From a76ab5731e32d50ff5b1ae97e9dc4b23f41c23f5 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Tue, 12 Nov 2024 08:39:07 -0800
Subject: bpf: Find eligible subprogs for private stack support

Private stack will be allocated with percpu allocator in jit time.
To avoid complexity at runtime, only one copy of private stack is
available per cpu per prog. So runtime recursion check is necessary
to avoid stack corruption.

Current private stack only supports kprobe/perf_event/tp/raw_tp
which has recursion check in the kernel, and prog types that use
bpf trampoline recursion check. For trampoline related prog types,
currently only tracing progs have recursion checking.

To avoid complexity, all async_cb subprogs use normal kernel stack
including those subprogs used by both main prog subtree and async_cb
subtree. Any prog having tail call also uses kernel stack.

To avoid jit penalty with private stack support, a subprog stack
size threshold is set such that only if the stack size is no less
than the threshold, private stack is supported. The current threshold
is 64 bytes. This avoids jit penality if the stack usage is small.

A useless 'continue' is also removed from a loop in func
check_max_stack_depth().

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20241112163907.2223839-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h |  7 ++++
 include/linux/filter.h       |  1 +
 kernel/bpf/core.c            |  5 +++
 kernel/bpf/verifier.c        | 96 +++++++++++++++++++++++++++++++++++++++-----
 4 files changed, 99 insertions(+), 10 deletions(-)

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 3a74033d49c4..d62bb2ca1828 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -633,6 +633,12 @@ struct bpf_subprog_arg_info {
 	};
 };
 
+enum priv_stack_mode {
+	PRIV_STACK_UNKNOWN,
+	NO_PRIV_STACK,
+	PRIV_STACK_ADAPTIVE,
+};
+
 struct bpf_subprog_info {
 	/* 'start' has to be the first field otherwise find_subprog() won't work */
 	u32 start; /* insn idx of function entry point */
@@ -653,6 +659,7 @@ struct bpf_subprog_info {
 	/* true if bpf_fastcall stack region is used by functions that can't be inlined */
 	bool keep_fastcall_stack: 1;
 
+	enum priv_stack_mode priv_stack_mode;
 	u8 arg_cnt;
 	struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS];
 };
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 7d7578a8eac1..3a21947f2fd4 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1119,6 +1119,7 @@ bool bpf_jit_supports_exceptions(void);
 bool bpf_jit_supports_ptr_xchg(void);
 bool bpf_jit_supports_arena(void);
 bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena);
+bool bpf_jit_supports_private_stack(void);
 u64 bpf_arch_uaddress_limit(void);
 void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie);
 bool bpf_helper_changes_pkt_data(void *func);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 233ea78f8f1b..14d9288441f2 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -3045,6 +3045,11 @@ bool __weak bpf_jit_supports_exceptions(void)
 	return false;
 }
 
+bool __weak bpf_jit_supports_private_stack(void)
+{
+	return false;
+}
+
 void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie)
 {
 }
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9f5de8d4fbd0..fb23793ac53d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -194,6 +194,8 @@ struct bpf_verifier_stack_elem {
 
 #define BPF_GLOBAL_PERCPU_MA_MAX_SIZE  512
 
+#define BPF_PRIV_STACK_MIN_SIZE		64
+
 static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx);
 static int release_reference(struct bpf_verifier_env *env, int ref_obj_id);
 static void invalidate_non_owning_refs(struct bpf_verifier_env *env);
@@ -6090,6 +6092,34 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
 					   strict);
 }
 
+static enum priv_stack_mode bpf_enable_priv_stack(struct bpf_prog *prog)
+{
+	if (!bpf_jit_supports_private_stack())
+		return NO_PRIV_STACK;
+
+	/* bpf_prog_check_recur() checks all prog types that use bpf trampoline
+	 * while kprobe/tp/perf_event/raw_tp don't use trampoline hence checked
+	 * explicitly.
+	 */
+	switch (prog->type) {
+	case BPF_PROG_TYPE_KPROBE:
+	case BPF_PROG_TYPE_TRACEPOINT:
+	case BPF_PROG_TYPE_PERF_EVENT:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+		return PRIV_STACK_ADAPTIVE;
+	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_LSM:
+	case BPF_PROG_TYPE_STRUCT_OPS:
+		if (bpf_prog_check_recur(prog))
+			return PRIV_STACK_ADAPTIVE;
+		fallthrough;
+	default:
+		break;
+	}
+
+	return NO_PRIV_STACK;
+}
+
 static int round_up_stack_depth(struct bpf_verifier_env *env, int stack_depth)
 {
 	if (env->prog->jit_requested)
@@ -6107,17 +6137,20 @@ static int round_up_stack_depth(struct bpf_verifier_env *env, int stack_depth)
  * Since recursion is prevented by check_cfg() this algorithm
  * only needs a local stack of MAX_CALL_FRAMES to remember callsites
  */
-static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx)
+static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx,
+					 bool priv_stack_supported)
 {
 	struct bpf_subprog_info *subprog = env->subprog_info;
 	struct bpf_insn *insn = env->prog->insnsi;
-	int depth = 0, frame = 0, i, subprog_end;
+	int depth = 0, frame = 0, i, subprog_end, subprog_depth;
 	bool tail_call_reachable = false;
 	int ret_insn[MAX_CALL_FRAMES];
 	int ret_prog[MAX_CALL_FRAMES];
 	int j;
 
 	i = subprog[idx].start;
+	if (!priv_stack_supported)
+		subprog[idx].priv_stack_mode = NO_PRIV_STACK;
 process_func:
 	/* protect against potential stack overflow that might happen when
 	 * bpf2bpf calls get combined with tailcalls. Limit the caller's stack
@@ -6144,11 +6177,31 @@ process_func:
 			depth);
 		return -EACCES;
 	}
-	depth += round_up_stack_depth(env, subprog[idx].stack_depth);
-	if (depth > MAX_BPF_STACK) {
-		verbose(env, "combined stack size of %d calls is %d. Too large\n",
-			frame + 1, depth);
-		return -EACCES;
+
+	subprog_depth = round_up_stack_depth(env, subprog[idx].stack_depth);
+	if (priv_stack_supported) {
+		/* Request private stack support only if the subprog stack
+		 * depth is no less than BPF_PRIV_STACK_MIN_SIZE. This is to
+		 * avoid jit penalty if the stack usage is small.
+		 */
+		if (subprog[idx].priv_stack_mode == PRIV_STACK_UNKNOWN &&
+		    subprog_depth >= BPF_PRIV_STACK_MIN_SIZE)
+			subprog[idx].priv_stack_mode = PRIV_STACK_ADAPTIVE;
+	}
+
+	if (subprog[idx].priv_stack_mode == PRIV_STACK_ADAPTIVE) {
+		if (subprog_depth > MAX_BPF_STACK) {
+			verbose(env, "stack size of subprog %d is %d. Too large\n",
+				idx, subprog_depth);
+			return -EACCES;
+		}
+	} else {
+		depth += subprog_depth;
+		if (depth > MAX_BPF_STACK) {
+			verbose(env, "combined stack size of %d calls is %d. Too large\n",
+				frame + 1, depth);
+			return -EACCES;
+		}
 	}
 continue_func:
 	subprog_end = subprog[idx + 1].start;
@@ -6205,6 +6258,8 @@ continue_func:
 		}
 		i = next_insn;
 		idx = sidx;
+		if (!priv_stack_supported)
+			subprog[idx].priv_stack_mode = NO_PRIV_STACK;
 
