Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "This covers all architectures (except MIPS) so I don't expect any
  other feature pull requests this merge window.

  ARM:

   - Add MTE support in guests, complete with tag save/restore interface

   - Reduce the impact of CMOs by moving them in the page-table code

   - Allow device block mappings at stage-2

   - Reduce the footprint of the vmemmap in protected mode

   - Support the vGIC on dumb systems such as the Apple M1

   - Add selftest infrastructure to support multiple configuration and
     apply that to PMU/non-PMU setups

   - Add selftests for the debug architecture

   - The usual crop of PMU fixes

  PPC:

   - Support for the H_RPT_INVALIDATE hypercall

   - Conversion of Book3S entry/exit to C

   - Bug fixes

  S390:

   - new HW facilities for guests

   - make inline assembly more robust with KASAN and co

  x86:

   - Allow userspace to handle emulation errors (unknown instructions)

   - Lazy allocation of the rmap (host physical -> guest physical
     address)

   - Support for virtualizing TSC scaling on VMX machines

   - Optimizations to avoid shattering huge pages at the beginning of
     live migration

   - Support for initializing the PDPTRs without loading them from
     memory

   - Many TLB flushing cleanups

   - Refuse to load if two-stage paging is available but NX is not (this
     has been a requirement in practice for over a year)

   - A large series that separates the MMU mode (WP/SMAP/SMEP etc.) from
     CR0/CR4/EFER, using the MMU mode everywhere once it is computed
     from the CPU registers

   - Use PM notifier to notify the guest about host suspend or hibernate

   - Support for passing arguments to Hyper-V hypercalls using XMM
     registers

   - Support for Hyper-V TLB flush hypercalls and enlightened MSR bitmap
     on AMD processors

   - Hide Hyper-V hypercalls that are not included in the guest CPUID

   - Fixes for live migration of virtual machines that use the Hyper-V
     "enlightened VMCS" optimization of nested virtualization

   - Bugfixes (not many)

  Generic:

   - Support for retrieving statistics without debugfs

   - Cleanups for the KVM selftests API"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (314 commits)
  KVM: x86: rename apic_access_page_done to apic_access_memslot_enabled
  kvm: x86: disable the narrow guest module parameter on unload
  selftests: kvm: Allows userspace to handle emulation errors.
  kvm: x86: Allow userspace to handle emulation errors
  KVM: x86/mmu: Let guest use GBPAGES if supported in hardware and TDP is on
  KVM: x86/mmu: Get CR4.SMEP from MMU, not vCPU, in shadow page fault
  KVM: x86/mmu: Get CR0.WP from MMU, not vCPU, in shadow page fault
  KVM: x86/mmu: Drop redundant rsvd bits reset for nested NPT
  KVM: x86/mmu: Optimize and clean up so called "last nonleaf level" logic
  KVM: x86: Enhance comments for MMU roles and nested transition trickiness
  KVM: x86/mmu: WARN on any reserved SPTE value when making a valid SPTE
  KVM: x86/mmu: Add helpers to do full reserved SPTE checks w/ generic MMU
  KVM: x86/mmu: Use MMU's role to determine PTTYPE
  KVM: x86/mmu: Collapse 32-bit PAE and 64-bit statements for helpers
  KVM: x86/mmu: Add a helper to calculate root from role_regs
  KVM: x86/mmu: Add helper to update paging metadata
  KVM: x86/mmu: Don't update nested guest's paging bitmasks if CR0.PG=0
  KVM: x86/mmu: Consolidate reset_rsvds_bits_mask() calls
  KVM: x86/mmu: Use MMU role_regs to get LA57, and drop vCPU LA57 helper
  KVM: x86/mmu: Get nested MMU's root level from the MMU's role
  ...

3 files changed, 177 insertions, 61 deletions

diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 5fef8db3b463..6e3495221ab7 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -357,30 +357,19 @@ static void __init radix_init_pgtable(void)
 	}
 
 	/* Find out how many PID bits are supported */
-	if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
-		if (!mmu_pid_bits)
-			mmu_pid_bits = 20;
-		mmu_base_pid = 1;
-	} else if (cpu_has_feature(CPU_FTR_HVMODE)) {
-		if (!mmu_pid_bits)
-			mmu_pid_bits = 20;
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	if (!cpu_has_feature(CPU_FTR_HVMODE) &&
+			cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
 		/*
-		 * When KVM is possible, we only use the top half of the
-		 * PID space to avoid collisions between host and guest PIDs
-		 * which can cause problems due to prefetch when exiting the
-		 * guest with AIL=3
+		 * Older versions of KVM on these machines perfer if the
+		 * guest only uses the low 19 PID bits.
 		 */
-		mmu_base_pid = 1 << (mmu_pid_bits - 1);
-#else
-		mmu_base_pid = 1;
-#endif
-	} else {
-		/* The guest uses the bottom half of the PID space */
 		if (!mmu_pid_bits)
 			mmu_pid_bits = 19;
-		mmu_base_pid = 1;
+	} else {
+		if (!mmu_pid_bits)
+			mmu_pid_bits = 20;
 	}
+	mmu_base_pid = 1;
 
 	/*
 	 * Allocate Partition table and process table for the
@@ -486,6 +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 ? */
@@ -560,9 +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);
 	}
 
 	/*
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index 409e61210789..318ec4f33661 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/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)
@@ -344,6 +407,31 @@ 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;
@@ -469,6 +557,20 @@ 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)
 {
@@ -549,6 +651,18 @@ 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,
@@ -1338,47 +1452,57 @@ void radix__flush_tlb_all(void)
 }
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
+/*
+ * 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 pid = mm->context.id;
+	unsigned long psize, nr_pages;
+	struct mmu_psize_def *def;
+	bool flush_pid;
 
-	if (unlikely(pid == MMU_NO_CONTEXT))
+	/*
+	 * 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 (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
-		return;
+	if (type & H_RPTI_TYPE_PWC)
+		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
 
-	/*
-	 * If this context hasn't run on that CPU before and KVM is
-	 * around, there's a slim chance that the guest on another
-	 * CPU just brought in obsolete translation into the TLB of
-	 * this CPU due to a bad prefetch using the guest PID on
-	 * the way into the hypervisor.
-	 *
-	 * We work around this here. If KVM is possible, we check if
-	 * any sibling thread is in KVM. If it is, the window may exist
-	 * and thus we flush that PID from the core.
-	 *
-	 * A potential future improvement would be to mark which PIDs
-	 * have never been used on the system and avoid it if the PID
-	 * is new and the process has no other cpumask bit set.
-	 */
-	if (cpu_has_feature(CPU_FTR_HVMODE) && radix_enabled()) {
-		int cpu = smp_processor_id();
-		int sib = cpu_first_thread_sibling(cpu);
-		bool flush = false;
-
-		for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) {
-			if (sib == cpu)
-				continue;
-			if (!cpu_possible(sib))
-				continue;
-			if (paca_ptrs[sib]->kvm_hstate.kvm_vcpu)
-				flush = true;
+	/* 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;
 		}
-		if (flush)
-			_tlbiel_pid(pid, RIC_FLUSH_ALL);
+		_tlbie_va_range_lpid(start, end, pid, lpid,
+				     (1UL << def->shift), psize, false);
 	}
 }
-EXPORT_SYMBOL_GPL(radix_kvm_prefetch_workaround);
+EXPORT_SYMBOL_GPL(do_h_rpt_invalidate_prt);
+
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c
index a857af401738..74246536b832 100644
--- a/arch/powerpc/mm/mmu_context.c
+++ b/arch/powerpc/mm/mmu_context.c
@@ -83,9 +83,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	if (cpu_has_feature(CPU_FTR_ALTIVEC))
 		asm volatile ("dssall");
 
-	if (new_on_cpu)
-		radix_kvm_prefetch_workaround(next);
-	else
+	if (!new_on_cpu)
 		membarrier_arch_switch_mm(prev, next, tsk);
 
 	/*