Merge tag 'powerpc-5.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Enable THREAD_INFO_IN_TASK to move thread_info off the stack.

   - A big series from Christoph reworking our DMA code to use more of
     the generic infrastructure, as he said:
       "This series switches the powerpc port to use the generic swiotlb
        and noncoherent dma ops, and to use more generic code for the
        coherent direct mapping, as well as removing a lot of dead
        code."

   - Increase our vmalloc space to 512T with the Hash MMU on modern
     CPUs, allowing us to support machines with larger amounts of total
     RAM or distance between nodes.

   - Two series from Christophe, one to optimise TLB miss handlers on
     6xx, and another to optimise the way STRICT_KERNEL_RWX is
     implemented on some 32-bit CPUs.

   - Support for KCOV coverage instrumentation which means we can run
     syzkaller and discover even more bugs in our code.

  And as always many clean-ups, reworks and minor fixes etc.

  Thanks to: Alan Modra, Alexey Kardashevskiy, Alistair Popple, Andrea
  Arcangeli, Andrew Donnellan, Aneesh Kumar K.V, Aravinda Prasad, Balbir
  Singh, Brajeswar Ghosh, Breno Leitao, Christian Lamparter, Christian
  Zigotzky, Christophe Leroy, Christoph Hellwig, Corentin Labbe, Daniel
  Axtens, David Gibson, Diana Craciun, Firoz Khan, Gustavo A. R. Silva,
  Igor Stoppa, Joe Lawrence, Joel Stanley, Jonathan Neuschäfer, Jordan
  Niethe, Laurent Dufour, Madhavan Srinivasan, Mahesh Salgaonkar, Mark
  Cave-Ayland, Masahiro Yamada, Mathieu Malaterre, Matteo Croce, Meelis
  Roos, Michael W. Bringmann, Nathan Chancellor, Nathan Fontenot,
  Nicholas Piggin, Nick Desaulniers, Nicolai Stange, Oliver O'Halloran,
  Paul Mackerras, Peter Xu, PrasannaKumar Muralidharan, Qian Cai,
  Rashmica Gupta, Reza Arbab, Robert P. J. Day, Russell Currey,
  Sabyasachi Gupta, Sam Bobroff, Sandipan Das, Sergey Senozhatsky,
  Souptick Joarder, Stewart Smith, Tyrel Datwyler, Vaibhav Jain,
  YueHaibing"

* tag 'powerpc-5.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (200 commits)
  powerpc/32: Clear on-stack exception marker upon exception return
  powerpc: Remove export of save_stack_trace_tsk_reliable()
  powerpc/mm: fix "section_base" set but not used
  powerpc/mm: Fix "sz" set but not used warning
  powerpc/mm: Check secondary hash page table
  powerpc: remove nargs from __SYSCALL
  powerpc/64s: Fix unrelocated interrupt trampoline address test
  powerpc/powernv/ioda: Fix locked_vm counting for memory used by IOMMU tables
  powerpc/fsl: Fix the flush of branch predictor.
  powerpc/powernv: Make opal log only readable by root
  powerpc/xmon: Fix opcode being uninitialized in print_insn_powerpc
  powerpc/powernv: move OPAL call wrapper tracing and interrupt handling to C
  powerpc/64s: Fix data interrupts vs d-side MCE reentrancy
  powerpc/64s: Prepare to handle data interrupts vs d-side MCE reentrancy
  powerpc/64s: system reset interrupt preserve HSRRs
  powerpc/64s: Fix HV NMI vs HV interrupt recoverability test
  powerpc/mm/hash: Handle mmap_min_addr correctly in get_unmapped_area topdown search
  powerpc/hugetlb: Handle mmap_min_addr correctly in get_unmapped_area callback
  selftests/powerpc: Remove duplicate header
  powerpc sstep: Add support for modsd, modud instructions
  ...

6 files changed, 63 insertions, 99 deletions

diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 64f1135e7732..3223aec88b2c 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -10,11 +10,6 @@ common-objs-y = $(KVM)/kvm_main.o $(KVM)/eventfd.o
 common-objs-$(CONFIG_KVM_VFIO) += $(KVM)/vfio.o
 common-objs-$(CONFIG_KVM_MMIO) += $(KVM)/coalesced_mmio.o
 
-CFLAGS_e500_mmu.o := -I.
-CFLAGS_e500_mmu_host.o := -I.
-CFLAGS_emulate.o  := -I.
-CFLAGS_emulate_loadstore.o  := -I.
-
 common-objs-y += powerpc.o emulate_loadstore.o
 obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o
 obj-$(CONFIG_KVM_BOOK3S_HANDLER) += book3s_exports.o
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index bd1a677dd9e4..9a7dadbe1f17 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -192,6 +192,13 @@ void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
 }
 EXPORT_SYMBOL_GPL(kvmppc_book3s_queue_irqprio);
 
