Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Alexei Starovoitov says:

====================
pull-request: bpf 2022-03-29

We've added 16 non-merge commits during the last 1 day(s) which contain
a total of 24 files changed, 354 insertions(+), 187 deletions(-).

The main changes are:

1) x86 specific bits of fprobe/rethook, from Masami and Peter.

2) ice/xsk fixes, from Maciej and Magnus.

3) Various small fixes, from Andrii, Yonghong, Geliang and others.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  selftests/bpf: Fix clang compilation errors
  ice: xsk: Fix indexing in ice_tx_xsk_pool()
  ice: xsk: Stop Rx processing when ntc catches ntu
  ice: xsk: Eliminate unnecessary loop iteration
  xsk: Do not write NULL in SW ring at allocation failure
  x86,kprobes: Fix optprobe trampoline to generate complete pt_regs
  x86,rethook: Fix arch_rethook_trampoline() to generate a complete pt_regs
  x86,rethook,kprobes: Replace kretprobe with rethook on x86
  kprobes: Use rethook for kretprobe if possible
  bpftool: Fix generated code in codegen_asserts
  selftests/bpf: fix selftest after random: Urandom_read tracepoint removal
  bpf: Fix maximum permitted number of arguments check
  bpf: Sync comments for bpf_get_stack
  fprobe: Fix sparse warning for acccessing __rcu ftrace_hash
  fprobe: Fix smatch type mismatch warning
  bpf/bpftool: Add unprivileged_bpf_disabled check against value of 2
====================

Link: https://lore.kernel.org/r/20220329234924.39053-1-alexei.starovoitov@gmail.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

arch/Kconfig

@@ -164,7 +164,13 @@ config ARCH_USE_BUILTIN_BSWAP
 
 config KRETPROBES
 	def_bool y
-	depends on KPROBES && HAVE_KRETPROBES
+	depends on KPROBES && (HAVE_KRETPROBES || HAVE_RETHOOK)
+
+config KRETPROBE_ON_RETHOOK
+	def_bool y
+	depends on HAVE_RETHOOK
+	depends on KRETPROBES
+	select RETHOOK
 
 config USER_RETURN_NOTIFIER
 	bool

arch/x86/Kconfig

@@ -224,6 +224,7 @@ config X86
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_KRETPROBES
+	select HAVE_RETHOOK
 	select HAVE_KVM
 	select HAVE_LIVEPATCH			if X86_64
 	select HAVE_MIXED_BREAKPOINTS_REGS

arch/x86/include/asm/unwind.h

@@ -4,7 +4,7 @@
 
 #include <linux/sched.h>
 #include <linux/ftrace.h>
-#include <linux/kprobes.h>
+#include <linux/rethook.h>
 #include <asm/ptrace.h>
 #include <asm/stacktrace.h>
 
@@ -16,7 +16,7 @@ struct unwind_state {
 	unsigned long stack_mask;
 	struct task_struct *task;
 	int graph_idx;
-#ifdef CONFIG_KRETPROBES
+#if defined(CONFIG_RETHOOK)
 	struct llist_node *kr_cur;
 #endif
 	bool error;
@@ -104,19 +104,18 @@ void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size,
 #endif
 
 static inline
-unsigned long unwind_recover_kretprobe(struct unwind_state *state,
-				       unsigned long addr, unsigned long *addr_p)
+unsigned long unwind_recover_rethook(struct unwind_state *state,
+				     unsigned long addr, unsigned long *addr_p)
 {
-#ifdef CONFIG_KRETPROBES
-	return is_kretprobe_trampoline(addr) ?
-		kretprobe_find_ret_addr(state->task, addr_p, &state->kr_cur) :
-		addr;
-#else
-	return addr;
+#ifdef CONFIG_RETHOOK
+	if (is_rethook_trampoline(addr))
+		return rethook_find_ret_addr(state->task, (unsigned long)addr_p,
+					     &state->kr_cur);
 #endif
+	return addr;
 }
 
-/* Recover the return address modified by kretprobe and ftrace_graph. */
+/* Recover the return address modified by rethook and ftrace_graph. */
 static inline
 unsigned long unwind_recover_ret_addr(struct unwind_state *state,
 				     unsigned long addr, unsigned long *addr_p)
@@ -125,7 +124,7 @@ unsigned long unwind_recover_ret_addr(struct unwind_state *state,
 
 	ret = ftrace_graph_ret_addr(state->task, &state->graph_idx,
 				    addr, addr_p);
-	return unwind_recover_kretprobe(state, ret, addr_p);
+	return unwind_recover_rethook(state, ret, addr_p);
 }
 
