Merge branch 'topic/ppc-kvm' into next

Pull in some more ppc KVM patches we are keeping in our topic branch.

In particular this brings in the series to add H_RPT_INVALIDATE.

Documentation/virt/kvm/api.rst

@@ -6362,6 +6362,24 @@ default.
 
 See Documentation/x86/sgx/2.Kernel-internals.rst for more details.
 
+7.26 KVM_CAP_PPC_RPT_INVALIDATE
+-------------------------------
+
+:Capability: KVM_CAP_PPC_RPT_INVALIDATE
+:Architectures: ppc
+:Type: vm
+
+This capability indicates that the kernel is capable of handling
+H_RPT_INVALIDATE hcall.
+
+In order to enable the use of H_RPT_INVALIDATE in the guest,
+user space might have to advertise it for the guest. For example,
+IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is
+present in the "ibm,hypertas-functions" device-tree property.
+
+This capability is enabled for hypervisors on platforms like POWER9
+that support radix MMU.
+
 8. Other capabilities.
 ======================
 

arch/powerpc/include/asm/book3s/64/mmu.h

@@ -19,6 +19,7 @@ struct mmu_psize_def {
 	int		penc[MMU_PAGE_COUNT];	/* HPTE encoding */
 	unsigned int	tlbiel;	/* tlbiel supported for that page size */
 	unsigned long	avpnm;	/* bits to mask out in AVPN in the HPTE */
+	unsigned long   h_rpt_pgsize; /* H_RPT_INVALIDATE page size encoding */
 	union {
 		unsigned long	sllp;	/* SLB L||LP (exact mask to use in slbmte) */
 		unsigned long ap;	/* Ap encoding used by PowerISA 3.0 */

arch/powerpc/include/asm/book3s/64/tlbflush-radix.h

@@ -4,6 +4,10 @@
 
 #include <asm/hvcall.h>
 
+#define RIC_FLUSH_TLB 0
+#define RIC_FLUSH_PWC 1
+#define RIC_FLUSH_ALL 2
+
 struct vm_area_struct;
 struct mm_struct;
 struct mmu_gather;

arch/powerpc/include/asm/cputhreads.h

@@ -98,6 +98,36 @@ static inline int cpu_last_thread_sibling(int cpu)
 	return cpu | (threads_per_core - 1);
 }
 
+/*
+ * tlb_thread_siblings are siblings which share a TLB. This is not
+ * architected, is not something a hypervisor could emulate and a future
+ * CPU may change behaviour even in compat mode, so this should only be
+ * used on PowerNV, and only with care.
+ */
+static inline int cpu_first_tlb_thread_sibling(int cpu)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+		return cpu & ~0x6;	/* Big Core */
+	else
+		return cpu_first_thread_sibling(cpu);
+}
+
+static inline int cpu_last_tlb_thread_sibling(int cpu)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+		return cpu | 0x6;	/* Big Core */
+	else
+		return cpu_last_thread_sibling(cpu);
+}
+
+static inline int cpu_tlb_thread_sibling_step(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+		return 2;		/* Big Core */
+	else
+		return 1;
+}
+
 static inline u32 get_tensr(void)
 {
 #ifdef	CONFIG_BOOKE

arch/powerpc/include/asm/hvcall.h

@@ -423,9 +423,9 @@
 #define H_RPTI_TYPE_NESTED	0x0001	/* Invalidate nested guest partition-scope */
 #define H_RPTI_TYPE_TLB		0x0002	/* Invalidate TLB */
 #define H_RPTI_TYPE_PWC		0x0004	/* Invalidate Page Walk Cache */
-/* Invalidate Process Table Entries if H_RPTI_TYPE_NESTED is clear */
+/* Invalidate caching of Process Table Entries if H_RPTI_TYPE_NESTED is clear */
 #define H_RPTI_TYPE_PRT		0x0008
-/* Invalidate Partition Table Entries if H_RPTI_TYPE_NESTED is set */
+/* Invalidate caching of Partition Table Entries if H_RPTI_TYPE_NESTED is set */
 #define H_RPTI_TYPE_PAT		0x0008
 #define H_RPTI_TYPE_ALL		(H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC | \
 				 H_RPTI_TYPE_PRT)