 		if (subprog[idx].has_tail_call)
 			tail_call_reachable = true;
@@ -6238,7 +6293,8 @@ continue_func:
 	 */
 	if (frame == 0)
 		return 0;
-	depth -= round_up_stack_depth(env, subprog[idx].stack_depth);
+	if (subprog[idx].priv_stack_mode != PRIV_STACK_ADAPTIVE)
+		depth -= round_up_stack_depth(env, subprog[idx].stack_depth);
 	frame--;
 	i = ret_insn[frame];
 	idx = ret_prog[frame];
@@ -6247,16 +6303,36 @@ continue_func:
 
 static int check_max_stack_depth(struct bpf_verifier_env *env)
 {
+	enum priv_stack_mode priv_stack_mode = PRIV_STACK_UNKNOWN;
 	struct bpf_subprog_info *si = env->subprog_info;
+	bool priv_stack_supported;
 	int ret;
 
 	for (int i = 0; i < env->subprog_cnt; i++) {
+		if (si[i].has_tail_call) {
+			priv_stack_mode = NO_PRIV_STACK;
+			break;
+		}
+	}
+
+	if (priv_stack_mode == PRIV_STACK_UNKNOWN)
+		priv_stack_mode = bpf_enable_priv_stack(env->prog);
+
+	/* All async_cb subprogs use normal kernel stack. If a particular
+	 * subprog appears in both main prog and async_cb subtree, that
+	 * subprog will use normal kernel stack to avoid potential nesting.
+	 * The reverse subprog traversal ensures when main prog subtree is
+	 * checked, the subprogs appearing in async_cb subtrees are already
+	 * marked as using normal kernel stack, so stack size checking can
+	 * be done properly.
+	 */
+	for (int i = env->subprog_cnt - 1; i >= 0; i--) {
 		if (!i || si[i].is_async_cb) {
-			ret = check_max_stack_depth_subprog(env, i);
+			priv_stack_supported = !i && priv_stack_mode == PRIV_STACK_ADAPTIVE;
+			ret = check_max_stack_depth_subprog(env, i, priv_stack_supported);
 			if (ret < 0)
 				return ret;
 		}
-		continue;
 	}
 	return 0;
 }
-- 
cgit 


From e00931c02568dc6ac76f94b1ab471de05e6fdfe8 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Tue, 12 Nov 2024 08:39:12 -0800
Subject: bpf: Enable private stack for eligible subprogs

If private stack is used by any subprog, set that subprog
prog->aux->jits_use_priv_stack to be true so later jit can allocate
private stack for that subprog properly.

Also set env->prog->aux->jits_use_priv_stack to be true if
any subprog uses private stack. This is a use case for a
single main prog (no subprogs) to use private stack, and
also a use case for later struct-ops progs where
env->prog->aux->jits_use_priv_stack will enable recursion
check if any subprog uses private stack.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20241112163912.2224007-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h   |  1 +
 kernel/bpf/verifier.c | 11 +++++++++++
 2 files changed, 12 insertions(+)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7da41ae2eac8..129b29e85cec 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1523,6 +1523,7 @@ struct bpf_prog_aux {
 	bool exception_cb;
 	bool exception_boundary;
 	bool is_extended; /* true if extended by freplace program */
+	bool jits_use_priv_stack;
 	u64 prog_array_member_cnt; /* counts how many times as member of prog_array */
 	struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */
 	struct bpf_arena *arena;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index fb23793ac53d..176d19ad9d07 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6334,6 +6334,14 @@ static int check_max_stack_depth(struct bpf_verifier_env *env)
 				return ret;
 		}
 	}
+
+	for (int i = 0; i < env->subprog_cnt; i++) {
+		if (si[i].priv_stack_mode == PRIV_STACK_ADAPTIVE) {
+			env->prog->aux->jits_use_priv_stack = true;
+			break;
+		}
+	}
+
 	return 0;
 }
 
@@ -20274,6 +20282,9 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 
 		func[i]->aux->name[0] = 'F';
 		func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
+		if (env->subprog_info[i].priv_stack_mode == PRIV_STACK_ADAPTIVE)
+			func[i]->aux->jits_use_priv_stack = true;
+
 		func[i]->jit_requested = 1;
 		func[i]->blinding_requested = prog->blinding_requested;
 		func[i]->aux->kfunc_tab = prog->aux->kfunc_tab;
-- 
cgit 


From f4b21ed0b9d6c9fe155451a1fb3531fb44b0afa8 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Tue, 12 Nov 2024 08:39:17 -0800
Subject: bpf, x86: Avoid repeated usage of bpf_prog->aux->stack_depth

Refactor the code to avoid repeated usage of bpf_prog->aux->stack_depth
in do_jit() func. If the private stack is used, the stack_depth will be
0 for that prog. Refactoring make it easy to adjust stack_depth.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20241112163917.2224189-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 06b080b61aa5..3ff638c37999 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1425,14 +1425,17 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 	int i, excnt = 0;
 	int ilen, proglen = 0;
 	u8 *prog = temp;
+	u32 stack_depth;
 	int err;
 
+	stack_depth = bpf_prog->aux->stack_depth;
+
 	arena_vm_start = bpf_arena_get_kern_vm_start(bpf_prog->aux->arena);
 	user_vm_start = bpf_arena_get_user_vm_start(bpf_prog->aux->arena);
 
 	detect_reg_usage(insn, insn_cnt, callee_regs_used);
 
-	emit_prologue(&prog, bpf_prog->aux->stack_depth,
+	emit_prologue(&prog, stack_depth,
 		      bpf_prog_was_classic(bpf_prog), tail_call_reachable,
 		      bpf_is_subprog(bpf_prog), bpf_prog->aux->exception_cb);
 	/* Exception callback will clobber callee regs for its own use, and
@@ -2128,7 +2131,7 @@ populate_extable:
 
 			func = (u8 *) __bpf_call_base + imm32;
 			if (tail_call_reachable) {
-				LOAD_TAIL_CALL_CNT_PTR(bpf_prog->aux->stack_depth);
+				LOAD_TAIL_CALL_CNT_PTR(stack_depth);
 				ip += 7;
 			}
 			if (!imm32)
@@ -2145,13 +2148,13 @@ populate_extable:
 							  &bpf_prog->aux->poke_tab[imm32 - 1],
 							  &prog, image + addrs[i - 1],
 							  callee_regs_used,
-							  bpf_prog->aux->stack_depth,
+							  stack_depth,
 							  ctx);
 			else
 				emit_bpf_tail_call_indirect(bpf_prog,
 							    &prog,
 							    callee_regs_used,
-							    bpf_prog->aux->stack_depth,
+							    stack_depth,
 							    image + addrs[i - 1],
 							    ctx);
 			break;
-- 
cgit 