 /*

arch/x86/kernel/Makefile

@@ -103,6 +103,7 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_X86_TSC)		+= trace_clock.o
 obj-$(CONFIG_TRACING)		+= trace.o
+obj-$(CONFIG_RETHOOK)		+= rethook.o
 obj-$(CONFIG_CRASH_CORE)	+= crash_core_$(BITS).o
 obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC_CORE)	+= relocate_kernel_$(BITS).o crash.o

arch/x86/kernel/kprobes/common.h

@@ -6,6 +6,7 @@
 
 #include <asm/asm.h>
 #include <asm/frame.h>
+#include <asm/insn.h>
 
 #ifdef CONFIG_X86_64
 

arch/x86/kernel/kprobes/core.c

@@ -811,18 +811,6 @@ set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 		= (regs->flags & X86_EFLAGS_IF);
 }
 
-void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
-{
-	unsigned long *sara = stack_addr(regs);
-
-	ri->ret_addr = (kprobe_opcode_t *) *sara;
-	ri->fp = sara;
-
-	/* Replace the return addr with trampoline addr */
-	*sara = (unsigned long) &__kretprobe_trampoline;
-}
-NOKPROBE_SYMBOL(arch_prepare_kretprobe);
-
 static void kprobe_post_process(struct kprobe *cur, struct pt_regs *regs,
 			       struct kprobe_ctlblk *kcb)
 {
@@ -1023,101 +1011,6 @@ int kprobe_int3_handler(struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(kprobe_int3_handler);
 
-/*
- * When a retprobed function returns, this code saves registers and
- * calls trampoline_handler() runs, which calls the kretprobe's handler.
- */
-asm(
-	".text\n"
-	".global __kretprobe_trampoline\n"
-	".type __kretprobe_trampoline, @function\n"
-	"__kretprobe_trampoline:\n"
-#ifdef CONFIG_X86_64
-	ANNOTATE_NOENDBR
-	/* Push a fake return address to tell the unwinder it's a kretprobe. */
-	"	pushq $__kretprobe_trampoline\n"
-	UNWIND_HINT_FUNC
-	/* Save the 'sp - 8', this will be fixed later. */
-	"	pushq %rsp\n"
-	"	pushfq\n"
-	SAVE_REGS_STRING
-	"	movq %rsp, %rdi\n"
-	"	call trampoline_handler\n"
-	RESTORE_REGS_STRING
-	/* In trampoline_handler(), 'regs->flags' is copied to 'regs->sp'. */
-	"	addq $8, %rsp\n"
-	"	popfq\n"
-#else
-	/* Push a fake return address to tell the unwinder it's a kretprobe. */
-	"	pushl $__kretprobe_trampoline\n"
-	UNWIND_HINT_FUNC
-	/* Save the 'sp - 4', this will be fixed later. */
-	"	pushl %esp\n"
-	"	pushfl\n"
-	SAVE_REGS_STRING
-	"	movl %esp, %eax\n"
-	"	call trampoline_handler\n"
-	RESTORE_REGS_STRING
-	/* In trampoline_handler(), 'regs->flags' is copied to 'regs->sp'. */
-	"	addl $4, %esp\n"
-	"	popfl\n"
-#endif
-	ASM_RET
-	".size __kretprobe_trampoline, .-__kretprobe_trampoline\n"
-);
-NOKPROBE_SYMBOL(__kretprobe_trampoline);
-/*
- * __kretprobe_trampoline() skips updating frame pointer. The frame pointer
- * saved in trampoline_handler() points to the real caller function's
- * frame pointer. Thus the __kretprobe_trampoline() doesn't have a
- * standard stack frame with CONFIG_FRAME_POINTER=y.
- * Let's mark it non-standard function. Anyway, FP unwinder can correctly
- * unwind without the hint.
- */
-STACK_FRAME_NON_STANDARD_FP(__kretprobe_trampoline);
-
-/* This is called from kretprobe_trampoline_handler(). */
-void arch_kretprobe_fixup_return(struct pt_regs *regs,
-				 kprobe_opcode_t *correct_ret_addr)
-{
-	unsigned long *frame_pointer = &regs->sp + 1;
-
-	/* Replace fake return address with real one. */
-	*frame_pointer = (unsigned long)correct_ret_addr;
-}
-
-/*
- * Called from __kretprobe_trampoline
- */
-__used __visible void trampoline_handler(struct pt_regs *regs)
-{
-	unsigned long *frame_pointer;
-
-	/* fixup registers */
-	regs->cs = __KERNEL_CS;
-#ifdef CONFIG_X86_32
-	regs->gs = 0;
-#endif
-	regs->ip = (unsigned long)&__kretprobe_trampoline;
-	regs->orig_ax = ~0UL;
-	regs->sp += sizeof(long);
-	frame_pointer = &regs->sp + 1;
-
-	/*
-	 * The return address at 'frame_pointer' is recovered by the
-	 * arch_kretprobe_fixup_return() which called from the
-	 * kretprobe_trampoline_handler().
-	 */
-	kretprobe_trampoline_handler(regs, frame_pointer);
-
-	/*
-	 * Copy FLAGS to 'pt_regs::sp' so that __kretprobe_trapmoline()
-	 * can do RET right after POPF.
-	 */
-	regs->sp = regs->flags;
-}
-NOKPROBE_SYMBOL(trampoline_handler);
-
 int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 {
 	struct kprobe *cur = kprobe_running();

