[PATCH] powerpc/bpf/32: Fix Oops on tail call tests

2022-11-19 Thread Christophe Leroy
test_bpf tail call tests end up as:

  test_bpf: #0 Tail call leaf jited:1 85 PASS
  test_bpf: #1 Tail call 2 jited:1 111 PASS
  test_bpf: #2 Tail call 3 jited:1 145 PASS
  test_bpf: #3 Tail call 4 jited:1 170 PASS
  test_bpf: #4 Tail call load/store leaf jited:1 190 PASS
  test_bpf: #5 Tail call load/store jited:1
  BUG: Unable to handle kernel data access on write at 0xf1b4e000
  Faulting instruction address: 0xbe86b710
  Oops: Kernel access of bad area, sig: 11 [#1]
  BE PAGE_SIZE=4K MMU=Hash PowerMac
  Modules linked in: test_bpf(+)
  CPU: 0 PID: 97 Comm: insmod Not tainted 6.1.0-rc4+ #195
  Hardware name: PowerMac3,1 750CL 0x87210 PowerMac
  NIP:  be86b710 LR: be857e88 CTR: be86b704
  REGS: f1b4df20 TRAP: 0300   Not tainted  (6.1.0-rc4+)
  MSR:  9032   CR: 28008242  XER: 
  DAR: f1b4e000 DSISR: 4200
  GPR00: 0001 f1b4dfe0 c11d2280    0002 
  GPR08: f1b4e000 be86b704 f1b4e000   100d816a f244 fe73baa8
  GPR16: f2458000  c1941ae4 f1fe2248 0045 c0de f2458030 
  GPR24: 03e8 000f f2458000 f1b4dc90 3e584b46  f24466a0 c1941a00
  NIP [be86b710] 0xbe86b710
  LR [be857e88] __run_one+0xec/0x264 [test_bpf]
  Call Trace:
  [f1b4dfe0] [0002] 0x2 (unreliable)
  Instruction dump:
         
         
  ---[ end trace  ]---

This is a tentative to write above the stack. The problem is encoutered
with tests added by commit 38608ee7b690 ("bpf, tests: Add load store
test case for tail call")

This happens because tail call is done to a BPF prog with a different
stack_depth. At the time being, the stack is kept as is when the caller
tail calls its callee. But at exit, the callee restores the stack based
on its own properties. Therefore here, at each run, r1 is erroneously
increased by 32 - 16 = 16 bytes.

This was done that way in order to pass the tail call count from caller
to callee through the stack. As powerpc32 doesn't have a red zone in
the stack, it was necessary the maintain the stack as is for the tail
call. But it was not anticipated that the BPF frame size could be
different.

Let's take a new approach. Use register r0 to carry the tail call count
during the tail call, and save it into the stack at function entry if
required. That's a deviation from the ppc32 ABI, but after all the way
tail calls are implemented is already not in accordance with the ABI.

With the fix, tail call tests are now successfull:

  test_bpf: #0 Tail call leaf jited:1 53 PASS
  test_bpf: #1 Tail call 2 jited:1 115 PASS
  test_bpf: #2 Tail call 3 jited:1 154 PASS
  test_bpf: #3 Tail call 4 jited:1 165 PASS
  test_bpf: #4 Tail call load/store leaf jited:1 101 PASS
  test_bpf: #5 Tail call load/store jited:1 141 PASS
  test_bpf: #6 Tail call error path, max count reached jited:1 994 PASS
  test_bpf: #7 Tail call count preserved across function calls jited:1 140975 
PASS
  test_bpf: #8 Tail call error path, NULL target jited:1 110 PASS
  test_bpf: #9 Tail call error path, index out of range jited:1 69 PASS
  test_bpf: test_tail_calls: Summary: 10 PASSED, 0 FAILED, [10/10 JIT'ed]

Fixes: 51c66ad849a7 ("powerpc/bpf: Implement extended BPF on PPC32")
Cc: sta...@vger.kernel.org
Signed-off-by: Christophe Leroy 
---
 arch/powerpc/net/bpf_jit_comp32.c | 25 +++--
 1 file changed, 11 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp32.c 
b/arch/powerpc/net/bpf_jit_comp32.c
index 43f1c76d48ce..97e75b8181ca 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -115,21 +115,19 @@ void bpf_jit_build_prologue(u32 *image, struct 
codegen_context *ctx)
 