+void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, ulong flags)
+{
+	/* might as well deliver this straight away */
+	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_MACHINE_CHECK, flags);
+}
+EXPORT_SYMBOL_GPL(kvmppc_core_queue_machine_check);
+
 void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags)
 {
 	/* might as well deliver this straight away */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 5a066fc299e1..a3d5318f5d1e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1215,6 +1215,22 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 		break;
 	case BOOK3S_INTERRUPT_MACHINE_CHECK:
+		/* Print the MCE event to host console. */
+		machine_check_print_event_info(&vcpu->arch.mce_evt, false, true);
+
+		/*
+		 * If the guest can do FWNMI, exit to userspace so it can
+		 * deliver a FWNMI to the guest.
+		 * Otherwise we synthesize a machine check for the guest
+		 * so that it knows that the machine check occurred.
+		 */
+		if (!vcpu->kvm->arch.fwnmi_enabled) {
+			ulong flags = vcpu->arch.shregs.msr & 0x083c0000;
+			kvmppc_core_queue_machine_check(vcpu, flags);
+			r = RESUME_GUEST;
+			break;
+		}
+
 		/* Exit to guest with KVM_EXIT_NMI as exit reason */
 		run->exit_reason = KVM_EXIT_NMI;
 		run->hw.hardware_exit_reason = vcpu->arch.trap;
@@ -1227,8 +1243,6 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			run->flags |= KVM_RUN_PPC_NMI_DISP_NOT_RECOV;
 
 		r = RESUME_HOST;
-		/* Print the MCE event to host console. */
-		machine_check_print_event_info(&vcpu->arch.mce_evt, false);
 		break;
 	case BOOK3S_INTERRUPT_PROGRAM:
 	{
@@ -1392,7 +1406,7 @@ static int kvmppc_handle_nested_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		/* Pass the machine check to the L1 guest */
 		r = RESUME_HOST;
 		/* Print the MCE event to host console. */
-		machine_check_print_event_info(&vcpu->arch.mce_evt, false);
+		machine_check_print_event_info(&vcpu->arch.mce_evt, false, true);
 		break;
 	/*
 	 * We get these next two if the guest accesses a page which it thinks
@@ -3455,6 +3469,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 	unsigned long host_dscr = mfspr(SPRN_DSCR);
 	unsigned long host_tidr = mfspr(SPRN_TIDR);
 	unsigned long host_iamr = mfspr(SPRN_IAMR);
+	unsigned long host_amr = mfspr(SPRN_AMR);
 	s64 dec;
 	u64 tb;
 	int trap, save_pmu;
@@ -3571,13 +3586,15 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	mtspr(SPRN_PSPB, 0);
 	mtspr(SPRN_WORT, 0);
-	mtspr(SPRN_AMR, 0);
 	mtspr(SPRN_UAMOR, 0);
 	mtspr(SPRN_DSCR, host_dscr);
 	mtspr(SPRN_TIDR, host_tidr);
 	mtspr(SPRN_IAMR, host_iamr);
 	mtspr(SPRN_PSPB, 0);
 
+	if (host_amr != vcpu->arch.amr)
+		mtspr(SPRN_AMR, host_amr);
+
 	msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
 	store_fp_state(&vcpu->arch.fp);
 #ifdef CONFIG_ALTIVEC
diff --git a/arch/powerpc/kvm/book3s_hv_hmi.c b/arch/powerpc/kvm/book3s_hv_hmi.c
index e3f738eb1cac..64b5011475c7 100644
--- a/arch/powerpc/kvm/book3s_hv_hmi.c
+++ b/arch/powerpc/kvm/book3s_hv_hmi.c
@@ -24,6 +24,7 @@
 #include <linux/compiler.h>
 #include <asm/paca.h>
 #include <asm/hmi.h>
+#include <asm/processor.h>
 
 void wait_for_subcore_guest_exit(void)
 {
diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c
index 0787f12c1a1b..8c24c3bea0bf 100644
--- a/arch/powerpc/kvm/book3s_hv_ras.c
+++ b/arch/powerpc/kvm/book3s_hv_ras.c
@@ -66,10 +66,8 @@ static void reload_slb(struct kvm_vcpu *vcpu)
 /*
  * On POWER7, see if we can handle a machine check that occurred inside
  * the guest in real mode, without switching to the host partition.
- *
- * Returns: 0 => exit guest, 1 => deliver machine check to guest
  */
-static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
+static void kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
 {
 	unsigned long srr1 = vcpu->arch.shregs.msr;
 	struct machine_check_event mce_evt;
@@ -111,52 +109,24 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
 	}
 