arch/powerpc/include/asm/kvm_book3s.h

@@ -307,6 +307,9 @@ void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1);
 void kvmhv_release_all_nested(struct kvm *kvm);
 long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
 long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu);
+long do_h_rpt_invalidate_pat(struct kvm_vcpu *vcpu, unsigned long lpid,
+			     unsigned long type, unsigned long pg_sizes,
+			     unsigned long start, unsigned long end);
 int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu,
 			  u64 time_limit, unsigned long lpcr);
 void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr);

arch/powerpc/include/asm/mmu_context.h

@@ -215,6 +215,18 @@ static inline void mm_context_add_copro(struct mm_struct *mm) { }
 static inline void mm_context_remove_copro(struct mm_struct *mm) { }
 #endif
 
+#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)
+void do_h_rpt_invalidate_prt(unsigned long pid, unsigned long lpid,
+			     unsigned long type, unsigned long pg_sizes,
+			     unsigned long start, unsigned long end);
+#else
+static inline void do_h_rpt_invalidate_prt(unsigned long pid,
+					   unsigned long lpid,
+					   unsigned long type,
+					   unsigned long pg_sizes,
+					   unsigned long start,
+					   unsigned long end) { }
+#endif
 
 extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			       struct task_struct *tsk);

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -21,6 +21,7 @@
 #include <asm/pte-walk.h>
 #include <asm/ultravisor.h>
 #include <asm/kvm_book3s_uvmem.h>
+#include <asm/plpar_wrappers.h>
 
 /*
  * Supported radix tree geometry.
@@ -318,9 +319,19 @@ void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
 	}
 
 	psi = shift_to_mmu_psize(pshift);
-	rb = addr | (mmu_get_ap(psi) << PPC_BITLSHIFT(58));
-	rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(0, 0, 1),
-				lpid, rb);
+
+	if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE)) {
+		rb = addr | (mmu_get_ap(psi) << PPC_BITLSHIFT(58));
+		rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(0, 0, 1),
+					lpid, rb);
+	} else {
+		rc = pseries_rpt_invalidate(lpid, H_RPTI_TARGET_CMMU,
+					    H_RPTI_TYPE_NESTED |
+					    H_RPTI_TYPE_TLB,
+					    psize_to_rpti_pgsize(psi),
+					    addr, addr + psize);
+	}
+
 	if (rc)
 		pr_err("KVM: TLB page invalidation hcall failed, rc=%ld\n", rc);
 }
@@ -334,8 +345,14 @@ static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned int lpid)
 		return;
 	}
 
-	rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(1, 0, 1),
-				lpid, TLBIEL_INVAL_SET_LPID);
+	if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE))
+		rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(1, 0, 1),
+					lpid, TLBIEL_INVAL_SET_LPID);
+	else
+		rc = pseries_rpt_invalidate(lpid, H_RPTI_TARGET_CMMU,
+					    H_RPTI_TYPE_NESTED |
+					    H_RPTI_TYPE_PWC, H_RPTI_PAGE_ALL,
+					    0, -1UL);
 	if (rc)
 		pr_err("KVM: TLB PWC invalidation hcall failed, rc=%ld\n", rc);
 }

arch/powerpc/kvm/book3s_hv.c

@@ -76,6 +76,7 @@
 #include <asm/kvm_book3s_uvmem.h>
 #include <asm/ultravisor.h>
 #include <asm/dtl.h>
+#include <asm/plpar_wrappers.h>
 
 #include "book3s.h"
 
@@ -922,6 +923,68 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu)
 	return yield_count;
 }
 
+/*
+ * H_RPT_INVALIDATE hcall handler for nested guests.
+ *
+ * Handles only nested process-scoped invalidation requests in L0.
+ */
+static int kvmppc_nested_h_rpt_invalidate(struct kvm_vcpu *vcpu)
+{
+	unsigned long type = kvmppc_get_gpr(vcpu, 6);
+	unsigned long pid, pg_sizes, start, end;
+
+	/*
+	 * The partition-scoped invalidations aren't handled here in L0.
+	 */
+	if (type & H_RPTI_TYPE_NESTED)
+		return RESUME_HOST;
+
+	pid = kvmppc_get_gpr(vcpu, 4);
+	pg_sizes = kvmppc_get_gpr(vcpu, 7);
+	start = kvmppc_get_gpr(vcpu, 8);
+	end = kvmppc_get_gpr(vcpu, 9);
+
+	do_h_rpt_invalidate_prt(pid, vcpu->arch.nested->shadow_lpid,
+				type, pg_sizes, start, end);
+
+	kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
+	return RESUME_GUEST;
+}
+
+static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu,
+				    unsigned long id, unsigned long target,
+				    unsigned long type, unsigned long pg_sizes,
+				    unsigned long start, unsigned long end)
+{
+	if (!kvm_is_radix(vcpu->kvm))
+		return H_UNSUPPORTED;
+
+	if (end < start)
+		return H_P5;
+
+	/*
+	 * Partition-scoped invalidation for nested guests.
+	 */
+	if (type & H_RPTI_TYPE_NESTED) {
+		if (!nesting_enabled(vcpu->kvm))
+			return H_FUNCTION;
+
+		/* Support only cores as target */
+		if (target != H_RPTI_TARGET_CMMU)
+			return H_P2;
+
+		return do_h_rpt_invalidate_pat(vcpu, id, type, pg_sizes,
+					       start, end);
+	}
+
+	/*
+	 * Process-scoped invalidation for L1 guests.
+	 */
+	do_h_rpt_invalidate_prt(id, vcpu->kvm->arch.lpid,
+				type, pg_sizes, start, end);
+	return H_SUCCESS;
+}
+
 int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -1105,6 +1168,14 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		if (!powernv_get_random_long(&vcpu->arch.regs.gpr[4]))
 			ret = H_HARDWARE;
 		break;
+	case H_RPT_INVALIDATE:
+		ret = kvmppc_h_rpt_invalidate(vcpu, kvmppc_get_gpr(vcpu, 4),
+					      kvmppc_get_gpr(vcpu, 5),
+					      kvmppc_get_gpr(vcpu, 6),
+					      kvmppc_get_gpr(vcpu, 7),
+					      kvmppc_get_gpr(vcpu, 8),
+					      kvmppc_get_gpr(vcpu, 9));
+		break;
 
 	case H_SET_PARTITION_TABLE:
 		ret = H_FUNCTION;
@@ -1225,6 +1296,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
 	case H_XIRR_X:
 #endif
 	case H_PAGE_INIT:
+	case H_RPT_INVALIDATE:
 		return 1;
 	}
 
@@ -1748,6 +1820,23 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 		if (!xics_on_xive())
 			kvmppc_xics_rm_complete(vcpu, 0);
 		break;
+	case BOOK3S_INTERRUPT_SYSCALL:
+	{
+		unsigned long req = kvmppc_get_gpr(vcpu, 3);
+
+		/*
+		 * The H_RPT_INVALIDATE hcalls issued by nested
+		 * guests for process-scoped invalidations when
+		 * GTSE=0, are handled here in L0.
+		 */
+		if (req == H_RPT_INVALIDATE) {
+			r = kvmppc_nested_h_rpt_invalidate(vcpu);
+			break;
+		}
+
+		r = RESUME_HOST;
+		break;
+	}
 	default:
 		r = RESUME_HOST;
 		break;
@@ -2820,7 +2909,7 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
 	cpumask_t *cpu_in_guest;
 	int i;
 
-	cpu = cpu_first_thread_sibling(cpu);
+	cpu = cpu_first_tlb_thread_sibling(cpu);
 	if (nested) {
 		cpumask_set_cpu(cpu, &nested->need_tlb_flush);
 		cpu_in_guest = &nested->cpu_in_guest;
@@ -2834,9 +2923,10 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu)
 	 * the other side is the first smp_mb() in kvmppc_run_core().
 	 */
 	smp_mb();
-	for (i = 0; i < threads_per_core; ++i)
-		if (cpumask_test_cpu(cpu + i, cpu_in_guest))
-			smp_call_function_single(cpu + i, do_nothing, NULL, 1);
+	for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu);
+					i += cpu_tlb_thread_sibling_step())
+		if (cpumask_test_cpu(i, cpu_in_guest))
+			smp_call_function_single(i, do_nothing, NULL, 1);
 }
 
 static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
@@ -2867,8 +2957,8 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
 	 */
 	if (prev_cpu != pcpu) {
 		if (prev_cpu >= 0 &&
-		    cpu_first_thread_sibling(prev_cpu) !=
-		    cpu_first_thread_sibling(pcpu))
+		    cpu_first_tlb_thread_sibling(prev_cpu) !=
+		    cpu_first_tlb_thread_sibling(pcpu))
 			radix_flush_cpu(kvm, prev_cpu, vcpu);
 		if (nested)
 			nested->prev_cpu[vcpu->arch.nested_vcpu_id] = pcpu;

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -721,7 +721,7 @@ void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
 	 * Thus we make all 4 threads use the same bit.
 	 */
 	if (cpu_has_feature(CPU_FTR_ARCH_300))
-		pcpu = cpu_first_thread_sibling(pcpu);
+		pcpu = cpu_first_tlb_thread_sibling(pcpu);
 
 	if (nested)
 		need_tlb_flush = &nested->need_tlb_flush;

arch/powerpc/kvm/book3s_hv_nested.c

@@ -19,6 +19,7 @@
 #include <asm/pgalloc.h>
 #include <asm/pte-walk.h>
 #include <asm/reg.h>
+#include <asm/plpar_wrappers.h>
 
 static struct patb_entry *pseries_partition_tb;
 
@@ -53,7 +54,8 @@ void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
 	hr->dawrx1 = vcpu->arch.dawrx1;
 }
 
-static void byteswap_pt_regs(struct pt_regs *regs)
+/* Use noinline_for_stack due to https://bugs.llvm.org/show_bug.cgi?id=49610 */
+static noinline_for_stack void byteswap_pt_regs(struct pt_regs *regs)
 {
 	unsigned long *addr = (unsigned long *) regs;
 
@@ -467,8 +469,15 @@ static void kvmhv_flush_lpid(unsigned int lpid)
 		return;
 	}
 
-	rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(2, 0, 1),
-				lpid, TLBIEL_INVAL_SET_LPID);
+	if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE))
+		rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(2, 0, 1),
+					lpid, TLBIEL_INVAL_SET_LPID);
+	else
+		rc = pseries_rpt_invalidate(lpid, H_RPTI_TARGET_CMMU,
+					    H_RPTI_TYPE_NESTED |
+					    H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC |
+					    H_RPTI_TYPE_PAT,
+					    H_RPTI_PAGE_ALL, 0, -1UL);
 	if (rc)
 		pr_err("KVM: TLB LPID invalidation hcall failed, rc=%ld\n", rc);
 }
@@ -1214,6 +1223,113 @@ long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu)
 	return H_SUCCESS;
 }
 
