Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759608AbcLTFvh (ORCPT ); Tue, 20 Dec 2016 00:51:37 -0500 Received: from ozlabs.org ([103.22.144.67]:59863 "EHLO ozlabs.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753960AbcLTFtQ (ORCPT ); Tue, 20 Dec 2016 00:49:16 -0500 From: David Gibson To: paulus@samba.org, sjitindarsingh@gmail.com Cc: benh@kernel.crashing.org, thuth@redhat.com, lvivier@redhat.com, linuxppc-dev@lists.ozlabs.org, kvm@vger.kernel.org, linux-kernel@vger.kernel.org, David Gibson Subject: [PATCHv2 10/11] powerpc/kvm: KVM-HV HPT resizing implementation Date: Tue, 20 Dec 2016 16:49:06 +1100 Message-Id: <20161220054907.9204-11-david@gibson.dropbear.id.au> X-Mailer: git-send-email 2.9.3 In-Reply-To: <20161220054907.9204-1-david@gibson.dropbear.id.au> References: <20161220054907.9204-1-david@gibson.dropbear.id.au> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6219 Lines: 232 This adds the "guts" of the implementation for the HPT resizing PAPR extension. It has the code to allocate and clear a new HPT, rehash an existing HPT's entries into it, and accomplish the switchover for a KVM guest from the old HPT to the new one. Signed-off-by: David Gibson --- arch/powerpc/kvm/book3s_64_mmu_hv.c | 188 +++++++++++++++++++++++++++++++++++- 1 file changed, 187 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 86a1bcb..e22776e 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -66,6 +66,10 @@ struct kvm_resize_hpt { /* These fields protected by kvm->lock */ int error; bool prepare_done; + + /* Private to the work thread, until prepare_done is true, + * then protected by kvm->resize_hpt_sem */ + struct kvm_hpt_info hpt; }; static void kvmppc_rmap_reset(struct kvm *kvm); @@ -1187,21 +1191,203 @@ void kvmppc_unpin_guest_page(struct kvm *kvm, void *va, unsigned long gpa, */ static int resize_hpt_allocate(struct kvm_resize_hpt *resize) { + int rc; + + rc = kvmppc_allocate_hpt(&resize->hpt, resize->order); + if (rc < 0) + return rc; + + resize_hpt_debug(resize, "resize_hpt_allocate(): HPT @ 0x%lx\n", + resize->hpt.virt); + return 0; } +static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize, + unsigned long idx) +{ + struct kvm *kvm = resize->kvm; + struct kvm_hpt_info *old = &kvm->arch.hpt; + struct kvm_hpt_info *new = &resize->hpt; + unsigned long old_hash_mask = (1ULL << (old->order - 7)) - 1; + unsigned long new_hash_mask = (1ULL << (new->order - 7)) - 1; + __be64 *hptep, *new_hptep; + unsigned long vpte, rpte, guest_rpte; + int ret; + struct revmap_entry *rev; + unsigned long apsize, psize, avpn, pteg, hash; + unsigned long new_idx, new_pteg, replace_vpte; + + hptep = (__be64 *)(old->virt + (idx << 4)); + + /* Guest is stopped, so new HPTEs can't be added or faulted + * in, only unmapped or altered by host actions. So, it's + * safe to check this before we take the HPTE lock */ + vpte = be64_to_cpu(hptep[0]); + if (!(vpte & HPTE_V_VALID) && !(vpte & HPTE_V_ABSENT)) + return 0; /* nothing to do */ + + while (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) + cpu_relax(); + + vpte = be64_to_cpu(hptep[0]); + + ret = 0; + if (!(vpte & HPTE_V_VALID) && !