From: Paul Mackerras <paulus@samba.org> To: Alexander Graf <agraf@suse.de>, kvm-ppc@vger.kernel.org Cc: kvm@vger.kernel.org Subject: [PATCH 4/5] KVM: PPC: Book3S HV: Take the SRCU read lock before looking up memslots Date: Mon, 6 Aug 2012 20:06:55 +1000 [thread overview] Message-ID: <20120806100655.GE8980@bloggs.ozlabs.ibm.com> (raw) In-Reply-To: <20120806100207.GA8980@bloggs.ozlabs.ibm.com> The generic KVM code uses SRCU (sleeping RCU) to protect accesses to the memslots data structures against updates due to userspace adding, modifying or removing memory slots. We need to do that too, both to avoid accessing stale copies of the memslots and to avoid lockdep warnings. This therefore adds srcu_read_lock/unlock pairs around code that accesses and uses memslots. Since the real-mode handlers for H_ENTER, H_REMOVE and H_BULK_REMOVE need to access the memslots, and we don't want to call the SRCU code in real mode (since we have no assurance that it would only access the linear mapping), we hold the SRCU read lock for the VM while in the guest. This does mean that adding or removing memory slots while some vcpus are executing in the guest will block for up to two jiffies. This tradeoff is acceptable since adding/removing memory slots only happens rarely, while H_ENTER/H_REMOVE/H_BULK_REMOVE are performance-critical hot paths. Signed-off-by: Paul Mackerras <paulus@samba.org> --- arch/powerpc/kvm/book3s_64_mmu_hv.c | 17 +++++++++++++---- arch/powerpc/kvm/book3s_hv.c | 27 +++++++++++++++++++++++---- 2 files changed, 36 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 87735a7..6e17e97 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -24,6 +24,7 @@ #include <linux/slab.h> #include <linux/hugetlb.h> #include <linux/vmalloc.h> +#include <linux/srcu.h> #include <asm/tlbflush.h> #include <asm/kvm_ppc.h> @@ -1080,20 +1081,22 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa, unsigned long hva, psize, offset; unsigned long pa; unsigned long *physp; + int srcu_idx; + srcu_idx = srcu_read_lock(&kvm->srcu); memslot = gfn_to_memslot(kvm, gfn); if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) - return NULL; + goto err; if (!kvm->arch.using_mmu_notifiers) { physp = kvm->arch.slot_phys[memslot->id]; if (!physp) - return NULL; + goto err; physp += gfn - memslot->base_gfn; pa = *physp; if (!pa) { if (kvmppc_get_guest_page(kvm, gfn, memslot, PAGE_SIZE) < 0) - return NULL; + goto err; pa = *physp; } page = pfn_to_page(pa >> PAGE_SHIFT); @@ -1102,9 +1105,11 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa, hva = gfn_to_hva_memslot(memslot, gfn); npages = get_user_pages_fast(hva, 1, 1, pages); if (npages < 1) - return NULL; + goto err; page = pages[0]; } + srcu_read_unlock(&kvm->srcu, srcu_idx); + psize = PAGE_SIZE; if (PageHuge(page)) { page = compound_head(page); @@ -1114,6 +1119,10 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa, if (nb_ret) *nb_ret = psize - offset; return page_address(page) + offset; + + err: + srcu_read_unlock(&kvm->srcu, srcu_idx); + return NULL; } void kvmppc_unpin_guest_page(struct kvm *kvm, void *va) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index aad20ca0..067d0b6 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -30,6 +30,7 @@ #include <linux/cpumask.h> #include <linux/spinlock.h> #include <linux/page-flags.h> +#include <linux/srcu.h> #include <asm/reg.h> #include <asm/cputable.h> @@ -366,13 +367,16 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) unsigned