Merge tag 'powerpc-4.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Nothing really major this release, despite quite a lot of activity.
  Just lots of things all over the place.

  Some things of note include:

   - Access via perf to a new type of PMU (IMC) on Power9, which can
     count both core events as well as nest unit events (Memory
     controller etc).

   - Optimisations to the radix MMU TLB flushing, mostly to avoid
     unnecessary Page Walk Cache (PWC) flushes when the structure of the
     tree is not changing.

   - Reworks/cleanups of do_page_fault() to modernise it and bring it
     closer to other architectures where possible.

   - Rework of our page table walking so that THP updates only need to
     send IPIs to CPUs where the affected mm has run, rather than all
     CPUs.

   - The size of our vmalloc area is increased to 56T on 64-bit hash MMU
     systems. This avoids problems with the percpu allocator on systems
     with very sparse NUMA layouts.

   - STRICT_KERNEL_RWX support on PPC32.

   - A new sched domain topology for Power9, to capture the fact that
     pairs of cores may share an L2 cache.

   - Power9 support for VAS, which is a new mechanism for accessing
     coprocessors, and initial support for using it with the NX
     compression accelerator.

   - Major work on the instruction emulation support, adding support for
     many new instructions, and reworking it so it can be used to
     implement the emulation needed to fixup alignment faults.

   - Support for guests under PowerVM to use the Power9 XIVE interrupt
     controller.

  And probably that many things again that are almost as interesting,
  but I had to keep the list short. Plus the usual fixes and cleanups as
  always.

  Thanks to: Alexey Kardashevskiy, Alistair Popple, Andreas Schwab,
  Aneesh Kumar K.V, Anju T Sudhakar, Arvind Yadav, Balbir Singh,
  Benjamin Herrenschmidt, Bhumika Goyal, Breno Leitao, Bryant G. Ly,
  Christophe Leroy, Cédric Le Goater, Dan Carpenter, Dou Liyang,
  Frederic Barrat, Gautham R. Shenoy, Geliang Tang, Geoff Levand, Hannes
  Reinecke, Haren Myneni, Ivan Mikhaylov, John Allen, Julia Lawall,
  LABBE Corentin, Laurentiu Tudor, Madhavan Srinivasan, Markus Elfring,
  Masahiro Yamada, Matt Brown, Michael Neuling, Murilo Opsfelder Araujo,
  Nathan Fontenot, Naveen N. Rao, Nicholas Piggin, Oliver O'Halloran,
  Paul Mackerras, Rashmica Gupta, Rob Herring, Rui Teng, Sam Bobroff,
  Santosh Sivaraj, Scott Wood, Shilpasri G Bhat, Sukadev Bhattiprolu,
  Suraj Jitindar Singh, Tobin C. Harding, Victor Aoqui"

* tag 'powerpc-4.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (321 commits)
  powerpc/xive: Fix section __init warning
  powerpc: Fix kernel crash in emulation of vector loads and stores
  powerpc/xive: improve debugging macros
  powerpc/xive: add XIVE Exploitation Mode to CAS
  powerpc/xive: introduce H_INT_ESB hcall
  powerpc/xive: add the HW IRQ number under xive_irq_data
  powerpc/xive: introduce xive_esb_write()
  powerpc/xive: rename xive_poke_esb() in xive_esb_read()
  powerpc/xive: guest exploitation of the XIVE interrupt controller
  powerpc/xive: introduce a common routine xive_queue_page_alloc()
  powerpc/sstep: Avoid used uninitialized error
  axonram: Return directly after a failed kzalloc() in axon_ram_probe()
  axonram: Improve a size determination in axon_ram_probe()
  axonram: Delete an error message for a failed memory allocation in axon_ram_probe()
  powerpc/powernv/npu: Move tlb flush before launching ATSD
  powerpc/macintosh: constify wf_sensor_ops structures
  powerpc/iommu: Use permission-specific DEVICE_ATTR variants
  powerpc/eeh: Delete an error out of memory message at init time
  powerpc/mm: Use seq_putc() in two functions
  macintosh: Convert to using %pOF instead of full_name
  ...

7 files changed, 61 insertions, 30 deletions

diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index b42812e014c0..67075e065ef2 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -37,6 +37,7 @@
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
 #include <asm/cputable.h>
+#include <asm/pte-walk.h>
 
 #include "trace_hv.h"
 
@@ -599,8 +600,8 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			 * hugepage split and collapse.
 			 */
 			local_irq_save(flags);
-			ptep = find_linux_pte_or_hugepte(current->mm->pgd,
-							 hva, NULL, NULL);
+			ptep = find_current_mm_pte(current->mm->pgd,
+						   hva, NULL, NULL);
 			if (ptep) {
 				pte = kvmppc_read_update_linux_pte(ptep, 1);
 				if (__pte_write(pte))
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index f6b3e67c5762..c5d7435455f1 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -17,6 +17,7 @@
 #include <asm/mmu.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
+#include <asm/pte-walk.h>
 
