public inbox for linuxppc-dev@ozlabs.org
 help / color / mirror / Atom feed
From: adubey@linux.ibm.com
To: bpf@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
	linux-kselftest@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: hbathini@linux.ibm.com, sachinpb@linux.ibm.com,
	venkat88@linux.ibm.com, andrii@kernel.org, eddyz87@gmail.com,
	mykolal@fb.com, ast@kernel.org, daniel@iogearbox.net,
	martin.lau@linux.dev, song@kernel.org, yonghong.song@linux.dev,
	john.fastabend@gmail.com, kpsingh@kernel.org, sdf@fomichev.me,
	haoluo@google.com, jolsa@kernel.org, christophe.leroy@csgroup.eu,
	naveen@kernel.org, maddy@linux.ibm.com, mpe@ellerman.id.au,
	npiggin@gmail.com, memxor@gmail.com, iii@linux.ibm.com,
	shuah@kernel.org, Abhishek Dubey <adubey@linux.ibm.com>
Subject: [PATCH v3 1/6] powerpc64/bpf : Moving tail_call_cnt to bottom of frame
Date: Thu, 22 Jan 2026 22:27:11 +0530	[thread overview]
Message-ID: <20260122165716.10508-2-adubey@linux.ibm.com> (raw)
In-Reply-To: <20260122165716.10508-1-adubey@linux.ibm.com>

From: Abhishek Dubey <adubey@linux.ibm.com>

In the conventional stack frame, the position of tail_call_cnt
is after the NVR save area (BPF_PPC_STACK_SAVE). Whereas, the
offset of tail_call_cnt in the trampoline frame is after the
stack alignment padding. BPF JIT logic could become complex
when dealing with frame-sensitive offset calculation of
tail_call_cnt. Having the same offset in both frames is the
desired objective.

The trampoline frame does not have a BPF_PPC_STACK_SAVE area.
Introducing it leads to under-utilization of extra memory meant
only for the offset alignment of tail_call_cnt.
Another challenge is the variable alignment padding sitting at
the bottom of the trampoline frame, which requires additional
handling to compute tail_call_cnt offset.

This patch addresses the above issues by moving tail_call_cnt
to the bottom of the stack frame at offset 0 for both types
of frames. This saves additional bytes required by BPF_PPC_STACK_SAVE
in trampoline frame, and a common offset computation for
tail_call_cnt serves both frames.

The changes in this patch are required by the second patch in the
series, where the 'reference to tail_call_info' of the main frame
is copied into the trampoline frame from the previous frame.

Signed-off-by: Abhishek Dubey <adubey@linux.ibm.com>
---
 arch/powerpc/net/bpf_jit.h        |  1 +
 arch/powerpc/net/bpf_jit_comp.c   | 13 +++++++++++--
 arch/powerpc/net/bpf_jit_comp64.c | 31 ++++++++++++++++++++-----------
 3 files changed, 32 insertions(+), 13 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 8334cd667bba..9f6ec00bd02e 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -24,6 +24,7 @@
 
 #define SZL			sizeof(unsigned long)
 #define BPF_INSN_SAFETY		64
+#define BPF_PPC_TAILCALL	8
 
 #define PLANT_INSTR(d, idx, instr)					      \
 	do { if (d) { (d)[idx] = instr; } idx++; } while (0)
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 5e976730b2f5..d5757577f933 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -604,8 +604,8 @@ static void bpf_trampoline_setup_tail_call_cnt(u32 *image, struct codegen_contex
 					       int func_frame_offset, int r4_off)
 {
 	if (IS_ENABLED(CONFIG_PPC64)) {
-		/* See bpf_jit_stack_tailcallcnt() */
-		int tailcallcnt_offset = 7 * 8;
+		/* See Generated stack layout */
+		int tailcallcnt_offset = BPF_PPC_TAILCALL;
 
 		EMIT(PPC_RAW_LL(_R3, _R1, func_frame_offset - tailcallcnt_offset));
 		EMIT(PPC_RAW_STL(_R3, _R1, -tailcallcnt_offset));
@@ -714,6 +714,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	 * LR save area                 [ r0 save (64-bit)  ]   | header
 	 *                              [ r0 save (32-bit)  ]   |
 	 * dummy frame for unwind       [ back chain 1      ] --
+	 *                              [ tail_call_cnt     ] optional - 64-bit powerpc
 	 *                              [ padding           ] align stack frame
 	 *       r4_off                 [ r4 (tailcallcnt)  ] optional - 32-bit powerpc
 	 *       alt_lr_off             [ real lr (ool stub)] optional - actual lr
@@ -795,6 +796,14 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		}
 	}
 
+	/*
+	 * Save tailcall count pointer at the same offset on the
+	 * stack where subprogs expect it
+	 */
+	if ((flags & BPF_TRAMP_F_CALL_ORIG) &&
+		(flags & BPF_TRAMP_F_TAIL_CALL_CTX))
+		bpf_frame_size += BPF_PPC_TAILCALL;
+
 	/* Padding to align stack frame, if any */
 	bpf_frame_size = round_up(bpf_frame_size, SZL * 2);
 
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 1fe37128c876..296e9ea14f2e 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -20,13 +20,15 @@
 #include "bpf_jit.h"
 
 /*
- * Stack layout:
+ * Stack layout with frame:
+ * Layout when setting up our own stack frame.
+ * Note: r1 at bottom, component offsets positive wrt r1.
  * Ensure the top half (upto local_tmp_var) stays consistent
  * with our redzone usage.
  *
  *		[	prev sp		] <-------------
- *		[   nv gpr save area	] 6*8		|
  *		[    tail_call_cnt	] 8		|
+ *		[   nv gpr save area	] 6*8		|
  *		[    local_tmp_var	] 24		|
  * fp (r31) -->	[   ebpf stack space	] upto 512	|
  *		[     frame header	] 32/112	|
@@ -36,10 +38,12 @@
 /* for gpr non volatile registers BPG_REG_6 to 10 */
 #define BPF_PPC_STACK_SAVE	(6*8)
 /* for bpf JIT code internal usage */
-#define BPF_PPC_STACK_LOCALS	32
+#define BPF_PPC_STACK_LOCALS	24
 /* 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)
+				 BPF_PPC_STACK_LOCALS + \
+				 BPF_PPC_STACK_SAVE   + \
+				 BPF_PPC_TAILCALL)
 
 /* BPF register usage */
 #define TMP_REG_1	(MAX_BPF_JIT_REG + 0)
@@ -87,27 +91,32 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
 }
 
 /*
+ * Stack layout with redzone:
  * When not setting up our own stackframe, the redzone (288 bytes) usage is:
+ * Note: r1 from prev frame. Component offset negative wrt r1.
  *
  *		[	prev sp		] <-------------
  *		[	  ...       	] 		|
  * sp (r1) --->	[    stack pointer	] --------------
- *		[   nv gpr save area	] 6*8
  *		[    tail_call_cnt	] 8
+ *		[   nv gpr save area	] 6*8
  *		[    local_tmp_var	] 24
  *		[   unused red zone	] 224
  */
 static int bpf_jit_stack_local(struct codegen_context *ctx)
 {
-	if (bpf_has_stack_frame(ctx))
+	if (bpf_has_stack_frame(ctx)) {
+		/* Stack layout with frame */
 		return STACK_FRAME_MIN_SIZE + ctx->stack_size;
-	else
-		return -(BPF_PPC_STACK_SAVE + 32);
+	} else {
+		/* Stack layout with redzone */
+		return -(BPF_PPC_TAILCALL + BPF_PPC_STACK_SAVE + BPF_PPC_STACK_LOCALS);
+	}
 }
 
 static int bpf_jit_stack_tailcallcnt(struct codegen_context *ctx)
 {
-	return bpf_jit_stack_local(ctx) + 24;
+	return bpf_jit_stack_local(ctx) + BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE;
 }
 
 static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg)
@@ -115,7 +124,7 @@ 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 + ctx->stack_size) : 0)
-				- (8 * (32 - reg));
+				- (8 * (32 - reg)) - BPF_PPC_TAILCALL;
 
 	pr_err("BPF JIT is asking about unknown registers");
 	BUG();
@@ -145,7 +154,7 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 	if (ctx->seen & SEEN_TAILCALL) {
 		EMIT(PPC_RAW_LI(bpf_to_ppc(TMP_REG_1), 0));
 		/* this goes in the redzone */
-		EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), _R1, -(BPF_PPC_STACK_SAVE + 8)));
+		EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), _R1, -(BPF_PPC_TAILCALL)));
 	} else {
 		EMIT(PPC_RAW_NOP());
 		EMIT(PPC_RAW_NOP());
-- 
2.48.1



  reply	other threads:[~2026-01-22 16:58 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-22 16:57 [PATCH v3 0/6] powerpc64/bpf: Support tailcalls with subprogs & BPF exceptions adubey
2026-01-22 16:57 ` adubey [this message]
2026-01-22 17:20   ` [PATCH v3 1/6] powerpc64/bpf : Moving tail_call_cnt to bottom of frame bot+bpf-ci
2026-01-22 16:57 ` [PATCH v3 2/6] powerpc64/bpf: Support tailcalls with subprogs adubey
2026-01-22 16:57 ` [PATCH v3 3/6] powerpc64/bpf: Avoid tailcall restore from trampoline adubey
2026-01-22 17:20   ` bot+bpf-ci
2026-01-22 16:57 ` [PATCH v3 4/6] powerpc64/bpf: Add arch_bpf_stack_walk() for BPF JIT adubey
2026-01-22 16:57 ` [PATCH v3 5/6] powerpc64/bpf: Support exceptions adubey
2026-01-22 16:57 ` [PATCH v3 6/6] powerpc64/bpf: Additional NVR handling for bpf_throw adubey
2026-01-22 17:32   ` bot+bpf-ci

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260122165716.10508-2-adubey@linux.ibm.com \
    --to=adubey@linux.ibm.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=christophe.leroy@csgroup.eu \
    --cc=daniel@iogearbox.net \
    --cc=eddyz87@gmail.com \
    --cc=haoluo@google.com \
    --cc=hbathini@linux.ibm.com \
    --cc=iii@linux.ibm.com \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kpsingh@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=maddy@linux.ibm.com \
    --cc=martin.lau@linux.dev \
    --cc=memxor@gmail.com \
    --cc=mpe@ellerman.id.au \
    --cc=mykolal@fb.com \
    --cc=naveen@kernel.org \
    --cc=npiggin@gmail.com \
    --cc=sachinpb@linux.ibm.com \
    --cc=sdf@fomichev.me \
    --cc=shuah@kernel.org \
    --cc=song@kernel.org \
    --cc=venkat88@linux.ibm.com \
    --cc=yonghong.song@linux.dev \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox