KVM: PPC: Book3S HV: Fix handling of interrupted VCPUs

This fixes a bug which results in stale vcore pointers being left in the per-cpu preempted vcore lists when a VM is destroyed. The result of the stale vcore pointers is usually either a crash or a lockup inside collect_piggybacks() when another VM is run. A typical lockup message looks like:

[  472.161074] NMI watchdog: BUG: soft lockup - CPU#24 stuck for 22s! [qemu-system-ppc:7039]
[  472.161204] Modules linked in: kvm_hv kvm_pr kvm xt_CHECKSUM ipt_MASQUERADE nf_nat_masquerade_ipv4 tun ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 xt_conntrack ebtable_nat ebtable_broute bridge stp llc ebtable_filter ebtables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw ip6table_filter ip6_tables iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw ses enclosure shpchp rtc_opal i2c_opal powernv_rng binfmt_misc dm_service_time scsi_dh_alua radeon i2c_algo_bit drm_kms_helper ttm drm tg3 ptp pps_core cxgb3 ipr i2c_core mdio dm_multipath [last unloaded: kvm_hv]
[  472.162111] CPU: 24 PID: 7039 Comm: qemu-system-ppc Not tainted 4.2.0-kvm+ #49
[  472.162187] task: c000001e38512750 ti: c000001e41bfc000 task.ti: c000001e41bfc000
[  472.162262] NIP: c00000000096b094 LR: c00000000096b08c CTR: c000000000111130
[  472.162337] REGS: c000001e41bff520 TRAP: 0901   Not tainted  (4.2.0-kvm+)
[  472.162399] MSR: 9000000100009033 <SF,HV,EE,ME,IR,DR,RI,LE>  CR: 24848844  XER: 00000000
[  472.162588] CFAR: c00000000096b0ac SOFTE: 1

GPR00: c000000000111170 c000001e41bff7a0 c00000000127df00 0000000000000001
GPR04: 0000000000000003 0000000000000001 0000000000000000 0000000000874821
GPR08: c000001e41bff8e0 0000000000000001 0000000000000000 d00000000efde740
GPR12: c000000000111130 c00000000fdae400

[  472.163053] NIP [c00000000096b094] _raw_spin_lock_irqsave+0xa4/0x130
[  472.163117] LR [c00000000096b08c] _raw_spin_lock_irqsave+0x9c/0x130
[  472.163179] Call Trace:
[  472.163206] [c000001e41bff7a0] [c000001e41bff7f0] 0xc000001e41bff7f0 (unreliable)
[  472.163295] [c000001e41bff7e0] [c000000000111170] __wake_up+0x40/0x90
[  472.163375] [c000001e41bff830] [d00000000efd6fc0] kvmppc_run_core+0x1240/0x1950 [kvm_hv]
[  472.163465] [c000001e41bffa30] [d00000000efd8510] kvmppc_vcpu_run_hv+0x5a0/0xd90 [kvm_hv]
[  472.163559] [c000001e41bffb70] [d00000000e9318a4] kvmppc_vcpu_run+0x44/0x60 [kvm]
[  472.163653] [c000001e41bffba0] [d00000000e92e674] kvm_arch_vcpu_ioctl_run+0x64/0x170 [kvm]
[  472.163745] [c000001e41bffbe0] [d00000000e9263a8] kvm_vcpu_ioctl+0x538/0x7b0 [kvm]
[  472.163834] [c000001e41bffd40] [c0000000002d0f50] do_vfs_ioctl+0x480/0x7c0
[  472.163910] [c000001e41bffde0] [c0000000002d1364] SyS_ioctl+0xd4/0xf0
[  472.163986] [c000001e41bffe30] [c000000000009260] system_call+0x38/0xd0
[  472.164060] Instruction dump:
[  472.164098] ebc1fff0 ebe1fff8 7c0803a6 4e800020 60000000 60000000 60420000 8bad02e2
[  472.164224] 7fc3f378 4b6a57c1 60000000 7c210b78 <e92d0000> 89290009 792affe3 40820070

The bug is that kvmppc_run_vcpu does not correctly handle the case where a vcpu task receives a signal while its guest vcpu is executing in the guest as a result of being piggy-backed onto the execution of another vcore. In that case we need to wait for the vcpu to finish executing inside the guest, and then remove this vcore from the preempted vcores list. That way, we avoid leaving this vcpu's vcore on the preempted vcores list when the vcpu gets interrupted.

Fixes ec2571650826

Reported-by Thomas Huth <[email protected]>

Signed-off-by Paul Mackerras <[email protected]>

---
 arch/powerpc/kvm/book3s_hv.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

arch/powerpc/kvm/book3s_hv.c +0 -1

index 9754e68..2280497 100644
@@ -2692,9 +2692,13 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	while (vcpu->arch.state = KVMPPC_VCPU_RUNNABLE &&
 	       (vc->vcore_state = VCORE_RUNNING ||
-		vc->vcore_state = VCORE_EXITING))

This fixes several bugs in the radix page fault handler relating to the way large pages in the memory backing the guest were handled. First, the check for large pages only checked for explicit huge pages and missed transparent huge pages. Then the check that the addresses (host virtual vs. guest physical) had appropriate alignment was wrong, meaning that the code never put a large page in the partition scoped radix tree; it was always demoted to a small page.

Fixing this exposed bugs in kvmppc_create_pte(). We were never invalidating a 2MB PTE, which meant that if a page was initially faulted in without write permission and the guest then attempted to store to it, we would never update the PTE to have write permission. If we find a valid 2MB PTE in the PMD, we need to clear it and do a TLB invalidation before installing either the new 2MB PTE or a pointer to a page table page.

