powerpc/64s: Add cp_abort after tlbiel to invalidate copy-buffer address

The copy buffer is implemented as a real address in the nest which is
translated from EA by copy, and used for memory access by paste. This
requires that it be invalidated by TLB invalidation.

TLBIE does invalidate the copy buffer, but TLBIEL does not. Add
cp_abort to the tlbiel sequence.
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
[mpe: Fixup whitespace and comment formatting]
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200916030234.4110379-2-npiggin@gmail.com

arch/powerpc/include/asm/synch.h

@@ -3,8 +3,9 @@
 #define _ASM_POWERPC_SYNCH_H 
 #ifdef __KERNEL__
 
+#include <asm/cputable.h>
 #include <asm/feature-fixups.h>
-#include <asm/asm-const.h>
+#include <asm/ppc-opcode.h>
 
 #ifndef __ASSEMBLY__
 extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup;
@@ -20,6 +21,22 @@ static inline void isync(void)
 {
 	__asm__ __volatile__ ("isync" : : : "memory");
 }
+
+static inline void ppc_after_tlbiel_barrier(void)
+{
+	asm volatile("ptesync": : :"memory");
+	/*
+	 * POWER9, POWER10 need a cp_abort after tlbiel to ensure the copy is
+	 * invalidated correctly. If this is not done, the paste can take data
+	 * from the physical address that was translated at copy time.
+	 *
+	 * POWER9 in practice does not need this, because address spaces with
+	 * accelerators mapped will use tlbie (which does invalidate the copy)
+	 * to invalidate translations. It's not possible to limit POWER10 this
+	 * way due to local copy-paste.
+	 */
+	asm volatile(ASM_FTR_IFSET(PPC_CP_ABORT, "", %0) : : "i" (CPU_FTR_ARCH_31) : "memory");
+}
 #endif /* __ASSEMBLY__ */
 
 #if defined(__powerpc64__)

arch/powerpc/mm/book3s64/hash_native.c

@@ -82,7 +82,7 @@ static void tlbiel_all_isa206(unsigned int num_sets, unsigned int is)
 	for (set = 0; set < num_sets; set++)
 		tlbiel_hash_set_isa206(set, is);
 
-	asm volatile("ptesync": : :"memory");
+	ppc_after_tlbiel_barrier();
 }
 
 static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
@@ -110,7 +110,7 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
 	 */
 	tlbiel_hash_set_isa300(0, is, 0, 2, 1);
 
-	asm volatile("ptesync": : :"memory");
+	ppc_after_tlbiel_barrier();
 
 	asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT "; isync" : : :"memory");
 }
@@ -303,7 +303,7 @@ static inline void tlbie(unsigned long vpn, int psize, int apsize,
 	asm volatile("ptesync": : :"memory");
 	if (use_local) {
 		__tlbiel(vpn, psize, apsize, ssize);
-		asm volatile("ptesync": : :"memory");
+		ppc_after_tlbiel_barrier();
 	} else {
 		__tlbie(vpn, psize, apsize, ssize);
 		fixup_tlbie_vpn(vpn, psize, apsize, ssize);
@@ -879,7 +879,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 				__tlbiel(vpn, psize, psize, ssize);
 			} pte_iterate_hashed_end();
 		}
-		asm volatile("ptesync":::"memory");
+		ppc_after_tlbiel_barrier();
 	} else {
 		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 

arch/powerpc/mm/book3s64/radix_tlb.c

@@ -65,7 +65,7 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
 	for (set = 1; set < num_sets; set++)
 		tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 1);
 
-	asm volatile("ptesync": : :"memory");
+	ppc_after_tlbiel_barrier();
 }
 
 void radix__tlbiel_all(unsigned int action)
@@ -296,7 +296,7 @@ static __always_inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 
 	/* For PWC, only one flush is needed */
 	if (ric == RIC_FLUSH_PWC) {
-		asm volatile("ptesync": : :"memory");
+		ppc_after_tlbiel_barrier();
 		return;
 	}
 
@@ -304,7 +304,7 @@ static __always_inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 	for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++)
 		__tlbiel_pid(pid, set, RIC_FLUSH_TLB);
 
-	asm volatile("ptesync": : :"memory");
+	ppc_after_tlbiel_barrier();
 	asm volatile(PPC_RADIX_INVALIDATE_ERAT_USER "; isync" : : :"memory");
 }
 
@@ -431,7 +431,7 @@ static __always_inline void _tlbiel_va(unsigned long va, unsigned long pid,
 
 	asm volatile("ptesync": : :"memory");
 	__tlbiel_va(va, pid, ap, ric);
-	asm volatile("ptesync": : :"memory");
+	ppc_after_tlbiel_barrier();
 }
 
 static inline void _tlbiel_va_range(unsigned long start, unsigned long end,
@@ -442,7 +442,7 @@ static inline void _tlbiel_va_range(unsigned long start, unsigned long end,
 	if (also_pwc)
 		__tlbiel_pid(pid, 0, RIC_FLUSH_PWC);
 	__tlbiel_va_range(start, end, pid, page_size, psize);
-	asm volatile("ptesync": : :"memory");
+	ppc_after_tlbiel_barrier();
 }
 
 static inline void __tlbie_va_range(unsigned long start, unsigned long end,
@@ -949,7 +949,7 @@ static inline void __radix__flush_tlb_range(struct mm_struct *mm,
 			if (hflush)
 				__tlbiel_va_range(hstart, hend, pid,
 						PMD_SIZE, MMU_PAGE_2M);
-			asm volatile("ptesync": : :"memory");
+			ppc_after_tlbiel_barrier();
 		} else if (cputlb_use_tlbie()) {
 			asm volatile("ptesync": : :"memory");
 			__tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize);