Merge branch 'topic/ppc-kvm' into next

Merge in some commits we're sharing with the kvm-ppc tree.

arch/powerpc/include/asm/asm-prototypes.h

@@ -134,4 +134,7 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip);
 void pnv_power9_force_smt4_catch(void);
 void pnv_power9_force_smt4_release(void);
 
+void tm_enable(void);
+void tm_disable(void);
+void tm_abort(uint8_t cause);
 #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */

arch/powerpc/include/asm/book3s/64/tlbflush-radix.h

@@ -51,4 +51,11 @@ extern void radix__flush_tlb_all(void);
 extern void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,
 					unsigned long address);
 
+extern void radix__flush_tlb_lpid_page(unsigned int lpid,
+					unsigned long addr,
+					unsigned long page_size);
+extern void radix__flush_pwc_lpid(unsigned int lpid);
+extern void radix__local_flush_tlb_lpid(unsigned int lpid);
+extern void radix__local_flush_tlb_lpid_guest(unsigned int lpid);
+
 #endif

arch/powerpc/include/asm/reg.h

@@ -146,6 +146,12 @@
 #define MSR_64BIT	0
 #endif
 
+/* Condition Register related */
+#define CR0_SHIFT	28
+#define CR0_MASK	0xF
+#define CR0_TBEGIN_FAILURE	(0x2 << 28) /* 0b0010 */
+
+
 /* Power Management - Processor Stop Status and Control Register Fields */
 #define PSSCR_RL_MASK		0x0000000F /* Requested Level */
 #define PSSCR_MTL_MASK		0x000000F0 /* Maximum Transition Level */
@@ -239,13 +245,27 @@
 #define SPRN_TFIAR	0x81	/* Transaction Failure Inst Addr   */
 #define SPRN_TEXASR	0x82	/* Transaction EXception & Summary */
 #define SPRN_TEXASRU	0x83	/* ''	   ''	   ''	 Upper 32  */
-#define   TEXASR_ABORT	__MASK(63-31) /* terminated by tabort or treclaim */
-#define   TEXASR_SUSP	__MASK(63-32) /* tx failed in suspended state */
-#define   TEXASR_HV	__MASK(63-34) /* MSR[HV] when failure occurred */
-#define   TEXASR_PR	__MASK(63-35) /* MSR[PR] when failure occurred */
-#define   TEXASR_FS	__MASK(63-36) /* TEXASR Failure Summary */
-#define   TEXASR_EXACT	__MASK(63-37) /* TFIAR value is exact */
+
+#define TEXASR_FC_LG	(63 - 7)	/* Failure Code */
+#define TEXASR_AB_LG	(63 - 31)	/* Abort */
+#define TEXASR_SU_LG	(63 - 32)	/* Suspend */
+#define TEXASR_HV_LG	(63 - 34)	/* Hypervisor state*/
+#define TEXASR_PR_LG	(63 - 35)	/* Privilege level */
+#define TEXASR_FS_LG	(63 - 36)	/* failure summary */
+#define TEXASR_EX_LG	(63 - 37)	/* TFIAR exact bit */
+#define TEXASR_ROT_LG	(63 - 38)	/* ROT bit */
+
+#define   TEXASR_ABORT	__MASK(TEXASR_AB_LG) /* terminated by tabort or treclaim */
+#define   TEXASR_SUSP	__MASK(TEXASR_SU_LG) /* tx failed in suspended state */
+#define   TEXASR_HV	__MASK(TEXASR_HV_LG) /* MSR[HV] when failure occurred */
+#define   TEXASR_PR	__MASK(TEXASR_PR_LG) /* MSR[PR] when failure occurred */
+#define   TEXASR_FS	__MASK(TEXASR_FS_LG) /* TEXASR Failure Summary */
+#define   TEXASR_EXACT	__MASK(TEXASR_EX_LG) /* TFIAR value is exact */
+#define   TEXASR_ROT	__MASK(TEXASR_ROT_LG)
+#define   TEXASR_FC	(ASM_CONST(0xFF) << TEXASR_FC_LG)
+
 #define SPRN_TFHAR	0x80	/* Transaction Failure Handler Addr */
+
 #define SPRN_TIDR	144	/* Thread ID register */
 #define SPRN_CTRLF	0x088
 #define SPRN_CTRLT	0x098