This also corrects an assumption that get_user_pages_fast would set the _PAGE_DIRTY bit if we are writing, which is not true. Instead we mark the page dirty explicitly with set_page_dirty_lock(). This also means we don't need the dirty bit set on the host PTE when providing write access on a read fault.

Signed-off-by Paul Mackerras <[email protected]>

---
 arch/powerpc/kvm/book3s_64_mmu_radix.c | 70 +++++++++++++++++++++-------------
 1 file changed, 44 insertions(+), 26 deletions(-)

arch/powerpc/kvm/book3s_64_mmu_radix.c +11 -7

index 0c85481..5798c2c 100644
@@ -195,6 +195,12 @@ static void kvmppc_pte_free(pte_t *ptep)
 	kmem_cache_free(kvm_pte_cache, ptep);
 }
 
+/* Like pmd_huge() and pmd_large(), but works regardless of config options */
+static inline int pmd_is_leaf(pmd_t pmd)
+{
+	return !!(pmd_val(pmd) & _PAGE_PTE);
+}
+
 static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 			     unsigned int level, unsigned long mmu_seq)
 {

@@ -219,7 +225,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 	else
 		new_pmd = pmd_alloc_one(kvm->mm, gpa);
 
-	if (level = 0 && !(pmd && pmd_present(*pmd)))
+	if (level = 0 && !(pmd && pmd_present(*pmd) && !pmd_is_leaf(*pmd)))
 		new_ptep = kvmppc_pte_alloc();
 
 	/* Check if we might have been invalidated; let the guest retry if so */

@@ -244,12 +250,31 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 		new_pmd = NULL;
 	}
 	pmd = pmd_offset(pud, gpa);
-	if (pmd_large(*pmd)) {
-		/* Someone else has instantiated a large page here; retry */
-		ret = -EAGAIN;
-		goto out_unlock;
-	}
-	if (level = 1 && !pmd_none(*pmd)) {
+	if (pmd_is_leaf(*pmd)) {
+		unsigned long lgpa = gpa & PMD_MASK;
+
+		/*

arch/powerpc/kvm/book3s_64_mmu_radix.c +23 -19

+		kvmppc_radix_tlbie_page(kvm, lgpa, PMD_SHIFT);
+		if (old & _PAGE_DIRTY) {
+			unsigned long gfn = lgpa >> PAGE_SHIFT;
+			struct kvm_memory_slot *memslot;
+			memslot = gfn_to_memslot(kvm, gfn);
+			if (memslot && memslot->dirty_bitmap)
+				kvmppc_update_dirty_map(memslot,
+							gfn, PMD_SIZE);
+		}
+		pmd_clear(pmd);
+	} else if (level = 1 && !pmd_none(*pmd)) {
 		/*
 		 * There's a page table page here, but we wanted
 		 * to install a large page.  Tell the caller and let

@@ -412,28 +437,24 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	} else {
 		page = pages[0];
 		pfn = page_to_pfn(page);
-		if (PageHuge(page)) {
-			page = compound_head(page);
-			pte_size <<= compound_order(page);
+		if (PageCompound(page)) {
+			pte_size <<= compound_order(compound_head(page));
 			/* See if we can insert a 2MB large-page PTE here */
 			if (pte_size >= PMD_SIZE &&
-			    (gpa & PMD_MASK & PAGE_MASK) =
-			    (hva & PMD_MASK & PAGE_MASK)) {
+			    (gpa & (PMD_SIZE - PAGE_SIZE)) =
+			    (hva & (PMD_SIZE - PAGE_SIZE))) {
 				level = 1;
 				pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1);
 			}
 		}
 		/* See if we can provide write access */
 		if (writing) {
-			/*
-			 * We assume gup_fast has set dirty on the host PTE.
-			 */
 			pgflags |= _PAGE_WRITE;
 		} else {
 			local_irq_save(flags);
 			ptep = find_current_mm_pte(current->mm->pgd,
 						   hva, NULL, NULL);
-			if (ptep && pte_write(*ptep) && pte_dirty(*ptep))
+			if (ptep && pte_write(*ptep))
 				pgflags |= _PAGE_WRITE;
 			local_irq_restore(flags);
 		}

@@ -459,18 +480,15 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		pte = pfn_pte(pfn, __pgprot(pgflags));
 		ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
 	}
-	if (ret = 0 || ret = -EAGAIN)
-		ret = RESUME_GUEST;
 
 	if (page) {
-		/*
-		 * We drop pages[0] here, not page because page might
-		 * have been set to the head page of a compound, but
-		 * we have to drop the reference on the correct tail
-		 * page to match the get inside gup()
-		 */
-		put_page(pages[0]);
+		if (!ret && (pgflags & _PAGE_WRITE))
+			set_page_dirty_lock(page);
+		put_page(page);
 	}
+
+	if (ret = 0 || ret = -EAGAIN)
+		ret = RESUME_GUEST;
 	return ret;
 }
 

@@ -644,7 +662,7 @@ void kvmppc_free_radix(struct kvm *kvm)
 				continue;
 			pmd = pmd_offset(pud, 0);
 			for (im = 0; im < PTRS_PER_PMD; ++im, ++pmd) {
-				if (pmd_huge(*pmd)) {
+				if (pmd_is_leaf(*pmd)) {
 					pmd_clear(pmd);
 					continue;
 				}

Signature · 6 lines

2.7.4

--
To unsubscribe from this list: send the line "unsubscribe kvm-ppc" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html