long req = kvmppc_get_gpr(vcpu, 3); unsigned long target, ret = H_SUCCESS; struct kvm_vcpu *tvcpu; + int idx; switch (req) { case H_ENTER: + idx = srcu_read_lock(&vcpu->kvm->srcu); ret = kvmppc_virtmode_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4), kvmppc_get_gpr(vcpu, 5), kvmppc_get_gpr(vcpu, 6), kvmppc_get_gpr(vcpu, 7)); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; case H_CEDE: break; @@ -411,6 +415,7 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, struct task_struct *tsk) { int r = RESUME_HOST; + int srcu_idx; vcpu->stat.sum_exits++; @@ -470,12 +475,16 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, * have been handled already. */ case BOOK3S_INTERRUPT_H_DATA_STORAGE: + srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvmppc_book3s_hv_page_fault(run, vcpu, vcpu->arch.fault_dar, vcpu->arch.fault_dsisr); + srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); break; case BOOK3S_INTERRUPT_H_INST_STORAGE: + srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvmppc_book3s_hv_page_fault(run, vcpu, kvmppc_get_pc(vcpu), 0); + srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); break; /* * This occurs if the guest executes an illegal instruction. @@ -820,6 +829,7 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc) long ret; u64 now; int ptid, i, need_vpa_update; + int srcu_idx; /* don't start if any threads have a signal pending */ need_vpa_update = 0; @@ -898,6 +908,9 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc) spin_unlock(&vc->lock); kvm_guest_enter(); + + srcu_idx = srcu_read_lock(&vcpu0->kvm->srcu); + __kvmppc_vcore_entry(NULL, vcpu0); for (i = 0; i < threads_per_core; ++i) kvmppc_release_hwthread(vc->pcpu + i); @@ -913,6 +926,8 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc) vc->vcore_state = VCORE_EXITING; spin_unlock(&vc->lock); + srcu_read_unlock(&vcpu0->kvm->srcu, srcu_idx); + /* make sure updates to secondary vcpu structs are visible now */ smp_mb(); kvm_guest_exit(); @@ -1383,6 +1398,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) unsigned long rmls; unsigned long *physp; unsigned long i, npages; + int srcu_idx; mutex_lock(&kvm->lock); if (kvm->arch.rma_setup_done) @@ -1398,12 +1414,13 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) } /* Look up the memslot for guest physical address 0 */ + srcu_idx = srcu_read_lock(&kvm->srcu); memslot = gfn_to_memslot(kvm, 0); /* We must have some memory at 0 by now */ err = -EINVAL; if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) - goto out; + goto out_srcu; /* Look up the VMA for the start of this memory slot */ hva = memslot->userspace_addr; @@ -1427,14 +1444,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) err = -EPERM; if (cpu_has_feature(CPU_FTR_ARCH_201)) { pr_err("KVM: CPU requires an RMO\n"); - goto out; + goto out_srcu; } /* We can handle 4k, 64k or 16M pages in the VRMA */ err = -EINVAL; if (!(psize == 0x1000 || psize == 0x10000 || psize == 0x1000000)) - goto out; + goto out_srcu; /* Update VRMASD field in the LPCR */ senc = slb_pgsize_encoding(psize); @@ -1457,7 +1474,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) err = -EINVAL; if (rmls < 0) { pr_err("KVM: Can't use RMA of 0x%lx bytes\n", rma_size); - goto out; + goto out_srcu; } atomic_inc(&ri->use_count); kvm->arch.rma = ri; @@ -1497,6 +1514,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) smp_wmb(); kvm->arch.rma_setup_done = 1; err = 0; + out_srcu: + srcu_read_unlock(&kvm->srcu, srcu_idx); out: mutex_unlock(&kvm->lock); return err; -- 1.7.10.rc3.219.g53414