/* First arg comes in as a 32 bits pointer. */
EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_1), _R3));
-   EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_1) - 1, 0));
+   EMIT(PPC_RAW_LI(_R0, 0));
+
+#define BPF_TAILCALL_PROLOGUE_SIZE 8
+
EMIT(PPC_RAW_STWU(_R1, _R1, -BPF_PPC_STACKFRAME(ctx)));
 
/*
-* Initialize tail_call_cnt in stack frame if we do tail calls.
-* Otherwise, put in NOPs so that it can be skipped when we are
-* invoked through a tail call.
+* Save tail_call_cnt in stack frame if we do tail calls.
 */
if (ctx->seen & SEEN_TAILCALL)
-   EMIT(PPC_RAW_STW(bpf_to_ppc(BPF_REG_1) - 1, _R1,
-bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
-   else
-   EMIT(PPC_RAW_NOP());
+   EMIT(PPC_RAW_STW(_R0, _R1, bpf_jit_stack_offsetof(ctx, 
BPF_PPC_TC)));
 
-#define BPF_TAILCALL_PROLOGUE_SIZE 16
+   EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_1) - 1, 0));
 
/*
 * We need a stack frame, but we don't necessarily need to
@@ -244,7 +242,6 @@ static int bpf_jit_emit_tail_call(u32 *image, struct 
codegen_context *ctx, u32 o
  

Re: [PATCH] powerpc/bpf/32: Fix Oops on tail call tests

2022-11-21 Thread Naveen N. Rao

Christophe Leroy wrote:

test_bpf tail call tests end up as:

  test_bpf: #0 Tail call leaf jited:1 85 PASS
  test_bpf: #1 Tail call 2 jited:1 111 PASS
  test_bpf: #2 Tail call 3 jited:1 145 PASS
  test_bpf: #3 Tail call 4 jited:1 170 PASS
  test_bpf: #4 Tail call load/store leaf jited:1 190 PASS
  test_bpf: #5 Tail call load/store jited:1
  BUG: Unable to handle kernel data access on write at 0xf1b4e000
  Faulting instruction address: 0xbe86b710
  Oops: Kernel access of bad area, sig: 11 [#1]
  BE PAGE_SIZE=4K MMU=Hash PowerMac
  Modules linked in: test_bpf(+)
  CPU: 0 PID: 97 Comm: insmod Not tainted 6.1.0-rc4+ #195
  Hardware name: PowerMac3,1 750CL 0x87210 PowerMac
  NIP:  be86b710 LR: be857e88 CTR: be86b704
  REGS: f1b4df20 TRAP: 0300   Not tainted  (6.1.0-rc4+)
  MSR:  9032   CR: 28008242  XER: 
  DAR: f1b4e000 DSISR: 4200
  GPR00: 0001 f1b4dfe0 c11d2280    0002 
  GPR08: f1b4e000 be86b704 f1b4e000   100d816a f244 fe73baa8
  GPR16: f2458000  c1941ae4 f1fe2248 0045 c0de f2458030 
  GPR24: 03e8 000f f2458000 f1b4dc90 3e584b46  f24466a0 c1941a00
  NIP [be86b710] 0xbe86b710
  LR [be857e88] __run_one+0xec/0x264 [test_bpf]
  Call Trace:
  [f1b4dfe0] [0002] 0x2 (unreliable)
  Instruction dump:
         
         
  ---[ end trace  ]---

This is a tentative to write above the stack. The problem is encoutered
with tests added by commit 38608ee7b690 ("bpf, tests: Add load store
test case for tail call")

This happens because tail call is done to a BPF prog with a different
stack_depth. At the time being, the stack is kept as is when the caller
tail calls its callee. But at exit, the callee restores the stack based
on its own properties. Therefore here, at each run, r1 is erroneously
increased by 32 - 16 = 16 bytes.

This was done that way in order to pass the tail call count from caller
to callee through the stack. As powerpc32 doesn't have a red zone in
the stack, it was necessary the maintain the stack as is for the tail
call. But it was not anticipated that the BPF frame size could be
different.

Let's take a new approach. Use register r0 to carry the tail call count
during the tail call, and save it into the stack at function entry if
required. That's a deviation from the ppc32 ABI, but after all the way
tail calls are implemented is already not in accordance with the ABI.


Can we pass the tail call count in r4 instead?