 	/*
-	 * See if we have already handled the condition in the linux host.
-	 * We assume that if the condition is recovered then linux host
-	 * will have generated an error log event that we will pick
-	 * up and log later.
-	 * Don't release mce event now. We will queue up the event so that
-	 * we can log the MCE event info on host console.
+	 * Now get the event and stash it in the vcpu struct so it can
+	 * be handled by the primary thread in virtual mode.  We can't
+	 * call machine_check_queue_event() here if we are running on
+	 * an offline secondary thread.
 	 */
-	if (!get_mce_event(&mce_evt, MCE_EVENT_DONTRELEASE))
-		goto out;
-
-	if (mce_evt.version == MCE_V1 &&
-	    (mce_evt.severity == MCE_SEV_NO_ERROR ||
-	     mce_evt.disposition == MCE_DISPOSITION_RECOVERED))
-		handled = 1;
-
-out:
-	/*
-	 * For guest that supports FWNMI capability, hook the MCE event into
-	 * vcpu structure. We are going to exit the guest with KVM_EXIT_NMI
-	 * exit reason. On our way to exit we will pull this event from vcpu
-	 * structure and print it from thread 0 of the core/subcore.
-	 *
-	 * For guest that does not support FWNMI capability (old QEMU):
-	 * We are now going enter guest either through machine check
-	 * interrupt (for unhandled errors) or will continue from
-	 * current HSRR0 (for handled errors) in guest. Hence
-	 * queue up the event so that we can log it from host console later.
-	 */
-	if (vcpu->kvm->arch.fwnmi_enabled) {
-		/*
-		 * Hook up the mce event on to vcpu structure.
-		 * First clear the old event.
-		 */
-		memset(&vcpu->arch.mce_evt, 0, sizeof(vcpu->arch.mce_evt));
-		if (get_mce_event(&mce_evt, MCE_EVENT_RELEASE)) {
-			vcpu->arch.mce_evt = mce_evt;
-		}
-	} else
-		machine_check_queue_event();
+	if (get_mce_event(&mce_evt, MCE_EVENT_RELEASE)) {
+		if (handled && mce_evt.version == MCE_V1)
+			mce_evt.disposition = MCE_DISPOSITION_RECOVERED;
+	} else {
+		memset(&mce_evt, 0, sizeof(mce_evt));
+	}
 
-	return handled;
+	vcpu->arch.mce_evt = mce_evt;
 }
 
-long kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu)
+void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu)
 {
-	return kvmppc_realmode_mc_power7(vcpu);
+	kvmppc_realmode_mc_power7(vcpu);
 }
 
 /* Check if dynamic split is in force and return subcore size accordingly. */
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 9b8d50a7cbaf..25043b50cb30 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -58,6 +58,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 #define STACK_SLOT_DAWR		(SFS-56)
 #define STACK_SLOT_DAWRX	(SFS-64)
 #define STACK_SLOT_HFSCR	(SFS-72)
+#define STACK_SLOT_AMR		(SFS-80)
+#define STACK_SLOT_UAMOR	(SFS-88)
 /* the following is used by the P9 short path */
 #define STACK_SLOT_NVGPRS	(SFS-152)	/* 18 gprs */
 
@@ -726,11 +728,9 @@ BEGIN_FTR_SECTION
 	mfspr	r5, SPRN_TIDR
 	mfspr	r6, SPRN_PSSCR
 	mfspr	r7, SPRN_PID
-	mfspr	r8, SPRN_IAMR
 	std	r5, STACK_SLOT_TID(r1)
 	std	r6, STACK_SLOT_PSSCR(r1)
 	std	r7, STACK_SLOT_PID(r1)
-	std	r8, STACK_SLOT_IAMR(r1)
 	mfspr	r5, SPRN_HFSCR
 	std	r5, STACK_SLOT_HFSCR(r1)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
@@ -738,11 +738,18 @@ BEGIN_FTR_SECTION
 	mfspr	r5, SPRN_CIABR
 	mfspr	r6, SPRN_DAWR
 	mfspr	r7, SPRN_DAWRX
+	mfspr	r8, SPRN_IAMR
 	std	r5, STACK_SLOT_CIABR(r1)
 	std	r6, STACK_SLOT_DAWR(r1)
 	std	r7, STACK_SLOT_DAWRX(r1)
+	std	r8, STACK_SLOT_IAMR(r1)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
+	mfspr	r5, SPRN_AMR
+	std	r5, STACK_SLOT_AMR(r1)
+	mfspr	r6, SPRN_UAMOR
+	std	r6, STACK_SLOT_UAMOR(r1)
+
 BEGIN_FTR_SECTION
 	/* Set partition DABR */
 	/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
@@ -1631,22 +1638,25 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	mtspr	SPRN_PSPB, r0
 	mtspr	SPRN_WORT, r0
 BEGIN_FTR_SECTION
-	mtspr	SPRN_IAMR, r0
 	mtspr	SPRN_TCSCR, r0
 	/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
 	li	r0, 1
 	sldi	r0, r0, 31
 	mtspr	SPRN_MMCRS, r0
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
-8:
 
