unlock(&vcpu->mutex); } + /* + * Now that we have cleared vcpu->arch.xive_vcpu, vcpu->arch.irq_type + * and vcpu->arch.xive_esc_[vr]addr on each vcpu, we are safe + * against xive code getting called during vcpu execution or + * set/get one_reg operations. + */ kvm->arch.xive = NULL; for (i = 0; i <= xive->max_sbid; i++) { @@ -1025,8 +1023,6 @@ static void kvmppc_xive_native_release(struct kvm_device *dev) if (xive->vp_base != XIVE_INVALID_VP) xive_native_free_vp_block(xive->vp_base); - kvm->arch.mmu_ready = was_ready; - /* * A reference of the kvmppc_xive pointer is now kept under * the xive_devices struct of the machine for reuse. It is -- cgit v1.2.3 From d47aacdb8e0bc03dcaa1a5630a3c633cdcd4cfa7 Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Mon, 20 May 2019 09:15:12 +0200 Subject: KVM: PPC: Book3S HV: XIVE: Clear file mapping when device is released MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Improve the release of the XIVE KVM device by clearing the file address_space, which is used to unmap the interrupt ESB pages when a device is passed-through. Suggested-by: Paul Mackerras Signed-off-by: Cédric Le Goater Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_xive_native.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/powerpc/kvm/book3s_xive_native.c') diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index da31dd05fd72..9cedd04e7a44 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -976,6 +976,14 @@ static void kvmppc_xive_native_release(struct kvm_device *dev) pr_devel("Releasing xive native device\n"); + /* + * Clear the KVM device file address_space which is used to + * unmap the ESB pages when a device is passed-through. + */ + mutex_lock(&xive->mapping_lock); + xive->mapping = NULL; + mutex_unlock(&xive->mapping_lock); + /* * Since this is the device release function, we know that * userspace does not have any open fd or mmap referring to -- cgit v1.2.3 From c468bc4e8468cb4b85ad61294ddd88efb2e47d8d Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Mon, 20 May 2019 09:15:13 +0200 Subject: KVM: PPC: Book3S HV: XIVE: Do not test the EQ flag validity when resetting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When a CPU is hot-unplugged, the EQ is deconfigured using a zero size and a zero address. In this case, there is no need to check the flag and queue size validity. Move the checks after the queue reset code section to fix CPU hot-unplug. Reported-by: Satheesh Rajendran Tested-by: Satheesh Rajendran Signed-off-by: Cédric Le Goater Reviewed-by: Greg Kurz Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_xive_native.c | 36 +++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) (limited to 'arch/powerpc/kvm/book3s_xive_native.c') diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 9cedd04e7a44..53b7159dc305 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -565,24 +565,6 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, __func__, server, priority, kvm_eq.flags, kvm_eq.qshift, kvm_eq.qaddr, kvm_eq.qtoggle, kvm_eq.qindex); - /* - * sPAPR specifies a "Unconditional Notify (n) flag" for the - * H_INT_SET_QUEUE_CONFIG hcall which forces notification - * without using the coalescing mechanisms provided by the - * XIVE END ESBs. This is required on KVM as notification - * using the END ESBs is not supported. - */ - if (kvm_eq.flags != KVM_XIVE_EQ_ALWAYS_NOTIFY) { - pr_err("invalid flags %d\n", kvm_eq.flags); - return -EINVAL; - } - - rc = xive_native_validate_queue_size(kvm_eq.qshift); - if (rc) { - pr_err("invalid queue size %d\n", kvm_eq.qshift); - return rc; - } - /* reset queue and disable queueing */ if (!kvm_eq.qshift) { q->guest_qaddr = 0; @@ -604,6 +586,24 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, return 0; } + /* + * sPAPR specifies a "Unconditional Notify (n) flag" for the + * H_INT_SET_QUEUE_CONFIG hcall which forces notification + * without using the coalescing mechanisms provided by the + * XIVE END ESBs. This is required on KVM as notification + * using the END ESBs is not supported. + */ + if (kvm_eq.flags != KVM_XIVE_EQ_ALWAYS_NOTIFY) { + pr_err("invalid flags %d\n", kvm_eq.flags); + return -EINVAL; + } + + rc = xive_native_validate_queue_size(kvm_eq.qshift); + if (rc) { + pr_err("invalid queue size %d\n", kvm_eq.qshift); + return rc; + } + if (kvm_eq.qaddr & ((1ull << kvm_eq.qshift) - 1)) { pr_err("queue page is not aligned %llx/%llx\n", kvm_eq.qaddr, 1ull << kvm_eq.qshift); -- cgit v1.2.3 From e717d0ae10041d18fa97da1e6bb4942b5eb9f77c Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Mon, 20 May 2019 09:15:14 +0200 Subject: KVM: PPC: Book3S HV: XIVE: Fix the enforced limit on the vCPU identifier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When a vCPU is connected to the KVM device, it is done using its vCPU identifier in the guest. Fix the enforced limit on the vCPU identifier by taking into account the SMT mode. Reported-by: Satheesh Rajendran Tested-by: Satheesh Rajendran Signed-off-by: Cédric Le Goater Reviewed-by: Greg Kurz Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_xive_native.