--- /dev/null
+From 61bd0f66ff92d5ce765ff9850fd3cbfec773c560 Mon Sep 17 00:00:00 2001
+From: Laurent Vivier <lvivier@redhat.com>
+Date: Fri, 2 Mar 2018 11:51:56 +0100
+Subject: KVM: PPC: Book3S HV: Fix guest time accounting with VIRT_CPU_ACCOUNTING_GEN
+
+From: Laurent Vivier <lvivier@redhat.com>
+
+commit 61bd0f66ff92d5ce765ff9850fd3cbfec773c560 upstream.
+
+Since commit 8b24e69fc47e ("KVM: PPC: Book3S HV: Close race with testing
+for signals on guest entry"), if CONFIG_VIRT_CPU_ACCOUNTING_GEN is set, the
+guest time is not accounted to guest time and user time, but instead to
+system time.
+
+This is because guest_enter()/guest_exit() are called while interrupts
+are disabled and the tick counter cannot be updated between them.
+
+To fix that, move guest_exit() after local_irq_enable(), and as
+guest_enter() is called with IRQ disabled, call guest_enter_irqoff()
+instead.
+
+Fixes: 8b24e69fc47e ("KVM: PPC: Book3S HV: Close race with testing for signals on guest entry")
+Signed-off-by: Laurent Vivier <lvivier@redhat.com>
+Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/powerpc/kvm/book3s_hv.c | 5 ++---
+ 1 file changed, 2 insertions(+), 3 deletions(-)
+
+--- a/arch/powerpc/kvm/book3s_hv.c
++++ b/arch/powerpc/kvm/book3s_hv.c
+@@ -2847,7 +2847,7 @@ static noinline void kvmppc_run_core(str
+ */
+ trace_hardirqs_on();
+
+- guest_enter();
++ guest_enter_irqoff();
+
+ srcu_idx = srcu_read_lock(&vc->kvm->srcu);
+
+@@ -2855,8 +2855,6 @@ static noinline void kvmppc_run_core(str
+
+ srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
+
+- guest_exit();
+-
+ trace_hardirqs_off();
+ set_irq_happened(trap);
+
+@@ -2890,6 +2888,7 @@ static noinline void kvmppc_run_core(str
+ kvmppc_set_host_core(pcpu);
+
+ local_irq_enable();
++ guest_exit();
+
+ /* Let secondaries go back to the offline loop */
+ for (i = 0; i < controlled_threads; ++i) {
--- /dev/null
+From a8b48a4dccea77e29462e59f1dbf0d5aa1ff167c Mon Sep 17 00:00:00 2001
+From: Paul Mackerras <paulus@ozlabs.org>
+Date: Wed, 7 Mar 2018 22:17:20 +1100
+Subject: KVM: PPC: Book3S HV: Fix trap number return from __kvmppc_vcore_entry
+
+From: Paul Mackerras <paulus@ozlabs.org>
+
+commit a8b48a4dccea77e29462e59f1dbf0d5aa1ff167c upstream.
+
+This fixes a bug where the trap number that is returned by
+__kvmppc_vcore_entry gets corrupted. The effect of the corruption
+is that IPIs get ignored on POWER9 systems when the IPI is sent via
+a doorbell interrupt to a CPU which is executing in a KVM guest.
+The effect of the IPI being ignored is often that another CPU locks
+up inside smp_call_function_many() (and if that CPU is holding a
+spinlock, other CPUs then lock up inside raw_spin_lock()).
+
+The trap number is currently held in register r12 for most of the
+assembly-language part of the guest exit path. In that path, we
+call kvmppc_subcore_exit_guest(), which is a C function, without
+restoring r12 afterwards. Depending on the kernel config and the
+compiler, it may modify r12 or it may not, so some config/compiler
+combinations see the bug and others don't.
+
+To fix this, we arrange for the trap number to be stored on the
+stack from the 'guest_bypass:' label until the end of the function,
+then the trap number is loaded and returned in r12 as before.
+
+Cc: stable@vger.kernel.org # v4.8+
+Fixes: fd7bacbca47a ("KVM: PPC: Book3S HV: Fix TB corruption in guest exit path on HMI interrupt")
+Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/powerpc/kvm/book3s_hv_rmhandlers.S | 8 +++++---
+ 1 file changed, 5 insertions(+), 3 deletions(-)
+
+--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
++++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+@@ -308,7 +308,6 @@ kvm_novcpu_exit:
+ stw r12, STACK_SLOT_TRAP(r1)
+ bl kvmhv_commence_exit
+ nop
+- lwz r12, STACK_SLOT_TRAP(r1)
+ b kvmhv_switch_to_host
+
+ /*
+@@ -1136,6 +1135,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
+ secondary_too_late:
+ li r12, 0
++ stw r12, STACK_SLOT_TRAP(r1)
+ cmpdi r4, 0
+ beq 11f
+ stw r12, VCPU_TRAP(r4)
+@@ -1445,12 +1445,12 @@ mc_cont:
+ 1:
+ #endif /* CONFIG_KVM_XICS */
+
++ stw r12, STACK_SLOT_TRAP(r1)
+ mr r3, r12
+ /* Increment exit count, poke other threads to exit */
+ bl kvmhv_commence_exit
+ nop
+ ld r9, HSTATE_KVM_VCPU(r13)
+- lwz r12, VCPU_TRAP(r9)
+
+ /* Stop others sending VCPU interrupts to this physical CPU */
+ li r0, -1
+@@ -1816,6 +1816,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1
+ * POWER7/POWER8 guest -> host partition switch code.