arch/powerpc/include/asm/tm.h

@@ -10,12 +10,10 @@
 
 #ifndef __ASSEMBLY__
 
-extern void tm_enable(void);
 extern void tm_reclaim(struct thread_struct *thread,
 		       uint8_t cause);
 extern void tm_reclaim_current(uint8_t cause);
 extern void tm_recheckpoint(struct thread_struct *thread);
-extern void tm_abort(uint8_t cause);
 extern void tm_save_sprs(struct thread_struct *thread);
 extern void tm_restore_sprs(struct thread_struct *thread);
 

arch/powerpc/kernel/kvm.c

@@ -25,6 +25,7 @@
 #include <linux/kvm_para.h>
 #include <linux/slab.h>
 #include <linux/of.h>
+#include <linux/pagemap.h>
 
 #include <asm/reg.h>
 #include <asm/sections.h>
@@ -672,14 +673,13 @@ static void kvm_use_magic_page(void)
 {
 	u32 *p;
 	u32 *start, *end;
-	u32 tmp;
 	u32 features;
 
 	/* Tell the host to map the magic page to -4096 on all CPUs */
 	on_each_cpu(kvm_map_magic_page, &features, 1);
 
 	/* Quick self-test to see if the mapping works */
-	if (__get_user(tmp, (u32*)KVM_MAGIC_PAGE)) {
+	if (!fault_in_pages_readable((const char *)KVM_MAGIC_PAGE, sizeof(u32))) {
 		kvm_patching_worked = false;
 		return;
 	}

arch/powerpc/kernel/process.c

@@ -154,6 +154,7 @@ unsigned long msr_check_and_set(unsigned long bits)
 
 	return newmsr;
 }
+EXPORT_SYMBOL_GPL(msr_check_and_set);
 
 void __msr_check_and_clear(unsigned long bits)
 {

arch/powerpc/kernel/tm.S

@@ -12,6 +12,7 @@
 #include <asm/ptrace.h>
 #include <asm/reg.h>
 #include <asm/bug.h>
+#include <asm/export.h>
 
 #ifdef CONFIG_VSX
 /* See fpu.S, this is borrowed from there */
@@ -55,6 +56,16 @@ _GLOBAL(tm_enable)
 	or	r4, r4, r3
 	mtmsrd	r4
 1:	blr
+EXPORT_SYMBOL_GPL(tm_enable);
+
+_GLOBAL(tm_disable)
+	mfmsr	r4
+	li	r3, MSR_TM >> 32
+	sldi	r3, r3, 32
+	andc	r4, r4, r3
+	mtmsrd	r4
+	blr
+EXPORT_SYMBOL_GPL(tm_disable);
 
 _GLOBAL(tm_save_sprs)
 	mfspr	r0, SPRN_TFHAR
@@ -78,6 +89,7 @@ _GLOBAL(tm_restore_sprs)
 _GLOBAL(tm_abort)
 	TABORT(R3)
 	blr
+EXPORT_SYMBOL_GPL(tm_abort);
 