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kvm/book3s_xive_native.c') diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 53b7159dc305..3caf64b96f7e 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -109,7 +109,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, return -EPERM; if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT) return -EBUSY; - if (server_num >= KVM_MAX_VCPUS) { + if (server_num >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) { pr_devel("Out of bounds !\n"); return -EINVAL; } -- cgit v1.2.3 From 7e10b9a6da619bcee243980d9c45112761a86e11 Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Fri, 24 May 2019 15:20:30 +0200 Subject: KVM: PPC: Book3S HV: XIVE: Introduce a new mutex for the XIVE device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The XICS-on-XIVE KVM device needs to allocate XIVE event queues when a priority is used by the OS. This is referred as EQ provisioning and it is done under the hood when : 1. a CPU is hot-plugged in the VM 2. the "set-xive" is called at VM startup 3. sources are restored at VM restore The kvm->lock mutex is used to protect the different XIVE structures being modified but in some contexts, kvm->lock is taken under the vcpu->mutex which is not permitted by the KVM locking rules. Introduce a new mutex 'lock' for the KVM devices for them to synchronize accesses to the XIVE device structures. Reviewed-by: Greg Kurz Signed-off-by: Cédric Le Goater Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_xive.c | 23 +++++++++++++---------- arch/powerpc/kvm/book3s_xive.h | 1 + arch/powerpc/kvm/book3s_xive_native.c | 15 ++++++++------- 3 files changed, 22 insertions(+), 17 deletions(-) (limited to 'arch/powerpc/kvm/book3s_xive_native.c') diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index f623451ec0a3..12c8a36dd980 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -271,14 +271,14 @@ static int xive_provision_queue(struct kvm_vcpu *vcpu, u8 prio) return rc; } -/* Called with kvm_lock held */ +/* Called with xive->lock held */ static int xive_check_provisioning(struct kvm *kvm, u8 prio) { struct kvmppc_xive *xive = kvm->arch.xive; struct kvm_vcpu *vcpu; int i, rc; - lockdep_assert_held(&kvm->lock); + lockdep_assert_held(&xive->lock); /* Already provisioned ? */ if (xive->qmap & (1 << prio)) @@ -621,9 +621,12 @@ int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server, irq, server, priority); /* First, check provisioning of queues */ - if (priority != MASKED) + if (priority != MASKED) { + mutex_lock(&xive->lock); rc = xive_check_provisioning(xive->kvm, xive_prio_from_guest(priority)); + mutex_unlock(&xive->lock); + } if (rc) { pr_devel(" provisioning failure %d !\n", rc); return rc; @@ -1199,7 +1202,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, return -ENOMEM; /* We need to synchronize with queue provisioning */ - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&xive->lock); vcpu->arch.xive_vcpu = xc; xc->xive = xive; xc->vcpu = vcpu; @@ -1283,7 +1286,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, xive_vm_esb_load(&xc->vp_ipi_data, XIVE_ESB_SET_PQ_00); bail: - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&xive->lock); if (r) { kvmppc_xive_cleanup_vcpu(vcpu); return r; @@ -1527,13 +1530,12 @@ static int xive_get_source(struct kvmppc_xive *xive, long irq, u64 addr) struct kvmppc_xive_src_block *kvmppc_xive_create_src_block( struct kvmppc_xive *xive, int irq) { - struct kvm *kvm = xive->kvm; struct kvmppc_xive_src_block *sb; int i, bid; bid = irq >> KVMPPC_XICS_ICS_SHIFT; - mutex_lock(&kvm->lock); + mutex_lock(&xive->lock); /* block already exists - somebody else got here first */ if (xive->src_blocks[bid]) @@ -1560,7 +1562,7 @@ struct kvmppc_xive_src_block *kvmppc_xive_create_src_block( xive->max_sbid = bid; out: - mutex_unlock(&kvm->lock); + mutex_unlock(&xive->lock); return xive->src_blocks[bid]; } @@ -1670,9 +1672,9 