WARNING: multiple messages have this Message-ID (diff)
From: Paul Mackerras <paulus@samba.org> To: Alexander Graf <agraf@suse.de>, kvm-ppc@vger.kernel.org Cc: kvm@vger.kernel.org Subject: [PATCH 4/5] KVM: PPC: Book3S HV: Take the SRCU read lock before looking up memslots Date: Mon, 06 Aug 2012 10:06:55 +0000 [thread overview] Message-ID: <20120806100655.GE8980@bloggs.ozlabs.ibm.com> (raw) In-Reply-To: <20120806100207.GA8980@bloggs.ozlabs.ibm.com> The generic KVM code uses SRCU (sleeping RCU) to protect accesses to the memslots data structures against updates due to userspace adding, modifying or removing memory slots. We need to do that too, both to avoid accessing stale copies of the memslots and to avoid lockdep warnings. This therefore adds srcu_read_lock/unlock pairs around code that accesses and uses memslots. Since the real-mode handlers for H_ENTER, H_REMOVE and H_BULK_REMOVE need to access the memslots, and we don't want to call the SRCU code in real mode (since we have no assurance that it would only access the linear mapping), we hold the SRCU read lock for the VM while in the guest. This does mean that adding or removing memory slots while some vcpus are executing in the guest will block for up to two jiffies. This tradeoff is acceptable since adding/removing memory slots only happens rarely, while H_ENTER/H_REMOVE/H_BULK_REMOVE are performance-critical hot paths. Signed-off-by: Paul Mackerras <paulus@samba.org> --- arch/powerpc/kvm/book3s_64_mmu_hv.c | 17 +++++++++++++---- arch/powerpc/kvm/book3s_hv.c | 27 +++++++++++++++++++++++---- 2 files changed, 36 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 87735a7..6e17e97 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -24,6 +24,7 @@ #include <linux/slab.h> #include <linux/hugetlb.h> #include <linux/vmalloc.h> +#include <linux/srcu.h> #include <asm/tlbflush.h> #include <asm/kvm_ppc.h> @@ -1080,20 +1081,22 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa, unsigned long hva, psize, offset; unsigned long pa; unsigned long *physp; + int srcu_idx; + srcu_idx = srcu_read_lock(&kvm->srcu); memslot = gfn_to_memslot(kvm, gfn); if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) - return NULL; + goto err; if (!kvm->arch.using_mmu_notifiers) { physp = kvm->arch.slot_phys[memslot->id]; if (!physp) - return NULL; + goto err; physp += gfn - memslot->base_gfn; pa = *physp; if (!pa) { if (kvmppc_get_guest_page(kvm, gfn, memslot, PAGE_SIZE) < 0) - return NULL; + goto err; pa = *physp; } page = pfn_to_page(pa >> PAGE_SHIFT); @@ -1102,9 +1105,11 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa, hva = gfn_to_hva_memslot(memslot, gfn); npages = get_user_pages_fast(hva, 1, 1, pages); if (npages < 1) - return NULL; + goto err; page = pages[0]; } + srcu_read_unlock(&kvm->srcu, srcu_idx); + psize = PAGE_SIZE; if (PageHuge(page)) { page = compound_head(page); @@ -1114,6 +1119,10 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa, if (nb_ret) *nb_ret = psize - offset; return page_address(page) + offset; + + err: + srcu_read_unlock(&kvm->srcu, srcu_idx); + return NULL; } void kvmppc_unpin_guest_page(struct kvm *kvm, void *va) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index aad20ca0..067d0b6 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -30,6 +30,7 @@ #include <linux/cpumask.h> #include <linux/spinlock.h> #include <linux/page-flags.h> +#include <linux/srcu.h> #include <asm/reg.h> #include <asm/cputable.h> @@ -366,13 +367,16 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) unsigned long req = kvmppc_get_gpr(vcpu, 3); unsigned long target, ret = H_SUCCESS; struct kvm_vcpu *tvcpu; + int idx; switch (req) { case H_ENTER: + idx = srcu_read_lock(&vcpu->kvm->srcu); ret = kvmppc_virtmode_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4), kvmppc_get_gpr(vcpu, 5), kvmppc_get_gpr(vcpu, 6), kvmppc_get_gpr(vcpu, 7)); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; case H_CEDE: break; @@ -411,6 +415,7 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, struct task_struct *tsk) { int r = RESUME_HOST; + int srcu_idx; vcpu->stat.sum_exits++; @@ -470,12 +475,16 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, * have been handled already. */ case BOOK3S_INTERRUPT_H_DATA_STORAGE: + srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvmppc_book3s_hv_page_fault(run, vcpu, vcpu->arch.fault_dar, vcpu->arch.fault_dsisr); + srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); break; case BOOK3S_INTERRUPT_H_INST_STORAGE: + srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvmppc_book3s_hv_page_fault(run, vcpu, kvmppc_get_pc(vcpu), 0); + srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); break; /* * This occurs if the guest executes an illegal instruction. @@ -820,6 +829,7 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc) long ret; u64 now; int ptid, i, need_vpa_update; + int srcu_idx; /* don't start if any threads have a signal pending */ need_vpa_update = 0; @@ -898,6 +908,9 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc) spin_unlock(&vc->lock); kvm_guest_enter(); + + srcu_idx = srcu_read_lock(&vcpu0->kvm->srcu); + __kvmppc_vcore_entry(NULL, vcpu0); for (i = 0; i < threads_per_core; ++i) kvmppc_release_hwthread(vc->pcpu + i); @@ -913,6 +926,8 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc) vc->vcore_state = VCORE_EXITING; spin_unlock(&vc->lock); + srcu_read_unlock(&vcpu0->kvm->srcu, srcu_idx); + /* make sure updates to secondary vcpu structs are visible now */ smp_mb(); kvm_guest_exit(); @@ -1383,6 +1398,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) unsigned long rmls; unsigned long *physp; unsigned long i, npages; + int srcu_idx; mutex_lock(&kvm->lock); if (kvm->arch.rma_setup_done) @@ -1398,12 +1414,13 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) } /* Look up the memslot for guest physical address 0 */ + srcu_idx = srcu_read_lock(&kvm->srcu); memslot = gfn_to_memslot(kvm, 0); /* We must have some memory at 0 by now */ err = -EINVAL; if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) - goto out; + goto out_srcu; /* Look up the VMA for the start of this memory slot */ hva = memslot->userspace_addr; @@ -1427,14 +1444,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) err = -EPERM; if (cpu_has_feature(CPU_FTR_ARCH_201)) { pr_err("KVM: CPU requires an RMO\n"); - goto out; + goto out_srcu; } /* We can handle 4k, 64k or 16M pages in the VRMA */ err = -EINVAL; if (!(psize = 0x1000 || psize = 0x10000 || psize = 0x1000000)) - goto out; + goto out_srcu; /* Update VRMASD field in the LPCR */ senc = slb_pgsize_encoding(psize); @@ -1457,7 +1474,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) err = -EINVAL; if (rmls < 0) { pr_err("KVM: Can't use RMA of 0x%lx bytes\n", rma_size); - goto out; + goto out_srcu; } atomic_inc(&ri->use_count); kvm->arch.rma = ri; @@ -1497,6 +1514,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) smp_wmb(); kvm->arch.rma_setup_done = 1; err = 0; + out_srcu: + srcu_read_unlock(&kvm->srcu, srcu_idx); out: mutex_unlock(&kvm->lock); return err; -- 1.7.10.rc3.219.g53414