With the fix, tail call tests are now successfull:

  test_bpf: #0 Tail call leaf jited:1 53 PASS
  test_bpf: #1 Tail call 2 jited:1 115 PASS
  test_bpf: #2 Tail call 3 jited:1 154 PASS
  test_bpf: #3 Tail call 4 jited:1 165 PASS
  test_bpf: #4 Tail call load/store leaf jited:1 101 PASS
  test_bpf: #5 Tail call load/store jited:1 141 PASS
  test_bpf: #6 Tail call error path, max count reached jited:1 994 PASS
  test_bpf: #7 Tail call count preserved across function calls jited:1 140975 
PASS
  test_bpf: #8 Tail call error path, NULL target jited:1 110 PASS
  test_bpf: #9 Tail call error path, index out of range jited:1 69 PASS
  test_bpf: test_tail_calls: Summary: 10 PASSED, 0 FAILED, [10/10 JIT'ed]

Fixes: 51c66ad849a7 ("powerpc/bpf: Implement extended BPF on PPC32")
Cc: sta...@vger.kernel.org
Signed-off-by: Christophe Leroy 
---
 arch/powerpc/net/bpf_jit_comp32.c | 25 +++--
 1 file changed, 11 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp32.c 
b/arch/powerpc/net/bpf_jit_comp32.c
index 43f1c76d48ce..97e75b8181ca 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -115,21 +115,19 @@ void bpf_jit_build_prologue(u32 *image, struct 
codegen_context *ctx)
 
 	/* First arg comes in as a 32 bits pointer. */

EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_1), _R3));
-   EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_1) - 1, 0));
+   EMIT(PPC_RAW_LI(_R0, 0));
+
+#define BPF_TAILCALL_PROLOGUE_SIZE 8
+
EMIT(PPC_RAW_STWU(_R1, _R1, -BPF_PPC_STACKFRAME(ctx)));
 
 	/*

-* Initialize tail_call_cnt in stack frame if we do tail calls.
-* Otherwise, put in NOPs so that it can be skipped when we are
-* invoked through a tail call.
+* Save tail_call_cnt in stack frame if we do tail calls.
 */
if (ctx->seen & SEEN_TAILCALL)
-   EMIT(PPC_RAW_STW(bpf_to_ppc(BPF_REG_1) - 1, _R1,
-bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
-   else
-   EMIT(PPC_RAW_NOP());
+   EMIT(PPC_RAW_STW(_R0, _R1, bpf_jit_stack_offsetof(ctx, 
BPF_PPC_TC)));
 
-#define BPF_TAILCALL_PROLOGUE_SIZE	16

+   EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_1) - 1, 0));
 
 	/*

 * We need a stack frame, but we don't necessarily need to
@@ -244,7 +242,6 @@ static int bpf_jit_emit_t

Re: [PATCH] powerpc/bpf/32: Fix Oops on tail call tests

2022-11-21 Thread Christophe Leroy


Le 22/11/2022 à 08:33, Naveen N. Rao a écrit :
> Christophe Leroy wrote:
>> test_bpf tail call tests end up as:
>>
>>   test_bpf: #0 Tail call leaf jited:1 85 PASS
>>   test_bpf: #1 Tail call 2 jited:1 111 PASS
>>   test_bpf: #2 Tail call 3 jited:1 145 PASS
>>   test_bpf: #3 Tail call 4 jited:1 170 PASS
>>   test_bpf: #4 Tail call load/store leaf jited:1 190 PASS
>>   test_bpf: #5 Tail call load/store jited:1
>>   BUG: Unable to handle kernel data access on write at 0xf1b4e000
>>   Faulting instruction address: 0xbe86b710
>>   Oops: Kernel access of bad area, sig: 11 [#1]
>>   BE PAGE_SIZE=4K MMU=Hash PowerMac
>>   Modules linked in: test_bpf(+)
>>   CPU: 0 PID: 97 Comm: insmod Not tainted 6.1.0-rc4+ #195
>>   Hardware name: PowerMac3,1 750CL 0x87210 PowerMac
>>   NIP:  be86b710 LR: be857e88 CTR: be86b704
>>   REGS: f1b4df20 TRAP: 0300   Not tainted  (6.1.0-rc4+)
>>   MSR:  9032   CR: 28008242  XER: 
>>   DAR: f1b4e000 DSISR: 4200
>>   GPR00: 0001 f1b4dfe0 c11d2280    
>> 0002 
>>   GPR08: f1b4e000 be86b704 f1b4e000   100d816a 
>> f244 fe73baa8
>>   GPR16: f2458000  c1941ae4 f1fe2248 0045 c0de 
>> f2458030 
>>   GPR24: 03e8 000f f2458000 f1b4dc90 3e584b46  
>> f24466a0 c1941a00
>>   NIP [be86b710] 0xbe86b710
>>   LR [be857e88] __run_one+0xec/0x264 [test_bpf]
>>   Call Trace:
>>   [f1b4dfe0] [0002] 0x2 (unreliable)
>>   Instruction dump:
>>          
>>          
>>   ---[ end trace  ]---
>>
>> This is a tentative to write above the stack. The problem is encoutered
>> with tests added by commit 38608ee7b690 ("bpf, tests: Add load store
>> test case for tail call")
>>
>> This happens because tail call is done to a BPF prog with a different
>> stack_depth. At the time being, the stack is kept as is when the caller
>> tail calls its callee. But at exit, the callee restores the stack based
>> on its own properties. Therefore here, at each run, r1 is erroneously
>> increased by 32 - 16 = 16 bytes.
>>
>> This was done that way in order to pass the tail call count from caller
>> to callee through the stack. As powerpc32 doesn't have a red zone in
>> the stack, it was necessary the maintain the stack as is for the tail
>> call. But it was not anticipated that the BPF frame size could be
>> different.
>>
>> Let's take a new approach. Use register r0 to carry the tail call count
>> during the tail call, and save it into the stack at function entry if
>> required. That's a deviation from the ppc32 ABI, but after all the way
>> tail calls are implemented is already not in accordance with the ABI.
> 
> Can we pass the tail call count in r4 instead?

