Merge tag 'powerpc-4.13-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:
 "The highlight is Ben's patch to work around a host killing bug when
  running KVM guests with the Radix MMU on Power9. See the long change
  log of that commit for more detail.

  And then three fairly minor fixes:

   - fix of_node_put() underflow during reconfig remove, using old DLPAR
     tools.

   - fix recently introduced ld version check with 64-bit LE-only
     toolchain.

   - free the subpage_prot_table correctly, avoiding a memory leak.

  Thanks to: Aneesh Kumar K.V, Benjamin Herrenschmidt, Laurent Vivier"

* tag 'powerpc-4.13-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/mm/hash: Free the subpage_prot_table correctly
  powerpc/Makefile: Fix ld version check with 64-bit LE-only toolchain
  powerpc/pseries: Fix of_node_put() underflow during reconfig remove
  powerpc/mm/radix: Workaround prefetch issue with KVM

9 files changed, 168 insertions, 36 deletions

diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 8d4ed73d5490..e2b3e7a00c9e 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -59,6 +59,19 @@ machine-$(CONFIG_PPC64) += 64
 machine-$(CONFIG_CPU_LITTLE_ENDIAN) += le
 UTS_MACHINE := $(subst $(space),,$(machine-y))
 
+# XXX This needs to be before we override LD below
+ifdef CONFIG_PPC32
+KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
+else
+ifeq ($(call ld-ifversion, -ge, 225000000, y),y)
+# Have the linker provide sfpr if possible.
+# There is a corresponding test in arch/powerpc/lib/Makefile
+KBUILD_LDFLAGS_MODULE += --save-restore-funcs
+else
+KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
+endif
+endif
+
 ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
 override LD	+= -EL
 LDEMULATION	:= lppc
@@ -190,18 +203,6 @@ else
 CHECKFLAGS	+= -D__LITTLE_ENDIAN__
 endif
 
-ifdef CONFIG_PPC32
-KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
-else
-ifeq ($(call ld-ifversion, -ge, 225000000, y),y)
-# Have the linker provide sfpr if possible.
-# There is a corresponding test in arch/powerpc/lib/Makefile
-KBUILD_LDFLAGS_MODULE += --save-restore-funcs
-else
-KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
-endif
-endif
-
 ifeq ($(CONFIG_476FPE_ERR46),y)
 	KBUILD_LDFLAGS_MODULE += --ppc476-workaround \
 		-T $(srctree)/arch/powerpc/platforms/44x/ppc476_modules.lds
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 77529a3e3811..5b4023c616f7 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -59,13 +59,14 @@ extern struct patb_entry *partition_tb;
 #define PRTS_MASK	0x1f		/* process table size field */
 #define PRTB_MASK	0x0ffffffffffff000UL
 
-/*
- * Limit process table to PAGE_SIZE table. This
- * also limit the max pid we can support.
- * MAX_USER_CONTEXT * 16 bytes of space.
- */
-#define PRTB_SIZE_SHIFT	(CONTEXT_BITS + 4)
-#define PRTB_ENTRIES	(1ul << CONTEXT_BITS)
+/* Number of supported PID bits */
+extern unsigned int mmu_pid_bits;
+
+/* Base PID to allocate from */
+extern unsigned int mmu_base_pid;
+
+#define PRTB_SIZE_SHIFT	(mmu_pid_bits + 4)
+#define PRTB_ENTRIES	(1ul << mmu_pid_bits)
 
 /*
  * Power9 currently only support 64K partition table size.
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index da7e9432fa8f..0c76675394c5 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -45,7 +45,7 @@ extern void set_context(unsigned long id, pgd_t *pgd);
 
 #ifdef CONFIG_PPC_BOOK3S_64
 extern void radix__switch_mmu_context(struct mm_struct *prev,
-				     struct mm_struct *next);
+				      struct mm_struct *next);
 static inline void switch_mmu_context(struct mm_struct *prev,
 				      struct mm_struct *next,
 				      struct task_struct *tsk)
@@ -67,6 +67,12 @@ extern void __destroy_context(unsigned long context_id);
 extern void mmu_context_init(void);
 #endif
 
