Re: [v2] Fix __tlbiel in hash_native_64

[Michael Ellerman]

On Tue, 2016-13-09 at 06:40:07 UTC, Balbir Singh wrote:
> __tlbie and __tlbiel are out of sync. __tlbie does the right thing
> it calls tlbie with "tlbie rb, L" if CPU_FTR_ARCH_206 (cpu feature) is clear
> and with "tlbie rb" otherwise. During the cleanup of __tlbiel I noticed
> that __tlbiel was setting bit 11 PPC_BIT(21) independent of the ISA
> version for non-4k (L) pages. This patch fixes that issue. It also changes
> the current PPC_TLBIEL to PPC_TLBIEL_5 and introduces a new PPC_TLBIEL similar
> to PPC_TLBIE.

This should give more description of what the problem is, ie. we're setting a
bit in the instruction which is reserved on some processors, before talking
about the solution or what tlbie does.
 
> The arguments to PPC_TLBIE have also been changed/switched in order
> to be consistent with the actual assembly usage for clearer reading
> of code.

The whole thing should be split in 3 patches:

One which fixes the buglet where we set L=1 on 2.06 and 2.07.
One which renames PPC_TLBIEL() to PPC_TLBIEL_5().
One which switches the order of the arguments to PPC_TLBIEL().

Also do we even need a macro for the two argument form? We've had uses of the
two argument tlbie since 2011, so I suspect the assembler will happily accept
it?

cheers

[PATCH v2] Fix __tlbiel in hash_native_64

[Balbir Singh]

__tlbie and __tlbiel are out of sync. __tlbie does the right thing
it calls tlbie with "tlbie rb, L" if CPU_FTR_ARCH_206 (cpu feature) is clear
and with "tlbie rb" otherwise. During the cleanup of __tlbiel I noticed
that __tlbiel was setting bit 11 PPC_BIT(21) independent of the ISA
version for non-4k (L) pages. This patch fixes that issue. It also changes
the current PPC_TLBIEL to PPC_TLBIEL_5 and introduces a new PPC_TLBIEL similar
to PPC_TLBIE.

The arguments to PPC_TLBIE have also been changed/switched in order
to be consistent with the actual assembly usage for clearer reading
of code.

Cc: Paul Mackerras 
Cc: Aneesh Kumar K.V 
Cc: Michael Ellerman 
Cc: Benjamin Herrenschmidt 

Signed-off-by: Balbir Singh 
---
 arch/powerpc/include/asm/ppc-opcode.h |  9 ++---
 arch/powerpc/mm/hash_native_64.c  | 14 --
 arch/powerpc/mm/tlb-radix.c   |  4 ++--
 3 files changed, 16 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/include/asm/ppc-opcode.h 
b/arch/powerpc/include/asm/ppc-opcode.h
index 127ebf5..308004a 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -354,14 +354,17 @@
 #define PPC_TLBILX_VA(a, b)PPC_TLBILX(3, a, b)
 #define PPC_WAIT(w)stringify_in_c(.long PPC_INST_WAIT | \
__PPC_WC(w))
-#define PPC_TLBIE(lp,a)stringify_in_c(.long PPC_INST_TLBIE | \
-  ___PPC_RB(a) | ___PPC_RS(lp))
+#define PPC_TLBIE(rb,lp)   stringify_in_c(.long PPC_INST_TLBIE | \
+  ___PPC_RB(rb) | ___PPC_RS(lp))
 #definePPC_TLBIE_5(rb,rs,ric,prs,r) \
stringify_in_c(.long PPC_INST_TLBIE | \
___PPC_RB(rb) | ___PPC_RS(rs) | \
___PPC_RIC(ric) | ___PPC_PRS(prs) | \
___PPC_R(r))
-#definePPC_TLBIEL(rb,rs,ric,prs,r) \
+#definePPC_TLBIEL(rb,lp) \
+   stringify_in_c(.long PPC_INST_TLBIEL | \
+   ___PPC_RB(rb) | ___PPC_RS(lp))
+#definePPC_TLBIEL_5(rb,rs,ric,prs,r) \
stringify_in_c(.long PPC_INST_TLBIEL | \
___PPC_RB(rb) | ___PPC_RS(rs) | \
___PPC_RIC(ric) | ___PPC_PRS(prs) | \
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 0e4e965..b3c34c8 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -74,7 +74,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int 
apsize, int ssize)
va |= ssize << 8;
sllp = get_sllp_encoding(apsize);
va |= sllp << 5;
-   asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2)
+   asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%0,%1), %2)
 : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
 : "memory");
break;
@@ -93,7 +93,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int 
apsize, int ssize)
 */
va |= (vpn & 0xfe); /* AVAL */
va |= 1; /* L */
-   asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2)
+   asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%0,%1), %2)
 : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
 : "memory");
break;
@@ -123,8 +123,9 @@ static inline void __tlbiel(unsigned long vpn, int psize, 
int apsize, int ssize)
va |= ssize << 8;
sllp = get_sllp_encoding(apsize);
va |= sllp << 5;
-   asm volatile(".long 0x7c000224 | (%0 << 11) | (0 << 21)"
-: : "r"(va) : "memory");
+   asm volatile(ASM_FTR_IFCLR("tlbiel %0,0", PPC_TLBIEL(%0,0), %1)
+: : "r" (va),  "i" (CPU_FTR_ARCH_206)
+: "memory");
break;
default:
/* We need 14 to 14 + i bits of va */
@@ -141,8 +142,9 @@ static inline void __tlbiel(unsigned long vpn, int psize, 
int apsize, int ssize)
 */
va |= (vpn & 0xfe);
va |= 1; /* L */
-   asm volatile(".long 0x7c000224 | (%0 << 11) | (1 << 21)"
-: : "r"(va) : "memory");
+   asm volatile(ASM_FTR_IFCLR("tlbiel %0,1", PPC_TLBIEL(%0,0), %1)
+: : "r" (va), "i" (CPU_FTR_ARCH_206)
+: "memory");
break;
}
 
diff --git a/arch/powerpc/mm/tlb-radix.c