powerpc/mm/radix: Workaround prefetch issue with KVM

There's a somewhat architectural issue with Radix MMU and KVM.

When coming out of a guest with AIL (Alternate Interrupt Location, ie,
MMU enabled), we start executing hypervisor code with the PID register
still containing whatever the guest has been using.

The problem is that the CPU can (and will) then start prefetching or
speculatively load from whatever host context has that same PID (if
any), thus bringing translations for that context into the TLB, which
Linux doesn't know about.

This can cause stale translations and subsequent crashes.

Fixing this in a way that is neither racy nor a huge performance
impact is difficult. We could just make the host invalidations always
use broadcast forms but that would hurt single threaded programs for
example.

We chose to fix it instead by partitioning the PID space between guest
and host. This is possible because today Linux only use 19 out of the
20 bits of PID space, so existing guests will work if we make the host
use the top half of the 20 bits space.

We additionally add support for a property to indicate to Linux the
size of the PID register which will be useful if we eventually have
processors with a larger PID space available.

There is still an issue with malicious guests purposefully setting the
PID register to a value in the hosts PID range. Hopefully future HW
can prevent that, but in the meantime, we handle it with a pair of
kludges:

 - On the way out of a guest, before we clear the current VCPU in the
   PACA, we check the PID and if it's outside of the permitted range
   we flush the TLB for that PID.

 - When context switching, if the mm is "new" on that CPU (the
   corresponding bit was set for the first time in the mm cpumask), we
   check if any sibling thread is in KVM (has a non-NULL VCPU pointer
   in the PACA). If that is the case, we also flush the PID for that
   CPU (core).

This second part is needed to handle the case where a process is
migrated (or starts a new pthread) on a sibling thread of the CPU
coming out of KVM, as there's a window where stale translations can
exist before we detect it and flush them out.

A future optimization could be added by keeping track of whether the
PID has ever been used and avoid doing that for completely fresh PIDs.
We could similarily mark PIDs that have been the subject of a global
invalidation as "fresh". But for now this will do.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
[mpe: Rework the asm to build with CONFIG_PPC_RADIX_MMU=n, drop
      unneeded include of kvm_book3s_asm.h]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

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.

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

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

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;
 

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;

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 */