+static long do_tlb_invalidate_nested_all(struct kvm_vcpu *vcpu,
+					 unsigned long lpid, unsigned long ric)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_nested_guest *gp;
+
+	gp = kvmhv_get_nested(kvm, lpid, false);
+	if (gp) {
+		kvmhv_emulate_tlbie_lpid(vcpu, gp, ric);
+		kvmhv_put_nested(gp);
+	}
+	return H_SUCCESS;
+}
+
+/*
+ * Number of pages above which we invalidate the entire LPID rather than
+ * flush individual pages.
+ */
+static unsigned long tlb_range_flush_page_ceiling __read_mostly = 33;
+
+static long do_tlb_invalidate_nested_tlb(struct kvm_vcpu *vcpu,
+					 unsigned long lpid,
+					 unsigned long pg_sizes,
+					 unsigned long start,
+					 unsigned long end)
+{
+	int ret = H_P4;
+	unsigned long addr, nr_pages;
+	struct mmu_psize_def *def;
+	unsigned long psize, ap, page_size;
+	bool flush_lpid;
+
+	for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
+		def = &mmu_psize_defs[psize];
+		if (!(pg_sizes & def->h_rpt_pgsize))
+			continue;
+
+		nr_pages = (end - start) >> def->shift;
+		flush_lpid = nr_pages > tlb_range_flush_page_ceiling;
+		if (flush_lpid)
+			return do_tlb_invalidate_nested_all(vcpu, lpid,
+							RIC_FLUSH_TLB);
+		addr = start;
+		ap = mmu_get_ap(psize);
+		page_size = 1UL << def->shift;
+		do {
+			ret = kvmhv_emulate_tlbie_tlb_addr(vcpu, lpid, ap,
+						   get_epn(addr));
+			if (ret)
+				return H_P4;
+			addr += page_size;
+		} while (addr < end);
+	}
+	return ret;
+}
+
+/*
+ * Performs partition-scoped invalidations for nested guests
+ * as part of H_RPT_INVALIDATE hcall.
+ */
+long do_h_rpt_invalidate_pat(struct kvm_vcpu *vcpu, unsigned long lpid,
+			     unsigned long type, unsigned long pg_sizes,
+			     unsigned long start, unsigned long end)
+{
+	/*
+	 * If L2 lpid isn't valid, we need to return H_PARAMETER.
+	 *
+	 * However, nested KVM issues a L2 lpid flush call when creating
+	 * partition table entries for L2. This happens even before the
+	 * corresponding shadow lpid is created in HV which happens in
+	 * H_ENTER_NESTED call. Since we can't differentiate this case from
+	 * the invalid case, we ignore such flush requests and return success.
+	 */
+	if (!kvmhv_find_nested(vcpu->kvm, lpid))
+		return H_SUCCESS;
+
+	/*
+	 * A flush all request can be handled by a full lpid flush only.
+	 */
+	if ((type & H_RPTI_TYPE_NESTED_ALL) == H_RPTI_TYPE_NESTED_ALL)
+		return do_tlb_invalidate_nested_all(vcpu, lpid, RIC_FLUSH_ALL);
+
+	/*
+	 * We don't need to handle a PWC flush like process table here,
+	 * because intermediate partition scoped table in nested guest doesn't
+	 * really have PWC. Only level we have PWC is in L0 and for nested
+	 * invalidate at L0 we always do kvm_flush_lpid() which does
+	 * radix__flush_all_lpid(). For range invalidate at any level, we
+	 * are not removing the higher level page tables and hence there is
+	 * no PWC invalidate needed.
+	 *
+	 * if (type & H_RPTI_TYPE_PWC) {
+	 *	ret = do_tlb_invalidate_nested_all(vcpu, lpid, RIC_FLUSH_PWC);
+	 *	if (ret)
+	 *		return H_P4;
+	 * }
+	 */
+
+	if (start == 0 && end == -1)
+		return do_tlb_invalidate_nested_all(vcpu, lpid, RIC_FLUSH_TLB);
+
+	if (type & H_RPTI_TYPE_TLB)
+		return do_tlb_invalidate_nested_tlb(vcpu, lpid, pg_sizes,
+						    start, end);
+	return H_SUCCESS;
+}
+
 /* Used to convert a nested guest real address to a L1 guest real address */
 static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu,
 				       struct kvm_nested_guest *gp,

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -60,7 +60,7 @@ static int global_invalidates(struct kvm *kvm)
 		 * so use the bit for the first thread to represent the core.
 		 */
 		if (cpu_has_feature(CPU_FTR_ARCH_300))
-			cpu = cpu_first_thread_sibling(cpu);
+			cpu = cpu_first_tlb_thread_sibling(cpu);
 		cpumask_clear_cpu(cpu, &kvm->arch.need_tlb_flush);
 	}
 

