Re: [1/1] bpf: take advantage of stack_depth tracking in powerpc JIT

[Michael Ellerman]

On Fri, 2017-09-01 at 18:53:01 UTC, Sandipan Das wrote:
> Take advantage of stack_depth tracking, originally introduced for
> x64, in powerpc JIT as well. Round up allocated stack by 16 bytes
> to make sure it stays aligned for functions called from JITed bpf
> program.
> 
> Signed-off-by: Sandipan Das 
> Reviewed-by: Naveen N. Rao 

Applied to powerpc next, thanks.

https://git.kernel.org/powerpc/c/ac0761ebcb08830d8f64b9181f6736

cheers

Re: [PATCH 1/1] bpf: take advantage of stack_depth tracking in powerpc JIT

[Daniel Borkmann]

On 09/01/2017 08:53 PM, Sandipan Das wrote:

Take advantage of stack_depth tracking, originally introduced for
x64, in powerpc JIT as well. Round up allocated stack by 16 bytes
to make sure it stays aligned for functions called from JITed bpf
program.

Signed-off-by: Sandipan Das 


Awesome, thanks for following up! :)

Re: [PATCH 1/1] bpf: take advantage of stack_depth tracking in powerpc JIT

[Naveen N. Rao]

On 2017/09/02 12:23AM, Sandipan Das wrote:
> Take advantage of stack_depth tracking, originally introduced for
> x64, in powerpc JIT as well. Round up allocated stack by 16 bytes
> to make sure it stays aligned for functions called from JITed bpf
> program.
> 
> Signed-off-by: Sandipan Das 
> ---

LGTM, thanks!
Reviewed-by: Naveen N. Rao 

Michael,
Seeing as this is powerpc specific, can you please take this through 
your tree?


