Merge remote-tracking branch 'torvalds/master' into perf/core

To pick up fixes.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

5 files changed, 181 insertions, 64 deletions

diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index c3df3a8501d4..2ffcf540f08b 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -13,7 +13,7 @@ obj-y				:= fault.o mem.o pgtable.o mmap.o maccess.o \
 obj-$(CONFIG_PPC_MMU_NOHASH)	+= nohash/
 obj-$(CONFIG_PPC_BOOK3S_32)	+= book3s32/
 obj-$(CONFIG_PPC_BOOK3S_64)	+= book3s64/
-obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
+obj-$(CONFIG_NUMA) += numa.o
 obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 5fef8db3b463..2176a5f70746 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/sched/mm.h>
 #include <linux/memblock.h>
+#include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
@@ -357,30 +358,19 @@ 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 +476,7 @@ 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 +551,13 @@ 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/mem.c b/arch/powerpc/mm/mem.c
index a6b36a40897a..c5e520c6f13b 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -127,7 +127,7 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
 }
 #endif
 
-#ifndef CONFIG_NEED_MULTIPLE_NODES
+#ifndef CONFIG_NUMA
 void __init mem_topology_setup(void)
 {
 	max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
@@ -162,7 +162,7 @@ static int __init mark_nonram_nosave(void)
 
 	return 0;
 }
-#else /* CONFIG_NEED_MULTIPLE_NODES */
+#else /* CONFIG_NUMA */
 static int __init mark_nonram_nosave(void)
 {
 	return 0;
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);
 
 	/*