arch/powerpc/kvm/powerpc.c

@@ -682,6 +682,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = !!(hv_enabled && kvmppc_hv_ops->enable_dawr1 &&
 		       !kvmppc_hv_ops->enable_dawr1(NULL));
 		break;
+	case KVM_CAP_PPC_RPT_INVALIDATE:
+		r = 1;
+		break;
 #endif
 	default:
 		r = 0;

arch/powerpc/mm/book3s64/radix_pgtable.c

@@ -475,6 +475,7 @@ static int __init radix_dt_scan_page_sizes(unsigned long node,
 		def = &mmu_psize_defs[idx];
 		def->shift = shift;
 		def->ap  = ap;
+		def->h_rpt_pgsize = psize_to_rpti_pgsize(idx);
 	}
 
 	/* needed ? */
@@ -549,9 +550,13 @@ void __init radix__early_init_devtree(void)
 		 */
 		mmu_psize_defs[MMU_PAGE_4K].shift = 12;
 		mmu_psize_defs[MMU_PAGE_4K].ap = 0x0;
+		mmu_psize_defs[MMU_PAGE_4K].h_rpt_pgsize =
+			psize_to_rpti_pgsize(MMU_PAGE_4K);
 
 		mmu_psize_defs[MMU_PAGE_64K].shift = 16;
 		mmu_psize_defs[MMU_PAGE_64K].ap = 0x5;
+		mmu_psize_defs[MMU_PAGE_64K].h_rpt_pgsize =
+			psize_to_rpti_pgsize(MMU_PAGE_64K);
 	}
 
 	/*

arch/powerpc/mm/book3s64/radix_tlb.c

@@ -20,10 +20,6 @@
 
 #include "internal.h"
 
-#define RIC_FLUSH_TLB 0
-#define RIC_FLUSH_PWC 1
-#define RIC_FLUSH_ALL 2
-
 /*
  * tlbiel instruction for radix, set invalidation
  * i.e., r=1 and is=01 or is=10 or is=11
@@ -130,6 +126,21 @@ static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric)
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
+static __always_inline void __tlbie_pid_lpid(unsigned long pid,
+					     unsigned long lpid,
+					     unsigned long ric)
+{
+	unsigned long rb, rs, prs, r;
+
+	rb = PPC_BIT(53); /* IS = 1 */
+	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
+	prs = 1; /* process scoped */
+	r = 1;   /* radix format */
+
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(0, 0, rb, rs, ric, prs, r);
+}
 static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
@@ -190,6 +201,23 @@ static __always_inline void __tlbie_va(unsigned long va, unsigned long pid,
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
+static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid,
+					    unsigned long lpid,
+					    unsigned long ap, unsigned long ric)
+{
+	unsigned long rb, rs, prs, r;
+
+	rb = va & ~(PPC_BITMASK(52, 63));
+	rb |= ap << PPC_BITLSHIFT(58);
+	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
+	prs = 1; /* process scoped */
+	r = 1;   /* radix format */
+
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(0, 0, rb, rs, ric, prs, r);
+}
+
 static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid,
 					    unsigned long ap, unsigned long ric)
 {
@@ -235,6 +263,22 @@ static inline void fixup_tlbie_va_range(unsigned long va, unsigned long pid,
 	}
 }
 
+static inline void fixup_tlbie_va_range_lpid(unsigned long va,
+					     unsigned long pid,
+					     unsigned long lpid,
+					     unsigned long ap)
+{
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB);
+	}
+}
+
 static inline void fixup_tlbie_pid(unsigned long pid)
 {
 	/*
@@ -254,6 +298,25 @@ static inline void fixup_tlbie_pid(unsigned long pid)
 	}
 }
 