 /* void tm_reclaim(struct thread_struct *thread,
  *		   uint8_t cause)

arch/powerpc/mm/hash_utils_64.c

@@ -64,6 +64,7 @@
 #include <asm/trace.h>
 #include <asm/ps3.h>
 #include <asm/pte-walk.h>
+#include <asm/asm-prototypes.h>
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)

arch/powerpc/mm/tlb-radix.c

@@ -118,6 +118,53 @@ static inline void __tlbie_pid(unsigned long pid, unsigned long ric)
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
+static inline void __tlbiel_lpid(unsigned long lpid, int set,
+				unsigned long ric)
+{
+	unsigned long rb,rs,prs,r;
+
+	rb = PPC_BIT(52); /* IS = 2 */
+	rb |= set << PPC_BITLSHIFT(51);
+	rs = 0;  /* LPID comes from LPIDR */
+	prs = 0; /* partition scoped */
+	r = 1;   /* radix format */
+
+	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(lpid, 1, rb, rs, ric, prs, r);
+}
+
+static inline void __tlbie_lpid(unsigned long lpid, unsigned long ric)
+{
+	unsigned long rb,rs,prs,r;
+
+	rb = PPC_BIT(52); /* IS = 2 */
+	rs = lpid;
+	prs = 0; /* partition 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(lpid, 0, rb, rs, ric, prs, r);
+}
+
+static inline void __tlbiel_lpid_guest(unsigned long lpid, int set,
+				unsigned long ric)
+{
+	unsigned long rb,rs,prs,r;
+
+	rb = PPC_BIT(52); /* IS = 2 */
+	rb |= set << PPC_BITLSHIFT(51);
+	rs = 0;  /* LPID comes from LPIDR */
+	prs = 1; /* process scoped */
+	r = 1;   /* radix format */
+
+	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(lpid, 1, rb, rs, ric, prs, r);
+}
+
+
 static inline void __tlbiel_va(unsigned long va, unsigned long pid,
 			       unsigned long ap, unsigned long ric)
 {
@@ -150,6 +197,22 @@ static inline void __tlbie_va(unsigned long va, unsigned long pid,
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
+static inline void __tlbie_lpid_va(unsigned long va, 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 = lpid;
+	prs = 0; /* partition 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(lpid, 0, rb, rs, ric, prs, r);
+}
+
 static inline void fixup_tlbie(void)
 {
 	unsigned long pid = 0;
@@ -161,6 +224,16 @@ static inline void fixup_tlbie(void)
 	}
 }
 
+static inline void fixup_tlbie_lpid(unsigned long lpid)
+{
+	unsigned long va = ((1UL << 52) - 1);
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+		asm volatile("ptesync": : :"memory");
+		__tlbie_lpid_va(va, lpid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB);
+	}
+}
+
 /*
  * We use 128 set in radix mode and 256 set in hpt mode.
  */
@@ -214,6 +287,86 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
+static inline void _tlbiel_lpid(unsigned long lpid, unsigned long ric)
+{
+	int set;
+
+	VM_BUG_ON(mfspr(SPRN_LPID) != lpid);
+
+	asm volatile("ptesync": : :"memory");
+
+	/*
+	 * Flush the first set of the TLB, and if we're doing a RIC_FLUSH_ALL,
+	 * also flush the entire Page Walk Cache.
+	 */
+	__tlbiel_lpid(lpid, 0, ric);
+
+	/* For PWC, only one flush is needed */
+	if (ric == RIC_FLUSH_PWC) {
+		asm volatile("ptesync": : :"memory");
+		return;
+	}
+
+	/* For the remaining sets, just flush the TLB */
+	for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++)
+		__tlbiel_lpid(lpid, set, RIC_FLUSH_TLB);
+
+	asm volatile("ptesync": : :"memory");
+	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
+}
+
+static inline void _tlbie_lpid(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_lpid(lpid, RIC_FLUSH_TLB);
+		break;
+	case RIC_FLUSH_PWC:
+		__tlbie_lpid(lpid, RIC_FLUSH_PWC);
+		break;
+	case RIC_FLUSH_ALL:
+	default:
+		__tlbie_lpid(lpid, RIC_FLUSH_ALL);
+	}
+	fixup_tlbie_lpid(lpid);
+	asm volatile("eieio; tlbsync; ptesync": : :"memory");
+}
+
+static inline void _tlbiel_lpid_guest(unsigned long lpid, unsigned long ric)
+{
+	int set;
+
+	VM_BUG_ON(mfspr(SPRN_LPID) != lpid);
+
+	asm volatile("ptesync": : :"memory");
+
+	/*
+	 * Flush the first set of the TLB, and if we're doing a RIC_FLUSH_ALL,
+	 * also flush the entire Page Walk Cache.
+	 */
+	__tlbiel_lpid_guest(lpid, 0, ric);
+
+	/* For PWC, only one flush is needed */
+	if (ric == RIC_FLUSH_PWC) {
+		asm volatile("ptesync": : :"memory");
+		return;
+	}
+
+	/* For the remaining sets, just flush the TLB */
+	for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++)
+		__tlbiel_lpid_guest(lpid, set, RIC_FLUSH_TLB);
+
+	asm volatile("ptesync": : :"memory");
+}
+
+
 static inline void __tlbiel_va_range(unsigned long start, unsigned long end,
 				    unsigned long pid, unsigned long page_size,
 				    unsigned long psize)
@@ -268,6 +421,17 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid,
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
+static inline void _tlbie_lpid_va(unsigned long va, unsigned long lpid,
+			      unsigned long psize, unsigned long ric)
+{
+	unsigned long ap = mmu_get_ap(psize);
+
+	asm volatile("ptesync": : :"memory");
+	__tlbie_lpid_va(va, lpid, ap, ric);
+	fixup_tlbie_lpid(lpid);
+	asm volatile("eieio; tlbsync; ptesync": : :"memory");
+}
+
 static inline void _tlbie_va_range(unsigned long start, unsigned long end,
 				    unsigned long pid, unsigned long page_size,
 				    unsigned long psize, bool also_pwc)
@@ -534,6 +698,49 @@ static int radix_get_mmu_psize(int page_size)
 	return psize;
 }
 