 /*
  * Supported radix tree geometry.
@@ -322,13 +323,13 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	gpa = vcpu->arch.fault_gpa & ~0xfffUL;
 	gpa &= ~0xF000000000000000ul;
 	gfn = gpa >> PAGE_SHIFT;
-	if (!(dsisr & DSISR_PGDIRFAULT))
+	if (!(dsisr & DSISR_PRTABLE_FAULT))
 		gpa |= ea & 0xfff;
 	memslot = gfn_to_memslot(kvm, gfn);
 
 	/* No memslot means it's an emulated MMIO region */
 	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
-		if (dsisr & (DSISR_PGDIRFAULT | DSISR_BADACCESS |
+		if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS |
 			     DSISR_SET_RC)) {
 			/*
 			 * Bad address in guest page table tree, or other
@@ -359,8 +360,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		if (writing)
 			pgflags |= _PAGE_DIRTY;
 		local_irq_save(flags);
-		ptep = __find_linux_pte_or_hugepte(current->mm->pgd, hva,
-						   NULL, NULL);
+		ptep = find_current_mm_pte(current->mm->pgd, hva, NULL, NULL);
 		if (ptep) {
 			pte = READ_ONCE(*ptep);
 			if (pte_present(pte) &&
@@ -374,8 +374,12 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				spin_unlock(&kvm->mmu_lock);
 				return RESUME_GUEST;
 			}
-			ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable,
-							gpa, NULL, &shift);
+			/*
+			 * We are walking the secondary page table here. We can do this
+			 * without disabling irq.
+			 */
+			ptep = __find_linux_pte(kvm->arch.pgtable,
+						gpa, NULL, &shift);
 			if (ptep && pte_present(*ptep)) {
 				kvmppc_radix_update_pte(kvm, ptep, 0, pgflags,
 							gpa, shift);
@@ -427,8 +431,8 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			pgflags |= _PAGE_WRITE;
 		} else {
 			local_irq_save(flags);
-			ptep = __find_linux_pte_or_hugepte(current->mm->pgd,
-							hva, NULL, NULL);
+			ptep = find_current_mm_pte(current->mm->pgd,
+						   hva, NULL, NULL);
 			if (ptep && pte_write(*ptep) && pte_dirty(*ptep))
 				pgflags |= _PAGE_WRITE;
 			local_irq_restore(flags);
@@ -499,8 +503,7 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	unsigned int shift;
 	unsigned long old;
 
-	ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa,
-					   NULL, &shift);
+	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep)) {
 		old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT, 0,
 					      gpa, shift);
@@ -525,8 +528,7 @@ int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	unsigned int shift;
 	int ref = 0;
 
-	ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa,
-					   NULL, &shift);
+	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep) && pte_young(*ptep)) {
 		kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0,
 					gpa, shift);
@@ -545,8 +547,7 @@ int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	unsigned int shift;
 	int ref = 0;
 
-	ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa,
-					   NULL, &shift);
+	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep) && pte_young(*ptep))
 		ref = 1;
 	return ref;
@@ -562,8 +563,7 @@ static int kvm_radix_test_clear_dirty(struct kvm *kvm,
 	unsigned int shift;
 	int ret = 0;
 
-	ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa,
-					   NULL, &shift);
+	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep) && pte_dirty(*ptep)) {
 		ret = 1;
 		if (shift)
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 3adfd2f5301c..c32e9bfe75b1 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -39,6 +39,7 @@
 #include <asm/udbg.h>
 #include <asm/iommu.h>
 #include <asm/tce.h>
+#include <asm/pte-walk.h>
 
 #ifdef CONFIG_BUG
 
@@ -353,7 +354,16 @@ static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu,
 	pte_t *ptep, pte;
 	unsigned shift = 0;
 
-	ptep = __find_linux_pte_or_hugepte(vcpu->arch.pgdir, ua, NULL, &shift);
+	/*
+	 * Called in real mode with MSR_EE = 0. We are safe here.
+	 * It is ok to do the lookup with arch.pgdir here, because
+	 * we are doing this on secondary cpus and current task there
+	 * is not the hypervisor. Also this is safe against THP in the
+	 * host, because an IPI to primary thread will wait for the secondary
+	 * to exit which will agains result in the below page table walk
+	 * to finish.
+	 */
+	ptep = __find_linux_pte(vcpu->arch.pgdir, ua, NULL, &shift);
 	if (!ptep || !pte_present(*ptep))
 		return -ENXIO;
 	pte = *ptep;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 359c79cdf0cc..ebcf97cb5c98 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2111,6 +2111,15 @@ static int kvmppc_grab_hwthread(int cpu)
 	struct paca_struct *tpaca;
 	long timeout = 10000;
 