-	/* Save and reset AMR and UAMOR before turning on the MMU */
+	/* Save and restore AMR, IAMR and UAMOR before turning on the MMU */
+	ld	r8, STACK_SLOT_IAMR(r1)
+	mtspr	SPRN_IAMR, r8
+
+8:	/* Power7 jumps back in here */
 	mfspr	r5,SPRN_AMR
 	mfspr	r6,SPRN_UAMOR
 	std	r5,VCPU_AMR(r9)
 	std	r6,VCPU_UAMOR(r9)
-	li	r6,0
-	mtspr	SPRN_AMR,r6
+	ld	r5,STACK_SLOT_AMR(r1)
+	ld	r6,STACK_SLOT_UAMOR(r1)
+	mtspr	SPRN_AMR, r5
 	mtspr	SPRN_UAMOR, r6
 
 	/* Switch DSCR back to host value */
@@ -1746,11 +1756,9 @@ BEGIN_FTR_SECTION
 	ld	r5, STACK_SLOT_TID(r1)
 	ld	r6, STACK_SLOT_PSSCR(r1)
 	ld	r7, STACK_SLOT_PID(r1)
-	ld	r8, STACK_SLOT_IAMR(r1)
 	mtspr	SPRN_TIDR, r5
 	mtspr	SPRN_PSSCR, r6
 	mtspr	SPRN_PID, r7
-	mtspr	SPRN_IAMR, r8
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 #ifdef CONFIG_PPC_RADIX_MMU
@@ -2826,49 +2834,15 @@ kvm_cede_exit:
 #endif /* CONFIG_KVM_XICS */
 3:	b	guest_exit_cont
 
-	/* Try to handle a machine check in real mode */
+	/* Try to do machine check recovery in real mode */
 machine_check_realmode:
 	mr	r3, r9		/* get vcpu pointer */
 	bl	kvmppc_realmode_machine_check
 	nop
+	/* all machine checks go to virtual mode for further handling */
 	ld	r9, HSTATE_KVM_VCPU(r13)
 	li	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
-	/*
-	 * For the guest that is FWNMI capable, deliver all the MCE errors
-	 * (handled/unhandled) by exiting the guest with KVM_EXIT_NMI exit
-	 * reason. This new approach injects machine check errors in guest
-	 * address space to guest with additional information in the form
-	 * of RTAS event, thus enabling guest kernel to suitably handle
-	 * such errors.
-	 *
-	 * For the guest that is not FWNMI capable (old QEMU) fallback
-	 * to old behaviour for backward compatibility:
-	 * Deliver unhandled/fatal (e.g. UE) MCE errors to guest either
-	 * through machine check interrupt (set HSRR0 to 0x200).
-	 * For handled errors (no-fatal), just go back to guest execution
-	 * with current HSRR0.
-	 * if we receive machine check with MSR(RI=0) then deliver it to
-	 * guest as machine check causing guest to crash.
-	 */
-	ld	r11, VCPU_MSR(r9)
-	rldicl.	r0, r11, 64-MSR_HV_LG, 63 /* check if it happened in HV mode */
-	bne	guest_exit_cont		/* if so, exit to host */
-	/* Check if guest is capable of handling NMI exit */
-	ld	r10, VCPU_KVM(r9)
-	lbz	r10, KVM_FWNMI(r10)
-	cmpdi	r10, 1			/* FWNMI capable? */
-	beq	guest_exit_cont		/* if so, exit with KVM_EXIT_NMI. */
-
-	/* if not, fall through for backward compatibility. */
-	andi.	r10, r11, MSR_RI	/* check for unrecoverable exception */
-	beq	1f			/* Deliver a machine check to guest */
-	ld	r10, VCPU_PC(r9)
-	cmpdi	r3, 0		/* Did we handle MCE ? */
-	bne	2f	/* Continue guest execution. */
-	/* If not, deliver a machine check.  SRR0/1 are already set */
-1:	li	r10, BOOK3S_INTERRUPT_MACHINE_CHECK
-	bl	kvmppc_msr_interrupt
-2:	b	fast_interrupt_c_return
+	b	guest_exit_cont
 
 /*
  * Call C code to handle a HMI in real mode.