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr) /* If we have a priority target the interrupt */ if (act_prio != MASKED) { /* First, check provisioning of queues */ - mutex_lock(&xive->kvm->lock); + mutex_lock(&xive->lock); rc = xive_check_provisioning(xive->kvm, act_prio); - mutex_unlock(&xive->kvm->lock); + mutex_unlock(&xive->lock); /* Target interrupt */ if (rc == 0) @@ -1963,6 +1965,7 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) dev->private = xive; xive->dev = dev; xive->kvm = kvm; + mutex_init(&xive->lock); /* Already there ? */ if (kvm->arch.xive) diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index 426146332984..862c2c9650ae 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -141,6 +141,7 @@ struct kvmppc_xive { struct kvmppc_xive_ops *ops; struct address_space *mapping; struct mutex mapping_lock; + struct mutex lock; }; #define KVMPPC_XIVE_Q_COUNT 8 diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 3caf64b96f7e..fec3b85411ef 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -114,7 +114,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, return -EINVAL; } - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&xive->lock); if (kvmppc_xive_find_server(vcpu->kvm, server_num)) { pr_devel("Duplicate !\n"); @@ -159,7 +159,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, /* TODO: reset all queues to a clean state ? */ bail: - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&xive->lock); if (rc) kvmppc_xive_native_cleanup_vcpu(vcpu); @@ -772,7 +772,7 @@ static int kvmppc_xive_reset(struct kvmppc_xive *xive) pr_devel("%s\n", __func__); - mutex_lock(&kvm->lock); + mutex_lock(&xive->lock); kvm_for_each_vcpu(i, vcpu, kvm) { struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; @@ -810,7 +810,7 @@ static int kvmppc_xive_reset(struct kvmppc_xive *xive) } } - mutex_unlock(&kvm->lock); + mutex_unlock(&xive->lock); return 0; } @@ -878,7 +878,7 @@ static int kvmppc_xive_native_eq_sync(struct kvmppc_xive *xive) pr_devel("%s\n", __func__); - mutex_lock(&kvm->lock); + mutex_lock(&xive->lock); for (i = 0; i <= xive->max_sbid; i++) { struct kvmppc_xive_src_block *sb = xive->src_blocks[i]; @@ -892,7 +892,7 @@ static int kvmppc_xive_native_eq_sync(struct kvmppc_xive *xive) kvm_for_each_vcpu(i, vcpu, kvm) { kvmppc_xive_native_vcpu_eq_sync(vcpu); } - mutex_unlock(&kvm->lock); + mutex_unlock(&xive->lock); return 0; } @@ -965,7 +965,7 @@ static int kvmppc_xive_native_has_attr(struct kvm_device *dev, } /* - * Called when device fd is closed + * Called when device fd is closed. kvm->lock is held. */ static void kvmppc_xive_native_release(struct kvm_device *dev) { @@ -1064,6 +1064,7 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type) xive->kvm = kvm; kvm->arch.xive = xive; mutex_init(&xive->mapping_lock); + mutex_init(&xive->lock); /* * Allocate a bunch of VPs. KVM_MAX_VCPUS is a large value for -- cgit v1.2.3 From aedb5b19429c807331e8387bcb98cb5dc4c2a75e Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Tue, 28 May 2019 14:17:16 +0200 Subject: KVM: PPC: Book3S HV: XIVE: Take the srcu read lock when accessing memslots MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit According to Documentation/virtual/kvm/locking.txt, the srcu read lock should be taken when accessing the memslots of the VM. The XIVE KVM device needs to do so when configuring the page of the OS event queue of vCPU for a given priority and when marking the same page dirty before migration. This avoids warnings such as : [ 208.224882] ============================= [ 208.224884] WARNING: suspicious RCU usage [ 208.224889] 5.2.0-rc2-xive+ #47 Not tainted [ 208.224890] ----------------------------- [ 208.224894] ../include/linux/kvm_host.h:633 suspicious rcu_dereference_check() usage! [ 208.224896] other info that might help us debug this: [ 208.224898] rcu_scheduler_active = 2, debug_locks = 1 [ 208.224901] no locks held by qemu-system-ppc/3923. [ 208.224902] stack backtrace: [ 208.224907] CPU: 64 PID: 3923 Comm: qemu-system-ppc Kdump: loaded Not tainted 5.2.0-rc2-xive+ #47 [ 208.224909] Call Trace: [ 208.224918] [c000200cdd98fa30] [c000000000be1934] dump_stack+0xe8/0x164 (unreliable) [ 208.224924] [c000200cdd98fa80] [c0000000001aec80] lockdep_rcu_suspicious+0x110/0x180 [ 208.224935] [c000200cdd98fb00] [c0080000075933a0] gfn_to_memslot+0x1c8/0x200 [kvm] [ 208.224943] [c000200cdd98fb40] [c008000007599600] gfn_to_pfn+0x28/0x60 [kvm] [ 208.224951] [c000200cdd98fb70] [c008000007599658] gfn_to_page+0x20/0x40 [kvm] [ 