+#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)
+extern void radix_kvm_prefetch_workaround(struct mm_struct *mm);
+#else
+static inline void radix_kvm_prefetch_workaround(struct mm_struct *mm) { }
+#endif
+
 extern void switch_cop(struct mm_struct *next);
 extern int use_cop(unsigned long acop, struct mm_struct *mm);
 extern void drop_cop(unsigned long acop, struct mm_struct *mm);
@@ -79,9 +85,13 @@ static inline void switch_mm_irqs_off(struct mm_struct *prev,
 				      struct mm_struct *next,
 				      struct task_struct *tsk)
 {
+	bool new_on_cpu = false;
+
 	/* Mark this context has been used on the new CPU */
-	if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next)))
+	if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next))) {
 		cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
+		new_on_cpu = true;
+	}
 
 	/* 32-bit keeps track of the current PGDIR in the thread struct */
 #ifdef CONFIG_PPC32
@@ -109,6 +119,10 @@ static inline void switch_mm_irqs_off(struct mm_struct *prev,
 	if (cpu_has_feature(CPU_FTR_ALTIVEC))
 		asm volatile ("dssall");
 #endif /* CONFIG_ALTIVEC */
+
+	if (new_on_cpu)
+		radix_kvm_prefetch_workaround(next);
+
 	/*
 	 * The actual HW switching method differs between the various
 	 * sub architectures. Out of line for now
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index cb44065e2946..c52184a8efdf 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1443,12 +1443,14 @@ mc_cont:
 	ori	r6,r6,1
 	mtspr	SPRN_CTRLT,r6
 4:
-	/* Read the guest SLB and save it away */
+	/* Check if we are running hash or radix and store it in cr2 */
 	ld	r5, VCPU_KVM(r9)
 	lbz	r0, KVM_RADIX(r5)
-	cmpwi	r0, 0
+	cmpwi	cr2,r0,0
+
+	/* Read the guest SLB and save it away */
 	li	r5, 0
-	bne	3f			/* for radix, save 0 entries */
+	bne	cr2, 3f			/* for radix, save 0 entries */
 	lwz	r0,VCPU_SLB_NR(r9)	/* number of entries in SLB */
 	mtctr	r0
 	li	r6,0
@@ -1712,11 +1714,6 @@ BEGIN_FTR_SECTION_NESTED(96)
 END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 22:
-	/* Clear out SLB */
-	li	r5,0
-	slbmte	r5,r5
-	slbia
-	ptesync
 
 	/* Restore host values of some registers */
 BEGIN_FTR_SECTION
@@ -1737,10 +1734,56 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_PID, r7
 	mtspr	SPRN_IAMR, r8
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
+#ifdef CONFIG_PPC_RADIX_MMU
+	/*
+	 * Are we running hash or radix ?
+	 */
+	beq	cr2,3f
+
+	/* Radix: Handle the case where the guest used an illegal PID */
+	LOAD_REG_ADDR(r4, mmu_base_pid)
+	lwz	r3, VCPU_GUEST_PID(r9)
+	lwz	r5, 0(r4)
+	cmpw	cr0,r3,r5
+	blt	2f
+
+	/*
+	 * Illegal PID, the HW might have prefetched and cached in the TLB
+	 * some translations for the  LPID 0 / guest PID combination which
+	 * Linux doesn't know about, so we need to flush that PID out of
+	 * the TLB. First we need to set LPIDR to 0 so tlbiel applies to
+	 * the right context.
+	*/
+	li	r0,0
+	mtspr	SPRN_LPID,r0
+	isync
+
+	/* Then do a congruence class local flush */
+	ld	r6,VCPU_KVM(r9)
+	lwz	r0,KVM_TLB_SETS(r6)
+	mtctr	r0
+	li	r7,0x400		/* IS field = 0b01 */
+	ptesync
+	sldi	r0,r3,32		/* RS has PID */
+1:	PPC_TLBIEL(7,0,2,1,1)		/* RIC=2, PRS=1, R=1 */
+	addi	r7,r7,0x1000
+	bdnz	1b
+	ptesync
+
+2:	/* Flush the ERAT on radix P9 DD1 guest exit */
 BEGIN_FTR_SECTION
 	PPC_INVALIDATE_ERAT
 END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
+	b	4f
+#endif /* CONFIG_PPC_RADIX_MMU */
 