+/*
+ * Flush partition scoped LPID address translation for all CPUs.
+ */
+void radix__flush_tlb_lpid_page(unsigned int lpid,
+					unsigned long addr,
+					unsigned long page_size)
+{
+	int psize = radix_get_mmu_psize(page_size);
+
+	_tlbie_lpid_va(addr, lpid, psize, RIC_FLUSH_TLB);
+}
+EXPORT_SYMBOL_GPL(radix__flush_tlb_lpid_page);
+
+/*
+ * Flush partition scoped PWC from LPID for all CPUs.
+ */
+void radix__flush_pwc_lpid(unsigned int lpid)
+{
+	_tlbie_lpid(lpid, RIC_FLUSH_PWC);
+}
+EXPORT_SYMBOL_GPL(radix__flush_pwc_lpid);
+
+/*
+ * Flush partition scoped translations from LPID (=LPIDR)
+ */
+void radix__local_flush_tlb_lpid(unsigned int lpid)
+{
+	_tlbiel_lpid(lpid, RIC_FLUSH_ALL);
+}
+EXPORT_SYMBOL_GPL(radix__local_flush_tlb_lpid);
+
+/*
+ * Flush process scoped translations from LPID (=LPIDR).
+ * Important difference, the guest normally manages its own translations,
+ * but some cases e.g., vCPU CPU migration require KVM to flush.
+ */
+void radix__local_flush_tlb_lpid_guest(unsigned int lpid)
+{
+	_tlbiel_lpid_guest(lpid, RIC_FLUSH_ALL);
+}
+EXPORT_SYMBOL_GPL(radix__local_flush_tlb_lpid_guest);
+
+
 static void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start,
 				  unsigned long end, int psize);
 

arch/powerpc/platforms/powernv/copy-paste.h

@@ -7,9 +7,8 @@
  * 2 of the License, or (at your option) any later version.
  */
 #include <asm/ppc-opcode.h>
+#include <asm/reg.h>
 
-#define CR0_SHIFT	28
-#define CR0_MASK	0xF
 /*
  * Copy/paste instructions:
  *