+ * We don't have to lock against tlbies but we do
+ * have to coordinate the hardware threads.
++ * Here STACK_SLOT_TRAP(r1) contains the trap number.
+ */
+ kvmhv_switch_to_host:
+ /* Secondary threads wait for primary to do partition switch */
+@@ -1868,11 +1869,11 @@ BEGIN_FTR_SECTION
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
+ /* If HMI, call kvmppc_realmode_hmi_handler() */
++ lwz r12, STACK_SLOT_TRAP(r1)
+ cmpwi r12, BOOK3S_INTERRUPT_HMI
+ bne 27f
+ bl kvmppc_realmode_hmi_handler
+ nop
+- li r12, BOOK3S_INTERRUPT_HMI
+ /*
+ * At this point kvmppc_realmode_hmi_handler would have resync-ed
+ * the TB. Hence it is not required to subtract guest timebase
+@@ -1950,6 +1951,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_R
+ li r0, KVM_GUEST_MODE_NONE
+ stb r0, HSTATE_IN_GUEST(r13)
+
++ lwz r12, STACK_SLOT_TRAP(r1) /* return trap # in r12 */
+ ld r0, SFS+PPC_LR_STKOFF(r1)
+ addi r1, r1, SFS
+ mtlr r0
--- /dev/null
+From debd574f4195e205ba505b25e19b2b797f4bcd94 Mon Sep 17 00:00:00 2001
+From: Paul Mackerras <paulus@ozlabs.org>
+Date: Fri, 2 Mar 2018 15:38:04 +1100
+Subject: KVM: PPC: Book3S HV: Fix VRMA initialization with 2MB or 1GB memory backing
+
+From: Paul Mackerras <paulus@ozlabs.org>
+
+commit debd574f4195e205ba505b25e19b2b797f4bcd94 upstream.
+
+The current code for initializing the VRMA (virtual real memory area)
+for HPT guests requires the page size of the backing memory to be one
+of 4kB, 64kB or 16MB. With a radix host we have the possibility that
+the backing memory page size can be 2MB or 1GB. In these cases, if the
+guest switches to HPT mode, KVM will not initialize the VRMA and the
+guest will fail to run.
+
+In fact it is not necessary that the VRMA page size is the same as the
+backing memory page size; any VRMA page size less than or equal to the
+backing memory page size is acceptable. Therefore we now choose the
+largest page size out of the set {4k, 64k, 16M} which is not larger
+than the backing memory page size.
+
+Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/powerpc/kvm/book3s_hv.c | 12 +++++++-----
+ 1 file changed, 7 insertions(+), 5 deletions(-)
+
+--- a/arch/powerpc/kvm/book3s_hv.c
++++ b/arch/powerpc/kvm/book3s_hv.c
+@@ -3618,15 +3618,17 @@ static int kvmppc_hv_setup_htab_rma(stru
+ goto up_out;
+
+ psize = vma_kernel_pagesize(vma);
+- porder = __ilog2(psize);
+
+ up_read(¤t->mm->mmap_sem);
+
+ /* We can handle 4k, 64k or 16M pages in the VRMA */
+- err = -EINVAL;
+- if (!(psize == 0x1000 || psize == 0x10000 ||
+- psize == 0x1000000))
+- goto out_srcu;
++ if (psize >= 0x1000000)
++ psize = 0x1000000;
++ else if (psize >= 0x10000)
++ psize = 0x10000;
++ else
++ psize = 0x1000;
++ porder = __ilog2(psize);
+
+ senc = slb_pgsize_encoding(psize);
+ kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
tcp-fix-tcp_repair_queue-bound-checking.patch
bdi-wake-up-concurrent-wb_shutdown-callers.patch
bdi-fix-oops-in-wb_workfn.patch
+kvm-ppc-book3s-hv-fix-trap-number-return-from-__kvmppc_vcore_entry.patch
+kvm-ppc-book3s-hv-fix-guest-time-accounting-with-virt_cpu_accounting_gen.patch
+kvm-ppc-book3s-hv-fix-vrma-initialization-with-2mb-or-1gb-memory-backing.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