From 7d1cd70d4b16ff0216a5f6c2ae7d0fa9fa978c07 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Tue, 12 Nov 2024 08:39:22 -0800
Subject: bpf, x86: Support private stack in jit

Private stack is allocated in function bpf_int_jit_compile() with
alignment 8. Private stack allocation size includes the stack size
determined by verifier and additional space to protect stack overflow
and underflow. See below an illustration:
  ---> memory address increasing
  [8 bytes to protect overflow] [normal stack] [8 bytes to protect underflow]
If overflow/underflow is detected, kernel messages will be
emited in dmesg like
  BPF private stack overflow/underflow detected for prog Fx
  BPF Private stack overflow/underflow detected for prog bpf_prog_a41699c234a1567a_subprog1x
Those messages are generated when I made some changes to jitted code
to intentially cause overflow for some progs.

For the jited prog, The x86 register 9 (X86_REG_R9) is used to replace
bpf frame register (BPF_REG_10). The private stack is used per
subprog per cpu. The X86_REG_R9 is saved and restored around every
func call (not including tailcall) to maintain correctness of
X86_REG_R9.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20241112163922.2224385-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c | 136 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/bpf.h         |   1 +
 2 files changed, 137 insertions(+)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 3ff638c37999..8f896c32172c 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -325,6 +325,22 @@ struct jit_context {
 /* Number of bytes that will be skipped on tailcall */
 #define X86_TAIL_CALL_OFFSET	(12 + ENDBR_INSN_SIZE)
 
+static void push_r9(u8 **pprog)
+{
+	u8 *prog = *pprog;
+
+	EMIT2(0x41, 0x51);   /* push r9 */
+	*pprog = prog;
+}
+
+static void pop_r9(u8 **pprog)
+{
+	u8 *prog = *pprog;
+
+	EMIT2(0x41, 0x59);   /* pop r9 */
+	*pprog = prog;
+}
+
 static void push_r12(u8 **pprog)
 {
 	u8 *prog = *pprog;
@@ -1404,6 +1420,24 @@ static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op)
 	*pprog = prog;
 }
 
+static void emit_priv_frame_ptr(u8 **pprog, void __percpu *priv_frame_ptr)
+{
+	u8 *prog = *pprog;
+
+	/* movabs r9, priv_frame_ptr */
+	emit_mov_imm64(&prog, X86_REG_R9, (__force long) priv_frame_ptr >> 32,
+		       (u32) (__force long) priv_frame_ptr);
+
+#ifdef CONFIG_SMP
+	/* add <r9>, gs:[<off>] */
+	EMIT2(0x65, 0x4c);
+	EMIT3(0x03, 0x0c, 0x25);
+	EMIT((u32)(unsigned long)&this_cpu_off, 4);
+#endif
+
+	*pprog = prog;
+}
+
 #define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp)))
 
 #define __LOAD_TCC_PTR(off)			\
@@ -1412,6 +1446,10 @@ static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op)
 #define LOAD_TAIL_CALL_CNT_PTR(stack)				\
 	__LOAD_TCC_PTR(BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack))
 
+/* Memory size/value to protect private stack overflow/underflow */
+#define PRIV_STACK_GUARD_SZ    8
+#define PRIV_STACK_GUARD_VAL   0xEB9F12345678eb9fULL
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image,
 		  int oldproglen, struct jit_context *ctx, bool jmp_padding)
 {
@@ -1421,7 +1459,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 	int insn_cnt = bpf_prog->len;
 	bool seen_exit = false;
 	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
+	void __percpu *priv_frame_ptr = NULL;
 	u64 arena_vm_start, user_vm_start;
+	void __percpu *priv_stack_ptr;
 	int i, excnt = 0;
 	int ilen, proglen = 0;
 	u8 *prog = temp;
@@ -1429,6 +1469,11 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 	int err;
 
 	stack_depth = bpf_prog->aux->stack_depth;
+	priv_stack_ptr = bpf_prog->aux->priv_stack_ptr;
+	if (priv_stack_ptr) {
+		priv_frame_ptr = priv_stack_ptr + PRIV_STACK_GUARD_SZ + round_up(stack_depth, 8);
+		stack_depth = 0;
+	}
 
 	arena_vm_start = bpf_arena_get_kern_vm_start(bpf_prog->aux->arena);
 	user_vm_start = bpf_arena_get_user_vm_start(bpf_prog->aux->arena);
@@ -1457,6 +1502,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 		emit_mov_imm64(&prog, X86_REG_R12,
 			       arena_vm_start >> 32, (u32) arena_vm_start);
 
+	if (priv_frame_ptr)
+		emit_priv_frame_ptr(&prog, priv_frame_ptr);
+
 	ilen = prog - temp;
 	if (rw_image)
 		memcpy(rw_image + proglen, temp, ilen);
@@ -1476,6 +1524,14 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 		u8 *func;
 		int nops;
 
+		if (priv_frame_ptr) {
+			if (src_reg == BPF_REG_FP)
+				src_reg = X86_REG_R9;
+
+			if (dst_reg == BPF_REG_FP)
+				dst_reg = X86_REG_R9;
+		}
+
 		switch (insn->code) {
 			/* ALU */
 		case BPF_ALU | BPF_ADD | BPF_X:
@@ -2136,9 +2192,15 @@ populate_extable:
 			}
 			if (!imm32)
 				return -EINVAL;
+			if (priv_frame_ptr) {
+				push_r9(&prog);
+				ip += 2;
+			}
 			ip += x86_call_depth_emit_accounting(&prog, func, ip);
 			if (emit_call(&prog, func, ip))
 				return -EINVAL;
+			if (priv_frame_ptr)
+				pop_r9(&prog);
 			break;
 		}
 
@@ -3306,6 +3368,42 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
 	return emit_bpf_dispatcher(&prog, 0, num_funcs - 1, funcs, image, buf);
 }
 