Thanks,
Naveen

>  arch/powerpc/net/bpf_jit64.h  |  7 ---
>  arch/powerpc/net/bpf_jit_comp64.c | 16 ++--
>  2 files changed, 14 insertions(+), 9 deletions(-)
> 
> diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h
> index 62fa7589db2b..8bdef7ed28a8 100644
> --- a/arch/powerpc/net/bpf_jit64.h
> +++ b/arch/powerpc/net/bpf_jit64.h
> @@ -23,7 +23,7 @@
>   *   [   nv gpr save area] 8*8   |
>   *   [tail_call_cnt  ] 8 |
>   *   [local_tmp_var  ] 8 |
> - * fp (r31) -->  [   ebpf stack space] 512   |
> + * fp (r31) -->  [   ebpf stack space] upto 512  |
>   *   [ frame header  ] 32/112|
>   * sp (r1) --->  [stack pointer  ] --
>   */
> @@ -32,8 +32,8 @@
>  #define BPF_PPC_STACK_SAVE   (8*8)
>  /* for bpf JIT code internal usage */
>  #define BPF_PPC_STACK_LOCALS 16
> -/* Ensure this is quadword aligned */
> -#define BPF_PPC_STACKFRAME   (STACK_FRAME_MIN_SIZE + MAX_BPF_STACK + \
> +/* stack frame excluding BPF stack, ensure this is quadword aligned */
> +#define BPF_PPC_STACKFRAME   (STACK_FRAME_MIN_SIZE + \
>BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE)
> 
>  #ifndef __ASSEMBLY__
> @@ -103,6 +103,7 @@ struct codegen_context {
>*/
>   unsigned int seen;
>   unsigned int idx;
> + unsigned int stack_size;
>  };
> 
>  #endif /* !__ASSEMBLY__ */
> diff --git a/arch/powerpc/net/bpf_jit_comp64.c 
> b/arch/powerpc/net/bpf_jit_comp64.c
> index 6ba5d253e857..a01362c88f6a 100644
> --- a/arch/powerpc/net/bpf_jit_comp64.c
> +++ b/arch/powerpc/net/bpf_jit_comp64.c
> @@ -69,7 +69,7 @@ static inline bool bpf_has_stack_frame(struct 
> codegen_context *ctx)
>  static int bpf_jit_stack_local(struct codegen_context *ctx)
>  {
>   if (bpf_has_stack_frame(ctx))
> - return STACK_FRAME_MIN_SIZE + MAX_BPF_STACK;
> + return STACK_FRAME_MIN_SIZE + ctx->stack_size;
>   else
>   return -(BPF_PPC_STACK_SAVE + 16);
>  }
> @@ -82,8 +82,9 @@ static int bpf_jit_stack_tailcallcnt(struct codegen_context 
> *ctx)
>  static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg)
>  {
>   if (reg >= BPF_PPC_NVR_MIN && reg < 32)
> - return (bpf_has_stack_frame(ctx) ? BPF_PPC_STACKFRAME : 0)
> - - (8 * (32 - reg));
> + return (bpf_has_stack_frame(ctx) ?
> + (BPF_PPC_STACKFRAME + ctx->stack_size) : 0)
> + - (8 * (32 - reg));
> 
>   pr_err("BPF JIT is asking about unknown registers");
>   BUG();
> @@ -134,7 +135,7 @@ static void bpf_jit_build_prologue(u32 *image, struct 
> codegen_context *ctx)
>   PPC_BPF_STL(0, 1, PPC_LR_STKOFF);
>   }
> 
> - PPC_BPF_STLU(1, 1, -BPF_PPC_STACKFRAME);
> + PPC_BPF_STLU(1, 1, -(BPF_PPC_STACKFRAME + ctx->stack_size));
>   }
> 
>   /*
> @@ -161,7 +162,7 @@ static void bpf_jit_build_prologue(u32 *image, struct 
> codegen_context *ctx)
>   /* Setup frame pointer to point to the bpf stack area */
>   if (bpf_is_seen_register(ctx, BPF_REG_FP))
>   PPC_ADDI(b2p[BPF_REG_FP], 1,
> - STACK_FRAME_MIN_SIZE + MAX_BPF_STACK);
> + STACK_FRAME_MIN_SIZE + ctx->stack_size);
>  }
> 
>  static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context 
> *ctx)
> @@ -183,7 +184,7 @@ static void bpf_jit_emit_common_epilogue(u32 *image, 
> struct codegen_context *ctx
> 
>   /* Tear down our stack frame */
>   if (bpf_has_stack_frame(ctx)) {
> - PPC_ADDI(1, 1, BPF_PPC_STACKFRAME);
> + PPC_ADDI(1, 1, BPF_PPC_STACKFRAME + ctx->stack_size);
>   if (ctx->seen & SEEN_FUNC) {
>   PPC_BPF_LL(0, 1, PPC_LR_STKOFF);
>   PPC_MTLR(0);
> @@ -993,6 +994,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
> 
>   memset(, 0, sizeof(struct codegen_context));
> 
> + /* Make sure that the stack is quadword aligned. */
> + cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
> +
>   /* Scouting faux-generate pass 0 */
>   if (bpf_jit_build_body(fp, 0, , addrs)) {
>   /* We hit something illegal or unsupported. */
> -- 
> 2.13.5
> 

[PATCH 1/1] bpf: take advantage of stack_depth tracking in powerpc JIT

[Sandipan Das]

Take advantage of stack_depth tracking, originally introduced for
x64, in powerpc JIT as well. Round up allocated stack by 16 bytes
to make sure it stays aligned for functions called from JITed bpf
program.

Signed-off-by: Sandipan Das 
---
 arch/powerpc/net/bpf_jit64.h  |  7 ---
 arch/powerpc/net/bpf_jit_comp64.c | 16 ++--
 2 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h
index 62fa7589db2b..8bdef7ed28a8 100644
--- a/arch/powerpc/net/bpf_jit64.h
+++ b/arch/powerpc/net/bpf_jit64.h
@@ -23,7 +23,7 @@
  * [   nv gpr save area] 8*8   |
  * [tail_call_cnt  ] 8 |
  * [local_tmp_var  ] 8 |
- * fp (r31) -->[   ebpf stack space] 512   |
+ * fp (r31) -->[   ebpf stack space] upto 512  |
  * [ frame header  ] 32/112|
  * sp (r1) --->[stack pointer  ] --
  */
@@ -32,8 +32,8 @@
 #define BPF_PPC_STACK_SAVE (8*8)
 /* for bpf JIT code internal usage */
 #define BPF_PPC_STACK_LOCALS   16
-/* Ensure this is quadword aligned */
-#define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + MAX_BPF_STACK + \
+/* stack frame excluding BPF stack, ensure this is quadword aligned */
+#define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + \
 BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE)
 
 #ifndef __ASSEMBLY__
@@ -103,6 +103,7 @@ struct codegen_context {
 */
unsigned int seen;
unsigned int idx;
+   unsigned int stack_size;
 };
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/powerpc/net/bpf_jit_comp64.c 
b/arch/powerpc/net/bpf_jit_comp64.c
index 6ba5d253e857..a01362c88f6a 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -69,7 +69,7 @@ static inline bool bpf_has_stack_frame(struct codegen_context 
*ctx)
 static int bpf_jit_stack_local(struct codegen_context *ctx)
 {
if (bpf_has_stack_frame(ctx))
-   return STACK_FRAME_MIN_SIZE + MAX_BPF_STACK;
+   return STACK_FRAME_MIN_SIZE + ctx->stack_size;
else
return -(BPF_PPC_STACK_SAVE + 16);
 }
@@ -82,8 +82,9 @@ static int bpf_jit_stack_tailcallcnt(struct codegen_context 
*ctx)
 static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg)
 {
if (reg >= BPF_PPC_NVR_MIN && reg < 32)
-   return (bpf_has_stack_frame(ctx) ? BPF_PPC_STACKFRAME : 0)
-   - (8 * (32 - reg));
+   return (bpf_has_stack_frame(ctx) ?
+   (BPF_PPC_STACKFRAME + ctx->stack_size) : 0)
+   - (8 * (32 - reg));
 
pr_err("BPF JIT is asking about unknown registers");
BUG();
@@ -134,7 +135,7 @@ static void bpf_jit_build_prologue(u32 *image, struct 
codegen_context *ctx)
PPC_BPF_STL(0, 1, PPC_LR_STKOFF);
}
 
-   PPC_BPF_STLU(1, 1, -BPF_PPC_STACKFRAME);
+   PPC_BPF_STLU(1, 1, -(BPF_PPC_STACKFRAME + ctx->stack_size));
}
 
/*
@@ -161,7 +162,7 @@ static void bpf_jit_build_prologue(u32 *image, struct 
codegen_context *ctx)
/* Setup frame pointer to point to the bpf stack area */
if (bpf_is_seen_register(ctx, BPF_REG_FP))
PPC_ADDI(b2p[BPF_REG_FP], 1,
-   STACK_FRAME_MIN_SIZE + MAX_BPF_STACK);
+   STACK_FRAME_MIN_SIZE + ctx->stack_size);
 }
 
 static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context 
*ctx)
@@ -183,7 +184,7 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct 
codegen_context *ctx
 
/* Tear down our stack frame */
if (bpf_has_stack_frame(ctx)) {
-   PPC_ADDI(1, 1, BPF_PPC_STACKFRAME);
+   PPC_ADDI(1, 1, BPF_PPC_STACKFRAME + ctx->stack_size);
if (ctx->seen & SEEN_FUNC) {
PPC_BPF_LL(0, 1, PPC_LR_STKOFF);
PPC_MTLR(0);
@@ -993,6 +994,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 
memset(, 0, sizeof(struct codegen_context));
 
+   /* Make sure that the stack is quadword aligned. */
+   cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
+
/* Scouting faux-generate pass 0 */
if (bpf_jit_build_body(fp, 0, , addrs)) {
/* We hit something illegal or unsupported. */
-- 
2.13.5