+static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid)
+{
+	/*
+	 * We can use any address for the invalidation, pick one which is
+	 * probably unused as an optimisation.
+	 */
+	unsigned long va = ((1UL << 52) - 1);
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K),
+				RIC_FLUSH_TLB);
+	}
+}
 
 static inline void fixup_tlbie_lpid_va(unsigned long va, unsigned long lpid,
 				       unsigned long ap)
@@ -352,6 +415,31 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
+static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid,
+				   unsigned long ric)
+{
+	asm volatile("ptesync" : : : "memory");
+
+	/*
+	 * Workaround the fact that the "ric" argument to __tlbie_pid
+	 * must be a compile-time contraint to match the "i" constraint
+	 * in the asm statement.
+	 */
+	switch (ric) {
+	case RIC_FLUSH_TLB:
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
+		fixup_tlbie_pid_lpid(pid, lpid);
+		break;
+	case RIC_FLUSH_PWC:
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
+		break;
+	case RIC_FLUSH_ALL:
+	default:
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
+		fixup_tlbie_pid_lpid(pid, lpid);
+	}
+	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+}
 struct tlbiel_pid {
 	unsigned long pid;
 	unsigned long ric;
@@ -477,6 +565,20 @@ static inline void __tlbie_va_range(unsigned long start, unsigned long end,
 	fixup_tlbie_va_range(addr - page_size, pid, ap);
 }
 
+static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end,
+					 unsigned long pid, unsigned long lpid,
+					 unsigned long page_size,
+					 unsigned long psize)
+{
+	unsigned long addr;
+	unsigned long ap = mmu_get_ap(psize);
+
+	for (addr = start; addr < end; addr += page_size)
+		__tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB);
+
+	fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap);
+}
+
 static __always_inline void _tlbie_va(unsigned long va, unsigned long pid,
 				      unsigned long psize, unsigned long ric)
 {
@@ -557,6 +659,18 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end,
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
+static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end,
+					unsigned long pid, unsigned long lpid,
+					unsigned long page_size,
+					unsigned long psize, bool also_pwc)
+{
+	asm volatile("ptesync" : : : "memory");
+	if (also_pwc)
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
+	__tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize);
+	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+}
+
 static inline void _tlbiel_va_range_multicast(struct mm_struct *mm,
 				unsigned long start, unsigned long end,
 				unsigned long pid, unsigned long page_size,
@@ -1344,3 +1458,59 @@ void radix__flush_tlb_all(void)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(0) : "memory");
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+/*
+ * Performs process-scoped invalidations for a given LPID
+ * as part of H_RPT_INVALIDATE hcall.
+ */
+void do_h_rpt_invalidate_prt(unsigned long pid, unsigned long lpid,
+			     unsigned long type, unsigned long pg_sizes,
+			     unsigned long start, unsigned long end)
+{
+	unsigned long psize, nr_pages;
+	struct mmu_psize_def *def;
+	bool flush_pid;
+
+	/*
+	 * A H_RPTI_TYPE_ALL request implies RIC=3, hence
+	 * do a single IS=1 based flush.
+	 */
+	if ((type & H_RPTI_TYPE_ALL) == H_RPTI_TYPE_ALL) {
+		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
+		return;
+	}
+
+	if (type & H_RPTI_TYPE_PWC)
+		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
+
+	/* Full PID flush */
+	if (start == 0 && end == -1)
+		return _tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
+
+	/* Do range invalidation for all the valid page sizes */
+	for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
+		def = &mmu_psize_defs[psize];
+		if (!(pg_sizes & def->h_rpt_pgsize))
+			continue;
+
+		nr_pages = (end - start) >> def->shift;
+		flush_pid = nr_pages > tlb_single_page_flush_ceiling;
+
+		/*
+		 * If the number of pages spanning the range is above
+		 * the ceiling, convert the request into a full PID flush.
+		 * And since PID flush takes out all the page sizes, there
+		 * is no need to consider remaining page sizes.
+		 */
+		if (flush_pid) {
+			_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
+			return;
+		}
+		_tlbie_va_range_lpid(start, end, pid, lpid,
+				     (1UL << def->shift), psize, false);
+	}
+}
+EXPORT_SYMBOL_GPL(do_h_rpt_invalidate_prt);
+
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */

include/uapi/linux/kvm.h

@@ -1082,6 +1082,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_SGX_ATTRIBUTE 196
 #define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197
 #define KVM_CAP_PTP_KVM 198
+#define KVM_CAP_PPC_RPT_INVALIDATE 199
 
 #ifdef KVM_CAP_IRQ_ROUTING