+static const char *bpf_get_prog_name(struct bpf_prog *prog)
+{
+	if (prog->aux->ksym.prog)
+		return prog->aux->ksym.name;
+	return prog->aux->name;
+}
+
+static void priv_stack_init_guard(void __percpu *priv_stack_ptr, int alloc_size)
+{
+	int cpu, underflow_idx = (alloc_size - PRIV_STACK_GUARD_SZ) >> 3;
+	u64 *stack_ptr;
+
+	for_each_possible_cpu(cpu) {
+		stack_ptr = per_cpu_ptr(priv_stack_ptr, cpu);
+		stack_ptr[0] = PRIV_STACK_GUARD_VAL;
+		stack_ptr[underflow_idx] = PRIV_STACK_GUARD_VAL;
+	}
+}
+
+static void priv_stack_check_guard(void __percpu *priv_stack_ptr, int alloc_size,
+				   struct bpf_prog *prog)
+{
+	int cpu, underflow_idx = (alloc_size - PRIV_STACK_GUARD_SZ) >> 3;
+	u64 *stack_ptr;
+
+	for_each_possible_cpu(cpu) {
+		stack_ptr = per_cpu_ptr(priv_stack_ptr, cpu);
+		if (stack_ptr[0] != PRIV_STACK_GUARD_VAL ||
+		    stack_ptr[underflow_idx] != PRIV_STACK_GUARD_VAL) {
+			pr_err("BPF private stack overflow/underflow detected for prog %sx\n",
+			       bpf_get_prog_name(prog));
+			break;
+		}
+	}
+}
+
 struct x64_jit_data {
 	struct bpf_binary_header *rw_header;
 	struct bpf_binary_header *header;
@@ -3323,7 +3421,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	struct bpf_binary_header *rw_header = NULL;
 	struct bpf_binary_header *header = NULL;
 	struct bpf_prog *tmp, *orig_prog = prog;
+	void __percpu *priv_stack_ptr = NULL;
 	struct x64_jit_data *jit_data;
+	int priv_stack_alloc_sz;
 	int proglen, oldproglen = 0;
 	struct jit_context ctx = {};
 	bool tmp_blinded = false;
@@ -3359,6 +3459,23 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		}
 		prog->aux->jit_data = jit_data;
 	}
+	priv_stack_ptr = prog->aux->priv_stack_ptr;
+	if (!priv_stack_ptr && prog->aux->jits_use_priv_stack) {
+		/* Allocate actual private stack size with verifier-calculated
+		 * stack size plus two memory guards to protect overflow and
+		 * underflow.
+		 */
+		priv_stack_alloc_sz = round_up(prog->aux->stack_depth, 8) +
+				      2 * PRIV_STACK_GUARD_SZ;
+		priv_stack_ptr = __alloc_percpu_gfp(priv_stack_alloc_sz, 8, GFP_KERNEL);
+		if (!priv_stack_ptr) {
+			prog = orig_prog;
+			goto out_priv_stack;
+		}
+
+		priv_stack_init_guard(priv_stack_ptr, priv_stack_alloc_sz);
+		prog->aux->priv_stack_ptr = priv_stack_ptr;
+	}
 	addrs = jit_data->addrs;
 	if (addrs) {
 		ctx = jit_data->ctx;
@@ -3494,6 +3611,11 @@ out_image:
 			bpf_prog_fill_jited_linfo(prog, addrs + 1);
 out_addrs:
 		kvfree(addrs);
+		if (!image && priv_stack_ptr) {
+			free_percpu(priv_stack_ptr);
+			prog->aux->priv_stack_ptr = NULL;
+		}
+out_priv_stack:
 		kfree(jit_data);
 		prog->aux->jit_data = NULL;
 	}
@@ -3532,6 +3654,8 @@ void bpf_jit_free(struct bpf_prog *prog)
 	if (prog->jited) {
 		struct x64_jit_data *jit_data = prog->aux->jit_data;
 		struct bpf_binary_header *hdr;
+		void __percpu *priv_stack_ptr;
+		int priv_stack_alloc_sz;
 
 		/*
 		 * If we fail the final pass of JIT (from jit_subprogs),
@@ -3547,6 +3671,13 @@ void bpf_jit_free(struct bpf_prog *prog)
 		prog->bpf_func = (void *)prog->bpf_func - cfi_get_offset();
 		hdr = bpf_jit_binary_pack_hdr(prog);
 		bpf_jit_binary_pack_free(hdr, NULL);
+		priv_stack_ptr = prog->aux->priv_stack_ptr;
+		if (priv_stack_ptr) {
+			priv_stack_alloc_sz = round_up(prog->aux->stack_depth, 8) +
+					      2 * PRIV_STACK_GUARD_SZ;
+			priv_stack_check_guard(priv_stack_ptr, priv_stack_alloc_sz, prog);
+			free_percpu(prog->aux->priv_stack_ptr);
+		}
 		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog));
 	}
 
@@ -3562,6 +3693,11 @@ bool bpf_jit_supports_exceptions(void)
 	return IS_ENABLED(CONFIG_UNWINDER_ORC);
 }
 
+bool bpf_jit_supports_private_stack(void)
+{
+	return true;
+}
+
 void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie)
 {
 #if defined(CONFIG_UNWINDER_ORC)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 129b29e85cec..d32cc373dfd1 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1507,6 +1507,7 @@ struct bpf_prog_aux {
 	u32 max_rdwr_access;
 	struct btf *attach_btf;
 	const struct bpf_ctx_arg_aux *ctx_arg_info;
+	void __percpu *priv_stack_ptr;
 	struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */
 	struct bpf_prog *dst_prog;
 	struct bpf_trampoline *dst_trampoline;
-- 
cgit 


From f4b295ab65980435d7dc8b12d110387d1d1c653c Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Tue, 12 Nov 2024 08:39:27 -0800
Subject: selftests/bpf: Add tracing prog private stack tests

Some private stack tests are added including:
  - main prog only with stack size greater than BPF_PSTACK_MIN_SIZE.
  - main prog only with stack size smaller than BPF_PSTACK_MIN_SIZE.
  - prog with one subprog having MAX_BPF_STACK stack size and another
    subprog having non-zero small stack size.
  - prog with callback function.
  - prog with exception in main prog or subprog.
  - prog with async callback without nesting
  - prog with async callback with possible nesting