+	/*
+	 * ISA v3.0 idle routines do not set hwthread_state or test
+	 * hwthread_req, so they can not grab idle threads.
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		WARN(1, "KVM: can not control sibling threads\n");
+		return -EBUSY;
+	}
+
 	tpaca = &paca[cpu];
 
 	/* Ensure the thread won't go into the kernel if it wakes */
@@ -2145,10 +2154,12 @@ static void kvmppc_release_hwthread(int cpu)
 	struct paca_struct *tpaca;
 
 	tpaca = &paca[cpu];
-	tpaca->kvm_hstate.hwthread_req = 0;
 	tpaca->kvm_hstate.kvm_vcpu = NULL;
 	tpaca->kvm_hstate.kvm_vcore = NULL;
 	tpaca->kvm_hstate.kvm_split_mode = NULL;
+	if (!cpu_has_feature(CPU_FTR_ARCH_300))
+		tpaca->kvm_hstate.hwthread_req = 0;
+
 }
 
 static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 584c74c8119f..fedb0139524c 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -22,6 +22,7 @@
 #include <asm/hvcall.h>
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
+#include <asm/pte-walk.h>
 
 /* Translate address of a vmalloc'd thing to a linear map address */
 static void *real_vmalloc_addr(void *x)
@@ -31,9 +32,9 @@ static void *real_vmalloc_addr(void *x)
 	/*
 	 * assume we don't have huge pages in vmalloc space...
 	 * So don't worry about THP collapse/split. Called
-	 * Only in realmode, hence won't need irq_save/restore.
+	 * Only in realmode with MSR_EE = 0, hence won't need irq_save/restore.
 	 */
-	p = __find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL, NULL);
+	p = find_init_mm_pte(addr, NULL);
 	if (!p || !pte_present(*p))
 		return NULL;
 	addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK);
@@ -230,14 +231,13 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	 * If we had a page table table change after lookup, we would
 	 * retry via mmu_notifier_retry.
 	 */
-	if (realmode)
-		ptep = __find_linux_pte_or_hugepte(pgdir, hva, NULL,
-						   &hpage_shift);
-	else {
+	if (!realmode)
 		local_irq_save(irq_flags);
-		ptep = find_linux_pte_or_hugepte(pgdir, hva, NULL,
-						 &hpage_shift);
-	}
+	/*
+	 * If called in real mode we have MSR_EE = 0. Otherwise
+	 * we disable irq above.
+	 */
+	ptep = __find_linux_pte(pgdir, hva, NULL, &hpage_shift);
 	if (ptep) {
 		pte_t pte;
 		unsigned int host_pte_size;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 9c9c983b864f..2259b6cde119 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -149,9 +149,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	subf	r4, r4, r3
 	mtspr	SPRN_DEC, r4
 
+BEGIN_FTR_SECTION
 	/* hwthread_req may have got set by cede or no vcpu, so clear it */
 	li	r0, 0
 	stb	r0, HSTATE_HWTHREAD_REQ(r13)
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 
 	/*
 	 * For external interrupts we need to call the Linux
@@ -314,6 +316,7 @@ kvm_novcpu_exit:
  * Relocation is off and most register values are lost.
  * r13 points to the PACA.
  * r3 contains the SRR1 wakeup value, SRR1 is trashed.
+ * This is not used by ISAv3.0B processors.
  */
 	.globl	kvm_start_guest
 kvm_start_guest:
@@ -432,6 +435,9 @@ kvm_secondary_got_guest:
  * While waiting we also need to check if we get given a vcpu to run.
  */
 kvm_no_guest:
+BEGIN_FTR_SECTION
+	twi	31,0,0
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	lbz	r3, HSTATE_HWTHREAD_REQ(r13)
 	cmpwi	r3, 0
 	bne	53f
@@ -2512,8 +2518,10 @@ kvm_do_nap:
 	clrrdi	r0, r0, 1
 	mtspr	SPRN_CTRLT, r0
 
+BEGIN_FTR_SECTION
 	li	r0,1
 	stb	r0,HSTATE_HWTHREAD_REQ(r13)
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mfspr	r5,SPRN_LPCR
 	ori	r5,r5,LPCR_PECE0 | LPCR_PECE1
 BEGIN_FTR_SECTION
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 77fd043b3ecc..c6c734424c70 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -30,6 +30,7 @@
 #include <linux/vmalloc.h>
 #include <linux/hugetlb.h>
 #include <asm/kvm_ppc.h>
+#include <asm/pte-walk.h>
 
 #include "e500.h"
 #include "timing.h"
@@ -476,7 +477,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	 * can't run hence pfn won't change.
 	 */
 	local_irq_save(flags);
-	ptep = find_linux_pte_or_hugepte(pgdir, hva, NULL, NULL);
+	ptep = find_linux_pte(pgdir, hva, NULL, NULL);
 	if (ptep) {
 		pte_t pte = READ_ONCE(*ptep);