(vpte & HPTE_V_ABSENT)) + /* Nothing to do */ + goto out; + + /* Unmap */ + rev = &old->rev[idx]; + guest_rpte = rev->guest_rpte; + + ret = -EIO; + apsize = hpte_page_size(vpte, guest_rpte); + if (!apsize) + goto out; + + if (vpte & HPTE_V_VALID) { + unsigned long gfn = hpte_rpn(guest_rpte, apsize); + int srcu_idx = srcu_read_lock(&kvm->srcu); + struct kvm_memory_slot *memslot = + __gfn_to_memslot(kvm_memslots(kvm), gfn); + + if (memslot) { + unsigned long *rmapp; + rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn]; + + lock_rmap(rmapp); + kvmppc_unmap_hpte(kvm, idx, rmapp, gfn); + unlock_rmap(rmapp); + } + + srcu_read_unlock(&kvm->srcu, srcu_idx); + } + + /* Reload PTE after unmap */ + vpte = be64_to_cpu(hptep[0]); + + BUG_ON(vpte & HPTE_V_VALID); + BUG_ON(!(vpte & HPTE_V_ABSENT)); + + ret = 0; + if (!(vpte & HPTE_V_BOLTED)) + goto out; + + rpte = be64_to_cpu(hptep[1]); + psize = hpte_base_page_size(vpte, rpte); + avpn = HPTE_V_AVPN_VAL(vpte) & ~((psize - 1) >> 23); + pteg = idx / HPTES_PER_GROUP; + if (vpte & HPTE_V_SECONDARY) + pteg = ~pteg; + + if (!(vpte & HPTE_V_1TB_SEG)) { + unsigned long offset, vsid; + + /* We only have 28 - 23 bits of offset in avpn */ + offset = (avpn & 0x1f) << 23; + vsid = avpn >> 5; + /* We can find more bits from the pteg value */ + if (psize < (1ULL << 23)) + offset |= ((vsid ^ pteg) & old_hash_mask) * psize; + + hash = vsid ^ (offset / psize); + } else { + unsigned long offset, vsid; + + /* We only have 40 - 23 bits of seg_off in avpn */ + offset = (avpn & 0x1ffff) << 23; + vsid = avpn >> 17; + if (psize < (1ULL << 23)) + offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask) * psize; + + hash = vsid ^ (vsid << 25) ^ (offset / psize); + } + + new_pteg = hash & new_hash_mask; + if (vpte & HPTE_V_SECONDARY) { + BUG_ON(~pteg != (hash & old_hash_mask)); + new_pteg = ~new_pteg; + } else { + BUG_ON(pteg != (hash & old_hash_mask)); + } + + new_idx = new_pteg * HPTES_PER_GROUP + (idx % HPTES_PER_GROUP); + new_hptep = (__be64 *)(new->virt + (new_idx << 4)); + + replace_vpte = be64_to_cpu(new_hptep[0]); + + if (replace_vpte & (HPTE_V_VALID | HPTE_V_ABSENT)) { + BUG_ON(new->order >= old->order); + + if (replace_vpte & HPTE_V_BOLTED) { + if (vpte & HPTE_V_BOLTED) + /* Bolted collision, nothing we can do */ + ret = -ENOSPC; + /* Discard the new HPTE */ + goto out; + } + + /* Discard the previous HPTE */ + } + + new_hptep[1] = cpu_to_be64(rpte); + new->rev[new_idx].guest_rpte = guest_rpte; + /* No need for a barrier, since new HPT isn't active */ + new_hptep[0] = cpu_to_be64(vpte); + unlock_hpte(new_hptep, vpte); + +out: + unlock_hpte(hptep, vpte); + return ret; +} + static int resize_hpt_rehash(struct kvm_resize_hpt *resize) { - return -EIO; + struct kvm *kvm = resize->kvm; + unsigned long i; + int rc; + + for (i = 0; i < kvmppc_hpt_npte(&kvm->arch.hpt); i++) { + rc = resize_hpt_rehash_hpte(resize, i); + if (rc != 0) + return rc; + } + + return 0; } static void resize_hpt_pivot(struct kvm_resize_hpt *resize) { + struct kvm *kvm = resize->kvm; + struct kvm_hpt_info hpt_tmp; + + /* Exchange the pending tables in the resize structure with + * the active tables */ + + resize_hpt_debug(resize, "resize_hpt_pivot()\n"); + + spin_lock(&kvm->mmu_lock); + asm volatile("ptesync" : : : "memory"); + + hpt_tmp = kvm->arch.hpt; + kvmppc_set_hpt(kvm, &resize->hpt); + resize->hpt = hpt_tmp; + + spin_unlock(&kvm->mmu_lock); + + synchronize_srcu_expedited(&kvm->srcu); + + resize_hpt_debug(resize, "resize_hpt_pivot() done\n"); } static void resize_hpt_release(struct kvm *kvm, struct kvm_resize_hpt *resize) { BUG_ON(kvm->arch.resize_hpt != resize); + + if (resize->hpt.virt) + kvmppc_free_hpt(&resize->hpt); + kvm->arch.resize_hpt = NULL; kfree(resize); } -- 2.9.3