+	/* Hash: clear out SLB */
+3:	li	r5,0
+	slbmte	r5,r5
+	slbia
+	ptesync
+4:
 	/*
 	 * POWER7/POWER8 guest -> host partition switch code.
 	 * We don't have to lock against tlbies but we do
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index abed1fe6992f..a75f63833284 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -126,9 +126,10 @@ static int hash__init_new_context(struct mm_struct *mm)
 static int radix__init_new_context(struct mm_struct *mm)
 {
 	unsigned long rts_field;
-	int index;
+	int index, max_id;
 
-	index = alloc_context_id(1, PRTB_ENTRIES - 1);
+	max_id = (1 << mmu_pid_bits) - 1;
+	index = alloc_context_id(mmu_base_pid, max_id);
 	if (index < 0)
 		return index;
 
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 5cc50d47ce3f..671a45d86c18 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -25,6 +25,9 @@
 
 #include <trace/events/thp.h>
 
+unsigned int mmu_pid_bits;
+unsigned int mmu_base_pid;
+
 static int native_register_process_table(unsigned long base, unsigned long pg_sz,
 					 unsigned long table_size)
 {
@@ -261,11 +264,34 @@ static void __init radix_init_pgtable(void)
 	for_each_memblock(memory, reg)
 		WARN_ON(create_physical_mapping(reg->base,
 						reg->base + reg->size));
+
+	/* Find out how many PID bits are supported */
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		if (!mmu_pid_bits)
+			mmu_pid_bits = 20;
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+		/*
+		 * 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
+		 */
+		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;
+	}
+
 	/*
 	 * Allocate Partition table and process table for the
 	 * host.
 	 */
-	BUILD_BUG_ON_MSG((PRTB_SIZE_SHIFT > 36), "Process table size too large.");
+	BUG_ON(PRTB_SIZE_SHIFT > 36);
 	process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT);
 	/*
 	 * Fill in the process table.
@@ -339,6 +365,12 @@ static int __init radix_dt_scan_page_sizes(unsigned long node,
 	if (type == NULL || strcmp(type, "cpu") != 0)
 		return 0;
 
+	/* Find MMU PID size */
+	prop = of_get_flat_dt_prop(node, "ibm,mmu-pid-bits", &size);
+	if (prop && size == 4)
+		mmu_pid_bits = be32_to_cpup(prop);
+
+	/* Grab page size encodings */
 	prop = of_get_flat_dt_prop(node, "ibm,processor-radix-AP-encodings", &size);
 	if (!prop)
 		return 0;
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index e94fbd4c8845..781532d7bc4d 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -36,7 +36,7 @@ void subpage_prot_free(struct mm_struct *mm)
 		}
 	}
 	addr = 0;
-	for (i = 0; i < 2; ++i) {
+	for (i = 0; i < (TASK_SIZE_USER64 >> 43); ++i) {
 		p = spt->protptrs[i];
 		if (!p)
 			continue;
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 744e0164ecf5..16ae1bbe13f0 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -12,12 +12,12 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/memblock.h>
-#include <asm/ppc-opcode.h>
 
+#include <asm/ppc-opcode.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/trace.h>
-
+#include <asm/cputhreads.h>
 
 #define RIC_FLUSH_TLB 0
 #define RIC_FLUSH_PWC 1
@@ -454,3 +454,44 @@ void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,
 	else
 		radix__flush_tlb_page_psize(mm, address, mmu_virtual_psize);
 }
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
+{
+	unsigned int pid = mm->context.id;
+
+	if (unlikely(pid == MMU_NO_CONTEXT))
+		return;
+
+	/*
+	 * 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 (paca[sib].kvm_hstate.kvm_vcpu)
+				flush = true;
+		}
+		if (flush)
+			_tlbiel_pid(pid, RIC_FLUSH_ALL);
+	}
+}
+EXPORT_SYMBOL_GPL(radix_kvm_prefetch_workaround);
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index e5bf1e84047f..011ef2180fe6 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -82,7 +82,6 @@ static int pSeries_reconfig_remove_node(struct device_node *np)
 
 	of_detach_node(np);
 	of_node_put(parent);
-	of_node_put(np); /* Must decrement the refcount */
 	return 0;
 }