next prev parent reply other threads:[~2012-08-06 10:08 UTC|newest] Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top 2012-08-06 10:02 [PATCH 0/5] Improve memory slot handling and other fixes Paul Mackerras 2012-08-06 10:02 ` Paul Mackerras 2012-08-06 10:03 ` [PATCH 1/5] KVM: PPC: Book3S HV: Fix incorrect branch in H_CEDE code Paul Mackerras 2012-08-06 10:03 ` Paul Mackerras 2012-08-06 10:04 ` [PATCH 2/5] KVM: PPC: Quieten message about allocating linear regions Paul Mackerras 2012-08-06 10:04 ` Paul Mackerras 2012-08-06 10:06 ` [PATCH 3/5] KVM: PPC: Book3S HV: Handle memory slot deletion and modification correctly Paul Mackerras 2012-08-06 10:06 ` Paul Mackerras 2012-08-09 18:16 ` Marcelo Tosatti 2012-08-09 18:16 ` Marcelo Tosatti 2012-08-10 0:34 ` Paul Mackerras 2012-08-10 0:34 ` Paul Mackerras 2012-08-10 1:25 ` Marcelo Tosatti 2012-08-10 1:25 ` Marcelo Tosatti 2012-08-10 1:33 ` Marcelo Tosatti 2012-08-10 1:33 ` Marcelo Tosatti 2012-08-10 2:09 ` Takuya Yoshikawa 2012-08-10 2:09 ` Takuya Yoshikawa 2012-08-10 18:35 ` Marcelo Tosatti 2012-08-10 18:35 ` Marcelo Tosatti 2012-08-11 0:37 ` Paul Mackerras 2012-08-11 0:37 ` Paul Mackerras 2012-08-13 16:34 ` Marcelo Tosatti 2012-08-13 16:34 ` Marcelo Tosatti 2012-08-13 22:04 ` Marcelo Tosatti 2012-08-13 22:04 ` Marcelo Tosatti 2012-08-15 9:26 ` Avi Kivity 2012-08-15 9:26 ` Avi Kivity 2012-08-15 17:59 ` Marcelo Tosatti 2012-08-15 17:59 ` Marcelo Tosatti 2012-08-17 7:06 ` Benjamin Herrenschmidt 2012-08-17 7:06 ` Benjamin Herrenschmidt 2012-08-17 18:39 ` Marcelo Tosatti 2012-08-17 18:39 ` Marcelo Tosatti 2012-08-17 20:32 ` Benjamin Herrenschmidt 2012-08-17 20:32 ` Benjamin Herrenschmidt 2012-08-23 13:55 ` Marcelo Tosatti 2012-08-23 13:55 ` Marcelo Tosatti 2012-08-24 9:29 ` Paul Mackerras 2012-08-24 9:29 ` Paul Mackerras 2012-08-24 18:58 ` Marcelo Tosatti 2012-08-24 18:58 ` Marcelo Tosatti 2012-08-19 9:39 ` Avi Kivity 2012-08-19 9:39 ` Avi Kivity 2012-08-15 6:06 ` Paul Mackerras 2012-08-15 6:06 ` Paul Mackerras 2012-08-15 9:23 ` Avi Kivity 2012-08-15 9:23 ` Avi Kivity 2012-08-06 10:06 ` Paul Mackerras [this message] 2012-08-06 10:06 ` [PATCH 4/5] KVM: PPC: Book3S HV: Take the SRCU read lock before looking up memslots Paul Mackerras 2012-08-09 18:22 ` Marcelo Tosatti 2012-08-09 18:22 ` Marcelo Tosatti 2012-08-10 0:45 ` Paul Mackerras 2012-08-10 0:45 ` Paul Mackerras 2012-08-06 10:08 ` [RFC PATCH 5/5] KVM: PPC: Take the SRCU lock around memslot use Paul Mackerras 2012-08-06 10:08 ` Paul Mackerras 2012-08-09 18:27 ` Marcelo Tosatti 2012-08-09 18:27 ` Marcelo Tosatti 2012-08-10 0:37 ` Paul Mackerras 2012-08-10 0:37 ` Paul Mackerras 2012-08-10 9:27 ` Alexander Graf 2012-08-10 9:27 ` Alexander Graf 2012-08-15 8:16 ` Benjamin Herrenschmidt 2012-08-15 8:16 ` Benjamin Herrenschmidt 2012-08-10 9:23 ` [PATCH 0/5] Improve memory slot handling and other fixes Alexander Graf 2012-08-10 9:23 ` Alexander Graf
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=20120806100655.GE8980@bloggs.ozlabs.ibm.com \ --to=paulus@samba.org \ --cc=agraf@suse.de \ --cc=kvm-ppc@vger.kernel.org \ --cc=kvm@vger.kernel.org \ /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: linkBe 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.