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 v5 1/6] powerpc64/bpf: Moving tail_call_cnt to bottom of frame
Date: Sat, 24 Jan 2026 13:22:18 +0530	[thread overview]
Message-ID: <20260124075223.6033-2-adubey@linux.ibm.com> (raw)
In-Reply-To: <20260124075223.6033-1-adubey@linux.ibm.com>

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

To support tailcalls in subprogs, tail_call_cnt needs to be on the BPF
trampoline stack frame. In a regular BPF program or subprog stack
frame, the position of tail_call_cnt is after the NVR save area
(BPF_PPC_STACK_SAVE). To avoid complex logic in deducing offset for
tail_call_cnt, it has to be kept at the same offset on the trampoline
frame as well. But doing that wastes nearly all of BPF_PPC_STACK_SAVE
bytes on the BPF trampoline stack frame as the NVR save area is not
the same for BPF trampoline and regular BPF programs. Address this by
moving tail_call_cnt to the bottom of the frame.

This change avoids the need to account for BPF_PPC_STACK_SAVE bytes
in the BPF trampoline stack frame when support for tailcalls in BPF
subprogs is added later. Also, this change makes offset calculation
of tail_call_cnt field simpler all across.

Signed-off-by: Abhishek Dubey <adubey@linux.ibm.com>
---
 arch/powerpc/net/bpf_jit.h        |  1 +
 arch/powerpc/net/bpf_jit_comp.c   |  6 +++---
 arch/powerpc/net/bpf_jit_comp64.c | 31 ++++++++++++++++++++-----------
 3 files changed, 24 insertions(+), 14 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..de1adc0b1157 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));
@@ -620,7 +620,7 @@ static void bpf_trampoline_restore_tail_call_cnt(u32 *image, struct codegen_cont
 {
 	if (IS_ENABLED(CONFIG_PPC64)) {
 		/* See bpf_jit_stack_tailcallcnt() */
-		int tailcallcnt_offset = 7 * 8;
+		int tailcallcnt_offset = BPF_PPC_TAILCALL;
 
 		EMIT(PPC_RAW_LL(_R3, _R1, -tailcallcnt_offset));
 		EMIT(PPC_RAW_STL(_R3, _R1, func_frame_offset - tailcallcnt_offset));
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:[~2026-01-24  7:54 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-24  7:52 [PATCH v5 0/6] powerpc64/bpf: Support tailcalls with subprogs & BPF exceptions adubey
2026-01-24  7:52 ` adubey [this message]
2026-01-24  7:52 ` [PATCH v5 2/6] powerpc64/bpf: Support tailcalls with subprogs adubey
2026-01-24  7:52 ` [PATCH v5 3/6] powerpc64/bpf: Avoid tailcall restore from trampoline adubey
2026-01-24  7:52 ` [PATCH v5 4/6] powerpc64/bpf: Add arch_bpf_stack_walk() for BPF JIT adubey
2026-01-24  7:52 ` [PATCH v5 5/6] powerpc64/bpf: Support exceptions adubey
2026-01-24  7:52 ` [PATCH v5 6/6] powerpc64/bpf: Additional NVR handling for bpf_throw adubey
2026-01-24  8:23   ` bot+bpf-ci
2026-01-26 18:30     ` Hari Bathini
2026-01-27  2:32       ` Hari Bathini
2026-01-27  6:53     ` Hari Bathini
2026-02-05 14:55 ` [PATCH v5 0/6] powerpc64/bpf: Support tailcalls with subprogs & BPF exceptions Venkat

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=20260124075223.6033-2-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