208.224959] [c000200cdd98fb90] [c0080000075b495c] kvmppc_xive_native_set_attr+0x8b4/0x1480 [kvm] [ 208.224967] [c000200cdd98fca0] [c00800000759261c] kvm_device_ioctl_attr+0x64/0xb0 [kvm] [ 208.224974] [c000200cdd98fcf0] [c008000007592730] kvm_device_ioctl+0xc8/0x110 [kvm] [ 208.224979] [c000200cdd98fd10] [c000000000433a24] do_vfs_ioctl+0xd4/0xcd0 [ 208.224981] [c000200cdd98fdb0] [c000000000434724] ksys_ioctl+0x104/0x120 [ 208.224984] [c000200cdd98fe00] [c000000000434768] sys_ioctl+0x28/0x80 [ 208.224988] [c000200cdd98fe20] [c00000000000b888] system_call+0x5c/0x70 legoater@boss01:~$ Fixes: 13ce3297c576 ("KVM: PPC: Book3S HV: XIVE: Add controls for the EQ configuration") Fixes: e6714bd1671d ("KVM: PPC: Book3S HV: XIVE: Add a control to dirty the XIVE EQ pages") Signed-off-by: Cédric Le Goater Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_xive_native.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/powerpc/kvm/book3s_xive_native.c') diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index fec3b85411ef..8b762e3ebbc5 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -535,6 +535,7 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, struct xive_q *q; gfn_t gfn; unsigned long page_size; + int srcu_idx; /* * Demangle priority/server tuple from the EQ identifier @@ -610,20 +611,24 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive, return -EINVAL; } + srcu_idx = srcu_read_lock(&kvm->srcu); gfn = gpa_to_gfn(kvm_eq.qaddr); page = gfn_to_page(kvm, gfn); if (is_error_page(page)) { + srcu_read_unlock(&kvm->srcu, srcu_idx); pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr); return -EINVAL; } page_size = kvm_host_page_size(kvm, gfn); if (1ull << kvm_eq.qshift > page_size) { + srcu_read_unlock(&kvm->srcu, srcu_idx); pr_warn("Incompatible host page size %lx!\n", page_size); return -EINVAL; } qaddr = page_to_virt(page) + (kvm_eq.qaddr & ~PAGE_MASK); + srcu_read_unlock(&kvm->srcu, srcu_idx); /* * Backup the queue page guest address to the mark EQ page @@ -854,6 +859,7 @@ static int kvmppc_xive_native_vcpu_eq_sync(struct kvm_vcpu *vcpu) { struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; unsigned int prio; + int srcu_idx; if (!xc) return -ENOENT; @@ -865,7 +871,9 @@ static int kvmppc_xive_native_vcpu_eq_sync(struct kvm_vcpu *vcpu) continue; /* Mark EQ page dirty for migration */ + srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); mark_page_dirty(vcpu->kvm, gpa_to_gfn(q->guest_qaddr)); + srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); } return 0; } -- cgit v1.2.3 From bcaa3110d584f982a17e9ddbfc03e1130bca2bc9 Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Tue, 28 May 2019 23:13:24 +0200 Subject: KVM: PPC: Book3S HV: XIVE: Fix page offset when clearing ESB pages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Under XIVE, the ESB pages of an interrupt are used for interrupt management (EOI) and triggering. They are made available to guests through a mapping of the XIVE KVM device. When a device is passed-through, the passthru_irq helpers, kvmppc_xive_set_mapped() and kvmppc_xive_clr_mapped(), clear the ESB pages of the guest IRQ number being mapped and let the VM fault handler repopulate with the correct page. The ESB pages are mapped at offset 4 (KVM_XIVE_ESB_PAGE_OFFSET) in the KVM device mapping. Unfortunately, this offset was not taken into account when clearing the pages. This lead to issues with the passthrough devices for which the interrupts were not functional under some guest configuration (tg3 and single CPU) or in any configuration (e1000e adapter). Reviewed-by: Greg Kurz Tested-by: Greg Kurz Signed-off-by: Cédric Le Goater Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_xive_native.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kvm/book3s_xive_native.c') diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 8b762e3ebbc5..5596c8ec221a 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -172,6 +172,7 @@ bail: static int kvmppc_xive_native_reset_mapped(struct kvm *kvm, unsigned long irq) { struct kvmppc_xive *xive = kvm->arch.xive; + pgoff_t esb_pgoff = KVM_XIVE_ESB_PAGE_OFFSET + irq * 2; if (irq >= KVMPPC_XIVE_NR_IRQS) return -EINVAL; @@ -185,7 +186,7 @@ static int kvmppc_xive_native_reset_mapped(struct kvm *kvm, unsigned long irq) mutex_lock(&xive->mapping_lock); if (xive->mapping) unmap_mapping_range(xive->mapping, - irq * (2ull << PAGE_SHIFT), + esb_pgoff << PAGE_SHIFT, 2ull << PAGE_SHIFT, 1); mutex_unlock(&xive->mapping_lock); return 0; -- cgit v1.2.3