It's a bit tricky.

When entering the function through the normal entry point, the input 
parameter is a 32 bits pointer and is in r3.
But at the begining of the function it gets moved to r4 and r3 is 
cleared because it becomes a 64 bits parameter.

When using the tailcall entry point, it is already in r4, and until now 
r3 was containing garbage, with this patch r3 gets cleared as well.

We could move the input pointer back into r3 for the tailcall as well, 
but it would mean unnecessary register move.

Or we can use r3 for the tailcall counter.

Or I should make r3,r4 a proper 64 bits param (Meaning clearing r3 
before the call instead of doing it at function tailcall entry), and use 
r5 for the tailcall counter. Maybe that's the cleanest.

> 
>>
>> With the fix, tail call tests are now successfull:
>>
>>   test_bpf: #0 Tail call leaf jited:1 53 PASS
>>   test_bpf: #1 Tail call 2 jited:1 115 PASS
>>   test_bpf: #2 Tail call 3 jited:1 154 PASS
>>   test_bpf: #3 Tail call 4 jited:1 165 PASS
>>   test_bpf: #4 Tail call load/store leaf jited:1 101 PASS
>>   test_bpf: #5 Tail call load/store jited:1 141 PASS
>>   test_bpf: #6 Tail call error path, max count reached jited:1 994 PASS
>>   test_bpf: #7 Tail call count preserved across function calls jited:1 
>> 140975 PASS
>>   test_bpf: #8 Tail call error path, NULL target jited:1 110 PASS
>>   test_bpf: #9 Tail call error path, index out of range jited:1 69 PASS
>>   test_bpf: test_tail_calls: Summary: 10 PASSED, 0 FAILED, [10/10 JIT'ed]
>>
>> Fixes: 51c66ad849a7 ("powerpc/bpf: Implement extended BPF on PPC32")
>> Cc: sta...@vger.kernel.org
>> Signed-off-by: Christophe Leroy 
>> ---
>>  arch/powerpc/net/bpf_jit_comp32.c | 25 +++--
>>  1 file changed, 11 insertions(+), 14 deletions(-)
>>
>> diff --git a/arch/powerpc/net/bpf_jit_comp32.c 
>> b/arch/powerpc/net/bpf_jit_comp32.c
>> index 43f1c76d48ce..97e75b8181ca 100644
>> --- a/arch/powerpc/net/bpf_jit_comp32.c
>> +++ b/arch/powerpc/net/bpf_jit_comp32.c
>> @@ -115,21 +115,19 @@ void bpf_jit_build_prologue(u32 *image, struct 
>> codegen_context *ctx)
>>
>>  /* First arg comes in as a 32 bits poin

Re: [PATCH] powerpc/bpf/32: Fix Oops on tail call tests

2022-11-22 Thread Naveen N. Rao

Christophe Leroy wrote:



Le 22/11/2022 à 08:33, Naveen N. Rao a écrit :

Christophe Leroy wrote:


This is a tentative to write above the stack. The problem is encoutered
with tests added by commit 38608ee7b690 ("bpf, tests: Add load store
test case for tail call")

This happens because tail call is done to a BPF prog with a different
stack_depth. At the time being, the stack is kept as is when the caller
tail calls its callee. But at exit, the callee restores the stack based
on its own properties. Therefore here, at each run, r1 is erroneously
increased by 32 - 16 = 16 bytes.

This was done that way in order to pass the tail call count from caller
to callee through the stack. As powerpc32 doesn't have a red zone in
the stack, it was necessary the maintain the stack as is for the tail
call. But it was not anticipated that the BPF frame size could be
different.

Let's take a new approach. Use register r0 to carry the tail call count
during the tail call, and save it into the stack at function entry if
required. That's a deviation from the ppc32 ABI, but after all the way
tail calls are implemented is already not in accordance with the ABI.


Can we pass the tail call count in r4 instead?


It's a bit tricky.

When entering the function through the normal entry point, the input 
parameter is a 32 bits pointer and is in r3.
But at the begining of the function it gets moved to r4 and r3 is 
cleared because it becomes a 64 bits parameter.


When using the tailcall entry point, it is already in r4, and until now 
r3 was containing garbage, with this patch r3 gets cleared as well.


We could move the input pointer back into r3 for the tailcall as well, 
but it would mean unnecessary register move.


Or we can use r3 for the tailcall counter.


Regarding zero'ing out r5, you're right -- we don't use the second 
parameter for a tail call, so that should be fine.


Using r3 will be difficult since it is used when you come in first.
My suggestion was something like the below (untested). Using r5 might be 
fine too.


- Naveen

--
diff --git a/arch/powerpc/net/bpf_jit_comp32.c 
b/arch/powerpc/net/bpf_jit_comp32.c
index 43f1c76d48cea9..6319283ce4ef01 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -113,24 +113,19 @@ void bpf_jit_build_prologue(u32 *image, struct 
codegen_context *ctx)
{
int i;

+   /* Initialize tail_call_cnt, to be skipped if we do tail calls. */
+   EMIT(PPC_RAW_LI(_R4, 0));
+
+#define BPF_TAILCALL_PROLOGUE_SIZE 4
+
+   if (ctx->seen & SEEN_TAILCALL)
+   EMIT(PPC_RAW_STW(_R4, _R1, bpf_jit_stack_offsetof(ctx, 
BPF_PPC_TC)));
+
/* First arg comes in as a 32 bits pointer. */
EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_1), _R3));
EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_1) - 1, 0));
EMIT(PPC_RAW_STWU(_R1, _R1, -BPF_PPC_STACKFRAME(ctx)));

-   /*
-* Initialize tail_call_cnt in stack frame if we do tail calls.
-* Otherwise, put in NOPs so that it can be skipped when we are
-* invoked through a tail call.
-*/
-   if (ctx->seen & SEEN_TAILCALL)
-   EMIT(PPC_RAW_STW(bpf_to_ppc(BPF_REG_1) - 1, _R1,
-bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));
-   else
-   EMIT(PPC_RAW_NOP());
-
-#define BPF_TAILCALL_PROLOGUE_SIZE 16
-
/*
 * We need a stack frame, but we don't necessarily need to
 * save/restore LR unless we call other functions
@@ -170,24 +165,24 @@ static void bpf_jit_emit_common_epilogue(u32 *image, 
struct codegen_context *ctx
for (i = BPF_PPC_NVR_MIN; i <= 31; i++)
if (bpf_is_seen_register(ctx, i))
EMIT(PPC_RAW_LWZ(i, _R1, bpf_jit_stack_offsetof(ctx, 
i)));
-}
-
-void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
-{
-   EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0)));
-
-   bpf_jit_emit_common_epilogue(image, ctx);
-
-   /* Tear down our stack frame */

if (ctx->seen & SEEN_FUNC)
EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + 
PPC_LR_STKOFF));

+   /* Tear down our stack frame */
EMIT(PPC_RAW_ADDI(_R1, _R1, BPF_PPC_STACKFRAME(ctx)));

if (ctx->seen & SEEN_FUNC)
EMIT(PPC_RAW_MTLR(_R0));

+}
+
+void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
+{
+   EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0)));
+
+   bpf_jit_emit_common_epilogue(image, ctx);
+
EMIT(PPC_RAW_BLR());
}

@@ -244,7 +239,6 @@ static int bpf_jit_emit_tail_call(u32 *image, struct 
codegen_context *ctx, u32 o
EMIT(PPC_RAW_RLWINM(_R3, b2p_index, 2, 0, 29));
EMIT(PPC_RAW_ADD(_R3, _R3, b2p_bpf_array));
EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_array, ptrs)));
-   EMIT(PPC_RAW_STW(_R0, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));

/*
 * if (prog == NULL)
@@ -255,18 +249,11 @@ static int bpf_jit_emit_tail_call