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20241112163927.2224750-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/verifier.c  |   2 +
 .../selftests/bpf/progs/verifier_private_stack.c   | 272 +++++++++++++++++++++
 2 files changed, 274 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/verifier_private_stack.c

diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index 75f7a2ce334b..d9f65adb456b 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -61,6 +61,7 @@
 #include "verifier_or_jmp32_k.skel.h"
 #include "verifier_precision.skel.h"
 #include "verifier_prevent_map_lookup.skel.h"
+#include "verifier_private_stack.skel.h"
 #include "verifier_raw_stack.skel.h"
 #include "verifier_raw_tp_writable.skel.h"
 #include "verifier_reg_equal.skel.h"
@@ -188,6 +189,7 @@ void test_verifier_bpf_fastcall(void)         { RUN(verifier_bpf_fastcall); }
 void test_verifier_or_jmp32_k(void)           { RUN(verifier_or_jmp32_k); }
 void test_verifier_precision(void)            { RUN(verifier_precision); }
 void test_verifier_prevent_map_lookup(void)   { RUN(verifier_prevent_map_lookup); }
+void test_verifier_private_stack(void)        { RUN(verifier_private_stack); }
 void test_verifier_raw_stack(void)            { RUN(verifier_raw_stack); }
 void test_verifier_raw_tp_writable(void)      { RUN(verifier_raw_tp_writable); }
 void test_verifier_reg_equal(void)            { RUN(verifier_reg_equal); }
diff --git a/tools/testing/selftests/bpf/progs/verifier_private_stack.c b/tools/testing/selftests/bpf/progs/verifier_private_stack.c
new file mode 100644
index 000000000000..b1fbdf119553
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_private_stack.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+/* From include/linux/filter.h */
+#define MAX_BPF_STACK    512
+
+#if defined(__TARGET_ARCH_x86)
+
+struct elem {
+	struct bpf_timer t;
+	char pad[256];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} array SEC(".maps");
+
+SEC("kprobe")
+__description("Private stack, single prog")
+__success
+__arch_x86_64
+__jited("	movabsq	$0x{{.*}}, %r9")
+__jited("	addq	%gs:0x{{.*}}, %r9")
+__jited("	movl	$0x2a, %edi")
+__jited("	movq	%rdi, -0x100(%r9)")
+__naked void private_stack_single_prog(void)
+{
+	asm volatile ("			\
+	r1 = 42;			\
+	*(u64 *)(r10 - 256) = r1;	\
+	r0 = 0;				\
+	exit;				\
+"	::: __clobber_all);
+}
+
+SEC("raw_tp")
+__description("No private stack")
+__success
+__arch_x86_64
+__jited("	subq	$0x8, %rsp")
+__naked void no_private_stack_nested(void)
+{
+	asm volatile ("			\
+	r1 = 42;			\
+	*(u64 *)(r10 - 8) = r1;		\
+	r0 = 0;				\
+	exit;				\
+"	::: __clobber_all);
+}
+
+__used
+__naked static void cumulative_stack_depth_subprog(void)
+{
+	asm volatile ("				\
+	r1 = 41;				\
+	*(u64 *)(r10 - 32) = r1;		\
+	call %[bpf_get_smp_processor_id];	\
+	exit;					\
+"	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("kprobe")
+__description("Private stack, subtree > MAX_BPF_STACK")
+__success
+__arch_x86_64
+/* private stack fp for the main prog */
+__jited("	movabsq	$0x{{.*}}, %r9")
+__jited("	addq	%gs:0x{{.*}}, %r9")
+__jited("	movl	$0x2a, %edi")
+__jited("	movq	%rdi, -0x200(%r9)")
+__jited("	pushq	%r9")
+__jited("	callq	0x{{.*}}")
+__jited("	popq	%r9")
+__jited("	xorl	%eax, %eax")
+__naked void private_stack_nested_1(void)
+{
+	asm volatile ("				\
+	r1 = 42;				\
+	*(u64 *)(r10 - %[max_bpf_stack]) = r1;	\
+	call cumulative_stack_depth_subprog;	\
+	r0 = 0;					\
+	exit;					\
+"	:
+	: __imm_const(max_bpf_stack, MAX_BPF_STACK)
+	: __clobber_all);
+}
+
+__naked __noinline __used
+static unsigned long loop_callback(void)
+{
+	asm volatile ("				\
+	call %[bpf_get_prandom_u32];		\
+	r1 = 42;				\
+	*(u64 *)(r10 - 512) = r1;		\
+	call cumulative_stack_depth_subprog;	\
+	r0 = 0;					\
+	exit;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_common);
+}
+
+SEC("raw_tp")
+__description("Private stack, callback")
+__success
+__arch_x86_64
+/* for func loop_callback */
+__jited("func #1")
+__jited("	endbr64")
+__jited("	nopl	(%rax,%rax)")
+__jited("	nopl	(%rax)")
+__jited("	pushq	%rbp")
+__jited("	movq	%rsp, %rbp")
+__jited("	endbr64")
+__jited("	movabsq	$0x{{.*}}, %r9")
+__jited("	addq	%gs:0x{{.*}}, %r9")
+__jited("	pushq	%r9")
+__jited("	callq")
+__jited("	popq	%r9")
+__jited("	movl	$0x2a, %edi")
+__jited("	movq	%rdi, -0x200(%r9)")
+__jited("	pushq	%r9")
+__jited("	callq")
+__jited("	popq	%r9")
+__naked void private_stack_callback(void)
+{
+	asm volatile ("			\
+	r1 = 1;				\
+	r2 = %[loop_callback];		\
+	r3 = 0;				\
+	r4 = 0;				\
+	call %[bpf_loop];		\
+	r0 = 0;				\
+	exit;				\
+"	:
+	: __imm_ptr(loop_callback),
+	  __imm(bpf_loop)
+	: __clobber_common);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("Private stack, exception in main prog")
+__success __retval(0)
+__arch_x86_64
+__jited("	pushq	%r9")
+__jited("	callq")
+__jited("	popq	%r9")
+int private_stack_exception_main_prog(void)
+{
+	asm volatile ("			\
+	r1 = 42;			\
+	*(u64 *)(r10 - 512) = r1;	\
+"	::: __clobber_common);
+
+	bpf_throw(0);
+	return 0;
+}
+
+__used static int subprog_exception(void)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("Private stack, exception in subprog")
+__success __retval(0)
+__arch_x86_64
+__jited("	movq	%rdi, -0x200(%r9)")
+__jited("	pushq	%r9")
+__jited("	callq")
+__jited("	popq	%r9")
+int private_stack_exception_sub_prog(void)
+{
+	asm volatile ("			\
+	r1 = 42;			\
+	*(u64 *)(r10 - 512) = r1;	\
+	call subprog_exception;		\
+"	::: __clobber_common);
+
+	return 0;
+}
+
+int glob;
+__noinline static void subprog2(int *val)
+{
+	glob += val[0] * 2;
+}
+
+__noinline static void subprog1(int *val)
+{
+	int tmp[64] = {};
+
+	tmp[0] = *val;
+	subprog2(tmp);
+}
+
+__noinline static int timer_cb1(void *map, int *key, struct bpf_timer *timer)
+{
+	subprog1(key);
+	return 0;
+}
+
+__noinline static int timer_cb2(void *map, int *key, struct bpf_timer *timer)
+{
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("Private stack, async callback, not nested")
+__success __retval(0)
+__arch_x86_64
+__jited("	movabsq	$0x{{.*}}, %r9")
+int private_stack_async_callback_1(void)
+{
+	struct bpf_timer *arr_timer;
+	int array_key = 0;
+
+	arr_timer = bpf_map_lookup_elem(&array, &array_key);
+	if (!arr_timer)
+		return 0;
+
+	bpf_timer_init(arr_timer, &array, 1);
+	bpf_timer_set_callback(arr_timer, timer_cb2);
+	bpf_timer_start(arr_timer, 0, 0);
+	subprog1(&array_key);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("Private stack, async callback, potential nesting")
+__success __retval(0)
+__arch_x86_64
+__jited("	subq	$0x100, %rsp")
+int private_stack_async_callback_2(void)
+{
+	struct bpf_timer *arr_timer;
+	int array_key = 0;
+
+	arr_timer = bpf_map_lookup_elem(&array, &array_key);
+	if (!arr_timer)
+		return 0;
+
+	bpf_timer_init(arr_timer, &array, 1);
+	bpf_timer_set_callback(arr_timer, timer_cb1);
+	bpf_timer_start(arr_timer, 0, 0);
+	subprog1(&array_key);
+	return 0;
+}
+
+#else
+
+SEC("kprobe")
+__description("private stack is not supported, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
-- 
cgit 


From 5bd36da1e37e7a78e8b38efd287de6e1394b7d6e Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Tue, 12 Nov 2024 08:39:33 -0800
Subject: bpf: Support private stack for struct_ops progs

For struct_ops progs, whether a particular prog uses private stack
depends on prog->aux->priv_stack_requested setting before actual
insn-level verification for that prog. One particular implementation
is to piggyback on struct_ops->check_member(). The next patch has
an example for this. The struct_ops->check_member() sets
prog->aux->priv_stack_requested to be true which enables private stack
usage.

The struct_ops prog follows the same rule as kprobe/tracing progs after
function bpf_enable_priv_stack(). For example, even a struct_ops prog
requests private stack, it could still use normal kernel stack if
the stack size is small (< 64 bytes).

Similar to tracing progs, nested same cpu same prog run will be skipped.
A field (recursion_detected()) is added to bpf_prog_aux structure.
If bpf_prog->aux->recursion_detected is implemented by the struct_ops
subsystem and nested same cpu/prog happens, the function will be
triggered to report an error, collect related info, etc.

Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20241112163933.2224962-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h          | 2 ++
 include/linux/bpf_verifier.h | 1 +
 kernel/bpf/trampoline.c      | 4 ++++
 kernel/bpf/verifier.c        | 7 ++++++-
 4 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d32cc373dfd1..10945c8858ce 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1525,9 +1525,11 @@ struct bpf_prog_aux {
 	bool exception_boundary;
 	bool is_extended; /* true if extended by freplace program */
 	bool jits_use_priv_stack;
+	bool priv_stack_requested;
 	u64 prog_array_member_cnt; /* counts how many times as member of prog_array */
 	struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */
 	struct bpf_arena *arena;
+	void (*recursion_detected)(struct bpf_prog *prog); /* callback if recursion is detected */
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
 	/* function name for valid attach_btf_id */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index d62bb2ca1828..6b7c91629176 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -879,6 +879,7 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog)
 	case BPF_PROG_TYPE_TRACING:
 		return prog->expected_attach_type != BPF_TRACE_ITER;
 	case BPF_PROG_TYPE_STRUCT_OPS:
+		return prog->aux->jits_use_priv_stack;
 	case BPF_PROG_TYPE_LSM:
 		return false;
 	default:
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 9f36c049f4c2..a8d188b31da5 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -899,6 +899,8 @@ static u64 notrace __bpf_prog_enter_recur(struct bpf_prog *prog, struct bpf_tram
 
 	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
 		bpf_prog_inc_misses_counter(prog);
+		if (prog->aux->recursion_detected)
+			prog->aux->recursion_detected(prog);
 		return 0;
 	}
 	return bpf_prog_start_time();
@@ -975,6 +977,8 @@ u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
 
 	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
 		bpf_prog_inc_misses_counter(prog);
+		if (prog->aux->recursion_detected)
+			prog->aux->recursion_detected(prog);
 		return 0;
 	}
 	return bpf_prog_start_time();
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 176d19ad9d07..f4c39bb50511 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6110,7 +6110,7 @@ static enum priv_stack_mode bpf_enable_priv_stack(struct bpf_prog *prog)
 	case BPF_PROG_TYPE_TRACING:
 	case BPF_PROG_TYPE_LSM:
 	case BPF_PROG_TYPE_STRUCT_OPS:
-		if (bpf_prog_check_recur(prog))
+		if (prog->aux->priv_stack_requested || bpf_prog_check_recur(prog))
 			return PRIV_STACK_ADAPTIVE;
 		fallthrough;
 	default:
@@ -22053,6 +22053,11 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 		}
 	}
 
+	if (prog->aux->priv_stack_requested && !bpf_jit_supports_private_stack()) {
+		verbose(env, "Private stack not supported by jit\n");
+		return -EACCES;
+	}
+
 	/* btf_ctx_access() used this to provide argument type info */
 	prog->aux->ctx_arg_info =
 		st_ops_desc->arg_info[member_idx].info;
-- 
cgit 


From becfe32b57c7d323fbd94c1a2c6d7eba918ddde8 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Tue, 12 Nov 2024 08:39:38 -0800
Subject: selftests/bpf: Add struct_ops prog private stack tests

Add three tests for struct_ops using private stack.
  ./test_progs -t struct_ops_private_stack
  #336/1   struct_ops_private_stack/private_stack:OK
  #336/2   struct_ops_private_stack/private_stack_fail:OK
  #336/3   struct_ops_private_stack/private_stack_recur:OK
  #336     struct_ops_private_stack:OK

The following is a snippet of a struct_ops check_member() implementation:

	u32 moff = __btf_member_bit_offset(t, member) / 8;
	switch (moff) {
	case offsetof(struct bpf_testmod_ops3, test_1):
        	prog->aux->priv_stack_requested = true;
                prog->aux->recursion_detected = test_1_recursion_detected;
        	fallthrough;
	default:
        	break;
	}
	return 0;

The first test is with nested two different callback functions where the
first prog has more than 512 byte stack size (including subprogs) with
private stack enabled.

The second test is a negative test where the second prog has more than 512
byte stack size without private stack enabled.

The third test is the same callback function recursing itself. At run time,
the jit trampoline recursion check kicks in to prevent the recursion. The
recursion_detected() callback function is implemented by the bpf_testmod,
the following message in dmesg
  bpf_testmod: oh no, recursing into test_1, recursion_misses 1
demonstrates the callback function is indeed triggered when recursion miss
happens.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20241112163938.2225528-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/bpf_testmod/bpf_testmod.c        | 104 ++++++++++++++++++++
 .../selftests/bpf/bpf_testmod/bpf_testmod.h        |   5 +
 .../bpf/prog_tests/struct_ops_private_stack.c      | 106 +++++++++++++++++++++
 .../selftests/bpf/progs/struct_ops_private_stack.c |  62 ++++++++++++
 .../bpf/progs/struct_ops_private_stack_fail.c      |  62 ++++++++++++
 .../bpf/progs/struct_ops_private_stack_recur.c     |  50 ++++++++++
 6 files changed, 389 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c
 create mode 100644 tools/testing/selftests/bpf/progs/struct_ops_private_stack.c
 create mode 100644 tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c
 create mode 100644 tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c

diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 987d41af71d2..cc9dde507aba 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -245,6 +245,39 @@ __bpf_kfunc void bpf_testmod_ctx_release(struct bpf_testmod_ctx *ctx)
 		call_rcu(&ctx->rcu, testmod_free_cb);
 }
 
+static struct bpf_testmod_ops3 *st_ops3;
+
+static int bpf_testmod_test_3(void)
+{
+	return 0;
+}
+
+static int bpf_testmod_test_4(void)
+{
+	return 0;
+}
+
+static struct bpf_testmod_ops3 __bpf_testmod_ops3 = {
+	.test_1 = bpf_testmod_test_3,
+	.test_2 = bpf_testmod_test_4,
+};
+
+static void bpf_testmod_test_struct_ops3(void)
+{
+	if (st_ops3)
+		st_ops3->test_1();
+}
+
+__bpf_kfunc void bpf_testmod_ops3_call_test_1(void)
+{
+	st_ops3->test_1();
+}
+
+__bpf_kfunc void bpf_testmod_ops3_call_test_2(void)
+{
+	st_ops3->test_2();
+}
+
 struct bpf_testmod_btf_type_tag_1 {
 	int a;
 };
@@ -382,6 +415,8 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 
 	(void)trace_bpf_testmod_test_raw_tp_null(NULL);
 
+	bpf_testmod_test_struct_ops3();
+
 	struct_arg3 = kmalloc((sizeof(struct bpf_testmod_struct_arg_3) +
 				sizeof(int)), GFP_KERNEL);
 	if (struct_arg3 != NULL) {
@@ -586,6 +621,8 @@ BTF_ID_FLAGS(func, bpf_kfunc_trusted_num_test, KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, bpf_kfunc_rcu_task_test, KF_RCU)
 BTF_ID_FLAGS(func, bpf_testmod_ctx_create, KF_ACQUIRE | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_testmod_ctx_release, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_testmod_ops3_call_test_1)
+BTF_ID_FLAGS(func, bpf_testmod_ops3_call_test_2)
 BTF_KFUNCS_END(bpf_testmod_common_kfunc_ids)
 
 BTF_ID_LIST(bpf_testmod_dtor_ids)
@@ -1096,6 +1133,10 @@ static const struct bpf_verifier_ops bpf_testmod_verifier_ops = {
 	.is_valid_access = bpf_testmod_ops_is_valid_access,
 };
 
+static const struct bpf_verifier_ops bpf_testmod_verifier_ops3 = {
+	.is_valid_access = bpf_testmod_ops_is_valid_access,
+};
+
 static int bpf_dummy_reg(void *kdata, struct bpf_link *link)
 {
 	struct bpf_testmod_ops *ops = kdata;
@@ -1175,6 +1216,68 @@ struct bpf_struct_ops bpf_testmod_ops2 = {
 	.owner = THIS_MODULE,
 };
 
+static int st_ops3_reg(void *kdata, struct bpf_link *link)
+{
+	int err = 0;
+
+	mutex_lock(&st_ops_mutex);
+	if (st_ops3) {
+		pr_err("st_ops has already been registered\n");
+		err = -EEXIST;
+		goto unlock;
+	}
+	st_ops3 = kdata;
+
+unlock:
+	mutex_unlock(&st_ops_mutex);
+	return err;
+}
+
+static void st_ops3_unreg(void *kdata, struct bpf_link *link)
+{
+	mutex_lock(&st_ops_mutex);
+	st_ops3 = NULL;
+	mutex_unlock(&st_ops_mutex);
+}
+
+static void test_1_recursion_detected(struct bpf_prog *prog)
+{
+	struct bpf_prog_stats *stats;
+
+	stats = this_cpu_ptr(prog->stats);
+	printk("bpf_testmod: oh no, recursing into test_1, recursion_misses %llu",
+	       u64_stats_read(&stats->misses));
+}
+
+static int st_ops3_check_member(const struct btf_type *t,
+				const struct btf_member *member,
+				const struct bpf_prog *prog)
+{
+	u32 moff = __btf_member_bit_offset(t, member) / 8;
+
+	switch (moff) {
+	case offsetof(struct bpf_testmod_ops3, test_1):
+		prog->aux->priv_stack_requested = true;
+		prog->aux->recursion_detected = test_1_recursion_detected;
+		fallthrough;
+	default:
+		break;
+	}
+	return 0;
+}
+
+struct bpf_struct_ops bpf_testmod_ops3 = {
+	.verifier_ops = &bpf_testmod_verifier_ops3,
+	.init = bpf_testmod_ops_init,
+	.init_member = bpf_testmod_ops_init_member,
+	.reg = st_ops3_reg,
+	.unreg = st_ops3_unreg,
+	.check_member = st_ops3_check_member,
+	.cfi_stubs = &__bpf_testmod_ops3,
+	.name = "bpf_testmod_ops3",
+	.owner = THIS_MODULE,
+};
+
 static int bpf_test_mod_st_ops__test_prologue(struct st_ops_args *args)
 {
 	return 0;
@@ -1333,6 +1436,7 @@ static int bpf_testmod_init(void)
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_testmod_kfunc_set);
 	ret = ret ?: register_bpf_struct_ops(&bpf_bpf_testmod_ops, bpf_testmod_ops);
 	ret = ret ?: register_bpf_struct_ops(&bpf_testmod_ops2, bpf_testmod_ops2);
+	ret = ret ?: register_bpf_struct_ops(&bpf_testmod_ops3, bpf_testmod_ops3);
 	ret = ret ?: register_bpf_struct_ops(&testmod_st_ops, bpf_testmod_st_ops);
 	ret = ret ?: register_btf_id_dtor_kfuncs(bpf_testmod_dtors,
 						 ARRAY_SIZE(bpf_testmod_dtors),
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
index fb7dff47597a..356803d1c10e 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
@@ -94,6 +94,11 @@ struct bpf_testmod_ops2 {
 	int (*test_1)(void);
 };
 
+struct bpf_testmod_ops3 {
+	int (*test_1)(void);
+	int (*test_2)(void);
+};
+
 struct st_ops_args {
 	u64 a;
 };
diff --git a/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c b/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c
new file mode 100644
index 000000000000..4006879ca3fe
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c
@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "struct_ops_private_stack.skel.h"
+#include "struct_ops_private_stack_fail.skel.h"
+#include "struct_ops_private_stack_recur.skel.h"
+
+static void test_private_stack(void)
+{
+	struct struct_ops_private_stack *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = struct_ops_private_stack__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_private_stack__open"))
+		return;
+
+	if (skel->data->skip) {
+		test__skip();
+		goto cleanup;
+	}
+
+	err = struct_ops_private_stack__load(skel);
+	if (!ASSERT_OK(err, "struct_ops_private_stack__load"))
+		goto cleanup;
+
+	link = bpf_map__attach_struct_ops(skel->maps.testmod_1);
+	if (!ASSERT_OK_PTR(link, "attach_struct_ops"))
+		goto cleanup;
+
+	ASSERT_OK(trigger_module_test_read(256), "trigger_read");
+
+	ASSERT_EQ(skel->bss->val_i, 3, "val_i");
+	ASSERT_EQ(skel->bss->val_j, 8, "val_j");
+
+	bpf_link__destroy(link);
+
+cleanup:
+	struct_ops_private_stack__destroy(skel);
+}
+
+static void test_private_stack_fail(void)
+{
+	struct struct_ops_private_stack_fail *skel;
+	int err;
+
+	skel = struct_ops_private_stack_fail__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_private_stack_fail__open"))
+		return;
+
+	if (skel->data->skip) {
+		test__skip();
+		goto cleanup;
+	}
+
+	err = struct_ops_private_stack_fail__load(skel);
+	if (!ASSERT_ERR(err, "struct_ops_private_stack_fail__load"))
+		goto cleanup;
+	return;
+
+cleanup:
+	struct_ops_private_stack_fail__destroy(skel);
+}
+
+static void test_private_stack_recur(void)
+{
+	struct struct_ops_private_stack_recur *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = struct_ops_private_stack_recur__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_private_stack_recur__open"))
+		return;
+
+	if (skel->data->skip) {
+		test__skip();
+		goto cleanup;
+	}
+
+	err = struct_ops_private_stack_recur__load(skel);
+	if (!ASSERT_OK(err, "struct_ops_private_stack_recur__load"))
+		goto cleanup;
+
+	link = bpf_map__attach_struct_ops(skel->maps.testmod_1);
+	if (!ASSERT_OK_PTR(link, "attach_struct_ops"))
+		goto cleanup;
+
+	ASSERT_OK(trigger_module_test_read(256), "trigger_read");
+
+	ASSERT_EQ(skel->bss->val_j, 3, "val_j");
+
+	bpf_link__destroy(link);
+
+cleanup:
+	struct_ops_private_stack_recur__destroy(skel);
+}
+
+void test_struct_ops_private_stack(void)
+{
+	if (test__start_subtest("private_stack"))
+		test_private_stack();
+	if (test__start_subtest("private_stack_fail"))
+		test_private_stack_fail();
+	if (test__start_subtest("private_stack_recur"))
+		test_private_stack_recur();
+}
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c
new file mode 100644
index 000000000000..8ea57e5348ab
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../bpf_testmod/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+#if defined(__TARGET_ARCH_x86)
+bool skip __attribute((__section__(".data"))) = false;
+#else
+bool skip = true;
+#endif
+
+void bpf_testmod_ops3_call_test_2(void) __ksym;
+
+int val_i, val_j;
+
+__noinline static int subprog2(int *a, int *b)
+{
+	return val_i + a[10] + b[20];
+}
+
+__noinline static int subprog1(int *a)
+{
+	/* stack size 200 bytes */
+	int b[50] = {};
+
+	b[20] = 2;
+	return subprog2(a, b);
+}
+
+
+SEC("struct_ops")
+int BPF_PROG(test_1)
+{
+	/* stack size 400 bytes */
+	int a[100] = {};
+
+	a[10] = 1;
+	val_i = subprog1(a);
+	bpf_testmod_ops3_call_test_2();
+	return 0;
+}
+
+SEC("struct_ops")
+int BPF_PROG(test_2)
+{
+	/* stack size 200 bytes */
+	int a[50] = {};
+
+	a[10] = 3;
+	val_j = subprog1(a);
+	return 0;
+}
+
+SEC(".struct_ops")
+struct bpf_testmod_ops3 testmod_1 = {
+	.test_1 = (void *)test_1,
+	.test_2 = (void *)test_2,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c
new file mode 100644
index 000000000000..1f55ec4cee37
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../bpf_testmod/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+#if defined(__TARGET_ARCH_x86)
+bool skip __attribute((__section__(".data"))) = false;
+#else
+bool skip = true;
+#endif
+
+void bpf_testmod_ops3_call_test_2(void) __ksym;
+
+int val_i, val_j;
+
+__noinline static int subprog2(int *a, int *b)
+{
+	return val_i + a[10] + b[20];
+}
+
+__noinline static int subprog1(int *a)
+{
+	/* stack size 200 bytes */
+	int b[50] = {};
+
+	b[20] = 2;
+	return subprog2(a, b);
+}
+
+
+SEC("struct_ops")
+int BPF_PROG(test_1)
+{
+	/* stack size 100 bytes */
+	int a[25] = {};
+
+	a[10] = 1;
+	val_i = subprog1(a);
+	bpf_testmod_ops3_call_test_2();
+	return 0;
+}
+
+SEC("struct_ops")
+int BPF_PROG(test_2)
+{
+	/* stack size 400 bytes */
+	int a[100] = {};
+
+	a[10] = 3;
+	val_j = subprog1(a);
+	return 0;
+}
+
+SEC(".struct_ops")
+struct bpf_testmod_ops3 testmod_1 = {
+	.test_1 = (void *)test_1,
+	.test_2 = (void *)test_2,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c
new file mode 100644
index 000000000000..f2f300d50988
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../bpf_testmod/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+#if defined(__TARGET_ARCH_x86)
+bool skip __attribute((__section__(".data"))) = false;
+#else
+bool skip = true;
+#endif
+
+void bpf_testmod_ops3_call_test_1(void) __ksym;
+
+int val_i, val_j;
+
+__noinline static int subprog2(int *a, int *b)
+{
+	return val_i + a[1] + b[20];
+}
+
+__noinline static int subprog1(int *a)
+{
+	/* stack size 400 bytes */
+	int b[100] = {};
+
+	b[20] = 2;
+	return subprog2(a, b);
+}
+
+
+SEC("struct_ops")
+int BPF_PROG(test_1)
+{
+	/* stack size 20 bytes */
+	int a[5] = {};
+
+	a[1] = 1;
+	val_j += subprog1(a);
+	bpf_testmod_ops3_call_test_1();
+	return 0;
+}
+
+SEC(".struct_ops")
+struct bpf_testmod_ops3 testmod_1 = {
+	.test_1 = (void *)test_1,
+};
-- 
cgit