Merge tag 'powerpc-5.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Removal of the NPU DMA code, used by the out-of-tree Nvidia driver,
     as well as some other functions only used by drivers that haven't
     (yet?) made it upstream.

   - A fix for a bug in our handling of hardware watchpoints (eg. perf
     record -e mem: ...) which could lead to register corruption and
     kernel crashes.

   - Enable HAVE_ARCH_HUGE_VMAP, which allows us to use large pages for
     vmalloc when using the Radix MMU.

   - A large but incremental rewrite of our exception handling code to
     use gas macros rather than multiple levels of nested CPP macros.

  And the usual small fixes, cleanups and improvements.

  Thanks to: Alastair D'Silva, Alexey Kardashevskiy, Andreas Schwab,
  Aneesh Kumar K.V, Anju T Sudhakar, Anton Blanchard, Arnd Bergmann,
  Athira Rajeev, Cédric Le Goater, Christian Lamparter, Christophe
  Leroy, Christophe Lombard, Christoph Hellwig, Daniel Axtens, Denis
  Efremov, Enrico Weigelt, Frederic Barrat, Gautham R. Shenoy, Geert
  Uytterhoeven, Geliang Tang, Gen Zhang, Greg Kroah-Hartman, Greg Kurz,
  Gustavo Romero, Krzysztof Kozlowski, Madhavan Srinivasan, Masahiro
  Yamada, Mathieu Malaterre, Michael Neuling, Nathan Lynch, Naveen N.
  Rao, Nicholas Piggin, Nishad Kamdar, Oliver O'Halloran, Qian Cai, Ravi
  Bangoria, Sachin Sant, Sam Bobroff, Satheesh Rajendran, Segher
  Boessenkool, Shaokun Zhang, Shawn Anastasio, Stewart Smith, Suraj
  Jitindar Singh, Thiago Jung Bauermann, YueHaibing"

* tag 'powerpc-5.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (163 commits)
  powerpc/powernv/idle: Fix restore of SPRN_LDBAR for POWER9 stop state.
  powerpc/eeh: Handle hugepages in ioremap space
  ocxl: Update for AFU descriptor template version 1.1
  powerpc/boot: pass CONFIG options in a simpler and more robust way
  powerpc/boot: add {get, put}_unaligned_be32 to xz_config.h
  powerpc/irq: Don't WARN continuously in arch_local_irq_restore()
  powerpc/module64: Use symbolic instructions names.
  powerpc/module32: Use symbolic instructions names.
  powerpc: Move PPC_HA() PPC_HI() and PPC_LO() to ppc-opcode.h
  powerpc/module64: Fix comment in R_PPC64_ENTRY handling
  powerpc/boot: Add lzo support for uImage
  powerpc/boot: Add lzma support for uImage
  powerpc/boot: don't force gzipped uImage
  powerpc/8xx: Add microcode patch to move SMC parameter RAM.
  powerpc/8xx: Use IO accessors in microcode programming.
  powerpc/8xx: replace #ifdefs by IS_ENABLED() in microcode.c
  powerpc/8xx: refactor programming of microcode CPM params.
  powerpc/8xx: refactor printing of microcode patch name.
  powerpc/8xx: Refactor microcode write
  powerpc/8xx: refactor writing of CPM microcode arrays
  ...

5 files changed, 25 insertions, 19 deletions

diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index f53997a8ca62..711fca9bc6f0 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -38,6 +38,7 @@ config KVM_BOOK3S_32_HANDLER
 config KVM_BOOK3S_64_HANDLER
 	bool
 	select KVM_BOOK3S_HANDLER
+	select PPC_DAWR_FORCE_ENABLE
 
 config KVM_BOOK3S_PR_POSSIBLE
 	bool
@@ -183,9 +184,9 @@ config KVM_MPIC
 	select HAVE_KVM_MSI
 	help
 	  Enable support for emulating MPIC devices inside the
-          host kernel, rather than relying on userspace to emulate.
-          Currently, support is limited to certain versions of
-          Freescale's MPIC implementation.
+	  host kernel, rather than relying on userspace to emulate.
+	  Currently, support is limited to certain versions of
+	  Freescale's MPIC implementation.
 
 config KVM_XICS
 	bool "KVM in-kernel XICS emulation"
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 08b2dfbc5305..2d415c36a61d 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -361,12 +361,6 @@ 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 pmd_t *kvmppc_pmd_alloc(void)
 {
 	return kmem_cache_alloc(kvm_pmd_cache, GFP_KERNEL);
@@ -487,7 +481,7 @@ static void kvmppc_unmap_free_pud(struct kvm *kvm, pud_t *pud,
 	for (iu = 0; iu < PTRS_PER_PUD; ++iu, ++p) {
 		if (!pud_present(*p))
 			continue;
-		if (pud_huge(*p)) {
+		if (pud_is_leaf(*p)) {
 			pud_clear(p);
 		} else {
 			pmd_t *pmd;
@@ -586,7 +580,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 		new_pud = pud_alloc_one(kvm->mm, gpa);
 
 	pmd = NULL;
-	if (pud && pud_present(*pud) && !pud_huge(*pud))
+	if (pud && pud_present(*pud) && !pud_is_leaf(*pud))
 		pmd = pmd_offset(pud, gpa);
 	else if (level <= 1)
 		new_pmd = kvmppc_pmd_alloc();
@@ -609,7 +603,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 		new_pud = NULL;
 	}
 	pud = pud_offset(pgd, gpa);
-	if (pud_huge(*pud)) {
+	if (pud_is_leaf(*pud)) {
 		unsigned long hgpa = gpa & PUD_MASK;
 
 		/* Check if we raced and someone else has set the same thing */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 76b1801aa44a..ec1804f822af 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3603,6 +3603,8 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	vcpu->arch.slb_max = 0;
 	dec = mfspr(SPRN_DEC);
+	if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */
+		dec = (s32) dec;
 	tb = mftb();
 	vcpu->arch.dec_expires = dec + tb;
 	vcpu->cpu = -1;
@@ -4122,8 +4124,15 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
 
 	preempt_enable();
 
-	/* cancel pending decrementer exception if DEC is now positive */
-	if (get_tb() < vcpu->arch.dec_expires && kvmppc_core_pending_dec(vcpu))
+	/*
+	 * cancel pending decrementer exception if DEC is now positive, or if
+	 * entering a nested guest in which case the decrementer is now owned
+	 * by L2 and the L1 decrementer is provided in hdec_expires
+	 */
+	if (kvmppc_core_pending_dec(vcpu) &&
+			((get_tb() < vcpu->arch.dec_expires) ||
+			 (trap == BOOK3S_INTERRUPT_SYSCALL &&
+			  kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED)))
 		kvmppc_core_dequeue_dec(vcpu);
 
 	trace_kvm_guest_exit(vcpu);
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index cb05ccc8bc6a..7c1909657b55 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -820,6 +820,8 @@ static void flush_guest_tlb(struct kvm *kvm)
 				     : : "r" (rb), "i" (1), "i" (1), "i" (0),
 				       "r" (0) : "memory");
 		}
+		asm volatile("ptesync": : :"memory");
+		asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory");
 	} else {
 		for (set = 0; set < kvm->arch.tlb_sets; ++set) {
 			/* R=0 PRS=0 RIC=0 */
@@ -828,9 +830,9 @@ static void flush_guest_tlb(struct kvm *kvm)
 				       "r" (0) : "memory");
 			rb += PPC_BIT(51);	/* increment set number */
 		}
+		asm volatile("ptesync": : :"memory");
+		asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory");
 	}
-	asm volatile("ptesync": : :"memory");
-	asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
 }
 
 void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
index 229496e2652e..0db937497169 100644
--- a/arch/powerpc/kvm/book3s_hv_tm.c
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -128,7 +128,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		}
 		/* Set CR0 to indicate previous transactional state */
 		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
-			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		/* L=1 => tresume, L=0 => tsuspend */
 		if (instr & (1 << 21)) {
 			if (MSR_TM_SUSPENDED(msr))
@@ -172,7 +172,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 
 		/* Set CR0 to indicate previous transactional state */
 		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
-			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		vcpu->arch.shregs.msr &= ~MSR_TS_MASK;
 		return RESUME_GUEST;
 
@@ -202,7 +202,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 
 		/* Set CR0 to indicate previous transactional state */
 		vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
-			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+			(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
 		vcpu->arch.shregs.msr = msr | MSR_TS_S;
 		return RESUME_GUEST;
 	}