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 v2 2/6] powerpc64/bpf: Support tailcalls with subprogs
Date: Wed, 14 Jan 2026 17:14:46 +0530	[thread overview]
Message-ID: <20260114114450.30405-3-adubey@linux.ibm.com> (raw)
In-Reply-To: <20260114114450.30405-1-adubey@linux.ibm.com>

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

Enabling tailcalls with subprog combinations by referencing
method. The actual tailcall count is always maintained in the
tail_call_info variable present in the frame of main function
(also called entry function). The tail_call_info variables in
the frames of all other subprog contains reference to the
tail_call_info present in frame of main function.

Dynamic resolution interprets the tail_call_info either as
value or reference depending on the context of active frame
while tailcall is invoked.

Signed-off-by: Abhishek Dubey <adubey@linux.ibm.com>
---
 arch/powerpc/net/bpf_jit.h        | 12 +++++-
 arch/powerpc/net/bpf_jit_comp.c   | 10 ++++-
 arch/powerpc/net/bpf_jit_comp64.c | 68 +++++++++++++++++++++++--------
 3 files changed, 70 insertions(+), 20 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 45d419c0ee73..5d735bc5e6bd 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -51,6 +51,12 @@
 		EMIT(PPC_INST_BRANCH_COND | (((cond) & 0x3ff) << 16) | (offset & 0xfffc));					\
 	} while (0)
 
+/* Same as PPC_BCC_SHORT, except valid dest is known prior to call. */
+#define PPC_COND_BRANCH(cond, dest)                                           \
+	do {								      \
+		long offset = (long)(dest) - CTX_NIA(ctx);		      \
+		EMIT(PPC_INST_BRANCH_COND | (((cond) & 0x3ff) << 16) | (offset & 0xfffc));    \
+	} while (0)
 /*
  * Sign-extended 32-bit immediate load
  *
@@ -75,6 +81,8 @@
 
 /* for tailcall counter */
 #define BPF_PPC_TAILCALL        8
+/* for gpr non volatile registers BPG_REG_6 to 10 */
+#define BPF_PPC_STACK_SAVE      (6*8)
 
 /* If dummy pass (!image), account for maximum possible instructions */
 #define PPC_LI64(d, i)		do {					      \
@@ -170,6 +178,7 @@ struct codegen_context {
 	unsigned int alt_exit_addr;
 	u64 arena_vm_start;
 	u64 user_vm_start;
+	bool is_subprog;
 };
 
 #define bpf_to_ppc(r)	(ctx->b2p[r])
@@ -204,11 +213,10 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx);
 void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx);
 void bpf_jit_realloc_regs(struct codegen_context *ctx);
 int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr);
-
 int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass,
 			  struct codegen_context *ctx, int insn_idx,
 			  int jmp_off, int dst_reg, u32 code);
-
+int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx);
 #endif
 
 #endif
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 5e976730b2f5..069a8822c30d 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -206,6 +206,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
 	cgctx.arena_vm_start = bpf_arena_get_kern_vm_start(fp->aux->arena);
 	cgctx.user_vm_start = bpf_arena_get_user_vm_start(fp->aux->arena);
+	cgctx.is_subprog = bpf_is_subprog(fp);
 
 	/* Scouting faux-generate pass 0 */
 	if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false)) {
@@ -435,6 +436,11 @@ void bpf_jit_free(struct bpf_prog *fp)
 	bpf_prog_unlock_free(fp);
 }
 
+bool bpf_jit_supports_subprog_tailcalls(void)
+{
+	return IS_ENABLED(CONFIG_PPC64);
+}
+
 bool bpf_jit_supports_kfunc_call(void)
 {
 	return true;
@@ -604,7 +610,7 @@ 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() */
+		/* See bpf_jit_stack_tailcallinfo_offset() */
 		int tailcallcnt_offset = 7 * 8;
 
 		EMIT(PPC_RAW_LL(_R3, _R1, func_frame_offset - tailcallcnt_offset));
@@ -619,7 +625,7 @@ static void bpf_trampoline_restore_tail_call_cnt(u32 *image, struct codegen_cont
 						 int func_frame_offset, int r4_off)
 {
 	if (IS_ENABLED(CONFIG_PPC64)) {
-		/* See bpf_jit_stack_tailcallcnt() */
+		/* See bpf_jit_stack_tailcallinfo_offset() */
 		int tailcallcnt_offset = 7 * 8;
 
 		EMIT(PPC_RAW_LL(_R3, _R1, -tailcallcnt_offset));
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 39061cd742c1..cebf81fbd59f 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -26,8 +26,12 @@
  * Ensure the top half (upto local_tmp_var) stays consistent
  * with our redzone usage.
  *
+ * tail_call_info - stores tailcall count value in main program's
+ *                  frame, stores reference to tail_call_info of
+ *                  main's frame in sub-prog's frame.
+ *
  *		[	prev sp		] <-------------
- *		[    tail_call_cnt	] 8		|
+ *		[    tail_call_info	] 8		|
  *		[   nv gpr save area	] 6*8		|
  *		[    local_tmp_var	] 24		|
  * fp (r31) -->	[   ebpf stack space	] upto 512	|
@@ -35,8 +39,6 @@
  * sp (r1) --->	[    stack pointer	] --------------
  */
 
-/* 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	24
 /* stack frame excluding BPF stack, ensure this is quadword aligned */
@@ -98,7 +100,7 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
  *		[	prev sp		] <-------------
  *		[	  ...       	] 		|
  * sp (r1) --->	[    stack pointer	] --------------
- *		[    tail_call_cnt	] 8
+ *		[    tail_call_info	] 8
  *		[   nv gpr save area	] 6*8
  *		[    local_tmp_var	] 24
  *		[   unused red zone	] 224
@@ -114,7 +116,7 @@ static int bpf_jit_stack_local(struct codegen_context *ctx)
 	}
 }
 
-static int bpf_jit_stack_tailcallcnt(struct codegen_context *ctx)
+int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx)
 {
 	return bpf_jit_stack_local(ctx) + BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE;
 }
@@ -147,17 +149,32 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 #endif
 
 	/*
-	 * Initialize tail_call_cnt if we do tail calls.
-	 * Otherwise, put in NOPs so that it can be skipped when we are
-	 * invoked through a tail call.
+	 * Tail call count(tcc) is saved & updated only in main
+	 * program's frame and the address of tcc in main program's
+	 * frame (tcc_ptr) is saved in subprogs frame.
+	 *
+	 * Offset of tail_call_info on any frame will be interpreted
+	 * as either tcc_ptr or tcc value depending on whether it is
+	 * greater than MAX_TAIL_CALL_CNT or not.
 	 */
-	if (ctx->seen & SEEN_TAILCALL) {
+	if (!ctx->is_subprog) {
 		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_TAILCALL)));
 	} else {
-		EMIT(PPC_RAW_NOP());
-		EMIT(PPC_RAW_NOP());
+		/*
+		 * if tail_call_info < MAX_TAIL_CALL_CNT
+		 *     main prog calling first subprog -> copy reference
+		 * else
+		 *     subsequent subprog calling another subprog -> directly copy content
+		 */
+		EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), _R1, 0));
+		EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), -(BPF_PPC_TAILCALL)));
+		EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT));
+		PPC_COND_BRANCH(COND_GT, CTX_NIA(ctx) + 8);
+		EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2),
+							-(BPF_PPC_TAILCALL)));
+		EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), _R1, -(BPF_PPC_TAILCALL)));
 	}
 
 	if (bpf_has_stack_frame(ctx)) {
@@ -352,19 +369,38 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	EMIT(PPC_RAW_CMPLW(b2p_index, bpf_to_ppc(TMP_REG_1)));
 	PPC_BCC_SHORT(COND_GE, out);
 
+	EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), _R1, bpf_jit_stack_tailcallinfo_offset(ctx)));
+	EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT));
+	PPC_COND_BRANCH(COND_LE, CTX_NIA(ctx) + 8);
+
+	/* dereference TMP_REG_1 */
+	EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), 0));
+
 	/*
-	 * if (tail_call_cnt >= MAX_TAIL_CALL_CNT)
+	 * if (tail_call_info == MAX_TAIL_CALL_CNT)
 	 *   goto out;
 	 */
-	EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), _R1, bpf_jit_stack_tailcallcnt(ctx)));
 	EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT));
-	PPC_BCC_SHORT(COND_GE, out);
+	PPC_COND_BRANCH(COND_EQ, out);
 
 	/*
-	 * tail_call_cnt++;
+	 * tail_call_info++; <- Actual value of tcc here
 	 */
 	EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), 1));
-	EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), _R1, bpf_jit_stack_tailcallcnt(ctx)));
+
+	/*
+	 * Before writing updated tail_call_info, distinguish if current frame
+	 * is storing a reference to tail_call_info or actual tcc value in
+	 * tail_call_info.
+	 */
+	EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), _R1, bpf_jit_stack_tailcallinfo_offset(ctx)));
+	EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_2), MAX_TAIL_CALL_CNT));
+	PPC_COND_BRANCH(COND_GT, CTX_NIA(ctx) + 8);
+
+	/* First get address of tail_call_info */
+	EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_2), _R1, bpf_jit_stack_tailcallinfo_offset(ctx)));
+	/* Writeback updated value to tail_call_info */
+	EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), 0));
 
 	/* prog = array->ptrs[index]; */
 	EMIT(PPC_RAW_MULI(bpf_to_ppc(TMP_REG_1), b2p_index, 8));
-- 
2.48.1



  parent reply	other threads:[~2026-01-14 11:46 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-14 11:44 [PATCH v2 0/6] powerpc64/bpf: Support tailcalls with subprogs & BPF exceptions adubey
2026-01-14 11:44 ` [PATCH v2 1/6] powerpc64/bpf: Move tail_call_cnt to bottom of stack frame adubey
2026-01-14 12:25   ` bot+bpf-ci
2026-01-15  8:29   ` Christophe Leroy (CS GROUP)
2026-01-17 10:11   ` Hari Bathini
     [not found]     ` <3e1c5930518113f349625cfa80ce82f5@imap.linux.ibm.com>
2026-01-17 10:59       ` Hari Bathini
2026-01-14 11:44 ` adubey [this message]
2026-01-14 12:27   ` [PATCH v2 2/6] powerpc64/bpf: Support tailcalls with subprogs Christophe Leroy (CS GROUP)
     [not found]     ` <2d242f4476b61373da236d24272b0ec3@imap.linux.ibm.com>
2026-01-16  4:50       ` Hari Bathini
2026-01-16  7:49         ` Christophe Leroy (CS GROUP)
2026-01-16 13:59           ` Hari Bathini
2026-01-17 10:23   ` Hari Bathini
2026-01-14 11:44 ` [PATCH v2 3/6] powerpc64/bpf: Tailcall handling with trampolines adubey
2026-01-14 12:25   ` bot+bpf-ci
2026-01-14 19:39   ` kernel test robot
2026-01-17 10:39   ` Hari Bathini
2026-01-17 10:41     ` Hari Bathini
2026-01-14 11:44 ` [PATCH v2 4/6] powerpc64/bpf: Add arch_bpf_stack_walk() for BPF JIT adubey
2026-01-14 12:37   ` Christophe Leroy (CS GROUP)
     [not found]     ` <bec1dfbacced0198fa76bc59e73811c6@imap.linux.ibm.com>
2026-01-16  5:38       ` Hari Bathini
2026-01-14 11:44 ` [PATCH v2 5/6] powerpc64/bpf: Support exceptions adubey
2026-01-16  6:27   ` Hari Bathini
     [not found]     ` <77a6a07add66189fbc9b68a410911e3c@imap.linux.ibm.com>
     [not found]       ` <cf1aea1601d03d42b3afde367c29d26b@imap.linux.ibm.com>
2026-01-16  7:48         ` Hari Bathini
2026-01-14 11:44 ` [PATCH v2 6/6] powerpc64/bpf: Additional NVR handling for bpf_throw adubey
2026-01-14 12:35   ` bot+bpf-ci
2026-01-17 10:51   ` Hari Bathini
2026-01-14 12:28 ` [PATCH v2 0/6] powerpc64/bpf: Support tailcalls with subprogs & BPF exceptions Christophe Leroy (CS GROUP)

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=20260114114450.30405-3-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