KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE

H_RPT_INVALIDATE does two types of TLB invalidations:

1. Process-scoped invalidations for guests when LPCR[GTSE]=0.
   This is currently not used in KVM as GTSE is not usually
   disabled in KVM.
2. Partition-scoped invalidations that an L1 hypervisor does on
   behalf of an L2 guest. This is currently handled
   by H_TLB_INVALIDATE hcall and this new replaces the old that.

This commit enables process-scoped invalidations for L1 guests.
Support for process-scoped and partition-scoped invalidations
from/for nested guests will be added separately.

Process scoped tlbie invalidations from L1 and nested guests
need RS register for TLBIE instruction to contain both PID and
LPID.  This patch introduces primitives that execute tlbie
instruction with both PID and LPID set in prepartion for
H_RPT_INVALIDATE hcall.

A description of H_RPT_INVALIDATE follows:

int64   /* H_Success: Return code on successful completion */
        /* H_Busy - repeat the call with the same */
        /* H_Parameter, H_P2, H_P3, H_P4, H_P5 : Invalid
	   parameters */
hcall(const uint64 H_RPT_INVALIDATE, /* Invalidate RPT
					translation
					lookaside information */
      uint64 id,        /* PID/LPID to invalidate */
      uint64 target,    /* Invalidation target */
      uint64 type,      /* Type of lookaside information */
      uint64 pg_sizes,  /* Page sizes */
      uint64 start,     /* Start of Effective Address (EA)
			   range (inclusive) */
      uint64 end)       /* End of EA range (exclusive) */

Invalidation targets (target)
-----------------------------
Core MMU        0x01 /* All virtual processors in the
			partition */
Core local MMU  0x02 /* Current virtual processor */
Nest MMU        0x04 /* All nest/accelerator agents
			in use by the partition */

A combination of the above can be specified,
except core and core local.

Type of translation to invalidate (type)
---------------------------------------
NESTED       0x0001  /* invalidate nested guest partition-scope */
TLB          0x0002  /* Invalidate TLB */
PWC          0x0004  /* Invalidate Page Walk Cache */
PRT          0x0008  /* Invalidate caching of Process Table
			Entries if NESTED is clear */
PAT          0x0008  /* Invalidate caching of Partition Table
			Entries if NESTED is set */

A combination of the above can be specified.

Page size mask (pages)
----------------------
4K              0x01
64K             0x02
2M              0x04
1G              0x08
All sizes       (-1UL)

A combination of the above can be specified.
All page sizes can be selected with -1.

Semantics: Invalidate radix tree lookaside information
           matching the parameters given.
* Return H_P2, H_P3 or H_P4 if target, type, or pageSizes parameters
  are different from the defined values.
* Return H_PARAMETER if NESTED is set and pid is not a valid nested
  LPID allocated to this partition
* Return H_P5 if (start, end) doesn't form a valid range. Start and
  end should be a valid Quadrant address and  end > start.
* Return H_NotSupported if the partition is not in running in radix
  translation mode.
* May invalidate more translation information than requested.
* If start = 0 and end = -1, set the range to cover all valid
  addresses. Else start and end should be aligned to 4kB (lower 11
  bits clear).
* If NESTED is clear, then invalidate process scoped lookaside
  information. Else pid specifies a nested LPID, and the invalidation
  is performed   on nested guest partition table and nested guest
  partition scope real addresses.
* If pid = 0 and NESTED is clear, then valid addresses are quadrant 3
  and quadrant 0 spaces, Else valid addresses are quadrant 0.
* Pages which are fully covered by the range are to be invalidated.
  Those which are partially covered are considered outside
  invalidation range, which allows a caller to optimally invalidate
  ranges that may   contain mixed page sizes.
* Return H_SUCCESS on success.
Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210621085003.904767-4-bharata@linux.ibm.com

arch/powerpc/include/asm/mmu_context.h

@@ -216,6 +216,18 @@ 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_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 +923,32 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu)
 	return yield_count;
 }
 
+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.
+	 * Not yet supported
+	 */
+	if (type & H_RPTI_TYPE_NESTED)
+		return H_P3;
+
+	/*
+	 * 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 +1132,14 @@ 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 +1260,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
 	case H_XIRR_X:
 #endif
 	case H_PAGE_INIT:
+	case H_RPT_INVALIDATE:
 		return 1;
 	}
 

arch/powerpc/mm/book3s64/radix_tlb.c

@@ -130,6 +130,21 @@ 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 +205,23 @@ 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 +267,22 @@ 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 +302,25 @@ 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 +411,31 @@ 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 +561,20 @@ 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 +655,18 @@ 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,
@@ -1336,3 +1454,59 @@ 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 */