arch/x86/kernel/kprobes/opt.c

@@ -106,7 +106,8 @@ asm (
 			".global optprobe_template_entry\n"
 			"optprobe_template_entry:\n"
 #ifdef CONFIG_X86_64
-			/* We don't bother saving the ss register */
+			"       pushq $" __stringify(__KERNEL_DS) "\n"
+			/* Save the 'sp - 8', this will be fixed later. */
 			"	pushq %rsp\n"
 			"	pushfq\n"
 			".global optprobe_template_clac\n"
@@ -121,14 +122,17 @@ asm (
 			".global optprobe_template_call\n"
 			"optprobe_template_call:\n"
 			ASM_NOP5
-			/* Move flags to rsp */
+			/* Copy 'regs->flags' into 'regs->ss'. */
 			"	movq 18*8(%rsp), %rdx\n"
-			"	movq %rdx, 19*8(%rsp)\n"
+			"	movq %rdx, 20*8(%rsp)\n"
 			RESTORE_REGS_STRING
-			/* Skip flags entry */
-			"	addq $8, %rsp\n"
+			/* Skip 'regs->flags' and 'regs->sp'. */
+			"	addq $16, %rsp\n"
+			/* And pop flags register from 'regs->ss'. */
 			"	popfq\n"
 #else /* CONFIG_X86_32 */
+			"	pushl %ss\n"
+			/* Save the 'sp - 4', this will be fixed later. */
 			"	pushl %esp\n"
 			"	pushfl\n"
 			".global optprobe_template_clac\n"
@@ -142,12 +146,13 @@ asm (
 			".global optprobe_template_call\n"
 			"optprobe_template_call:\n"
 			ASM_NOP5
-			/* Move flags into esp */
+			/* Copy 'regs->flags' into 'regs->ss'. */
 			"	movl 14*4(%esp), %edx\n"
-			"	movl %edx, 15*4(%esp)\n"
+			"	movl %edx, 16*4(%esp)\n"
 			RESTORE_REGS_STRING
-			/* Skip flags entry */
-			"	addl $4, %esp\n"
+			/* Skip 'regs->flags' and 'regs->sp'. */
+			"	addl $8, %esp\n"
+			/* And pop flags register from 'regs->ss'. */
 			"	popfl\n"
 #endif
 			".global optprobe_template_end\n"
@@ -179,6 +184,8 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
 		kprobes_inc_nmissed_count(&op->kp);
 	} else {
 		struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+		/* Adjust stack pointer */
+		regs->sp += sizeof(long);
 		/* Save skipped registers */
 		regs->cs = __KERNEL_CS;
 #ifdef CONFIG_X86_32

arch/x86/kernel/rethook.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * x86 implementation of rethook. Mostly copied from arch/x86/kernel/kprobes/core.c.
+ */
+#include <linux/bug.h>
+#include <linux/rethook.h>
+#include <linux/kprobes.h>
+#include <linux/objtool.h>
+
+#include "kprobes/common.h"
+
+__visible void arch_rethook_trampoline_callback(struct pt_regs *regs);
+
+#ifndef ANNOTATE_NOENDBR
+#define ANNOTATE_NOENDBR
+#endif
+
+/*
+ * When a target function returns, this code saves registers and calls
+ * arch_rethook_trampoline_callback(), which calls the rethook handler.
+ */
+asm(
+	".text\n"
+	".global arch_rethook_trampoline\n"
+	".type arch_rethook_trampoline, @function\n"
+	"arch_rethook_trampoline:\n"
+#ifdef CONFIG_X86_64
+	ANNOTATE_NOENDBR	/* This is only jumped from ret instruction */
+	/* Push a fake return address to tell the unwinder it's a rethook. */
+	"	pushq $arch_rethook_trampoline\n"
+	UNWIND_HINT_FUNC
+	"       pushq $" __stringify(__KERNEL_DS) "\n"
+	/* Save the 'sp - 16', this will be fixed later. */
+	"	pushq %rsp\n"
+	"	pushfq\n"
+	SAVE_REGS_STRING
+	"	movq %rsp, %rdi\n"
+	"	call arch_rethook_trampoline_callback\n"
+	RESTORE_REGS_STRING
+	/* In the callback function, 'regs->flags' is copied to 'regs->ss'. */
+	"	addq $16, %rsp\n"
+	"	popfq\n"
+#else
+	/* Push a fake return address to tell the unwinder it's a rethook. */
+	"	pushl $arch_rethook_trampoline\n"
+	UNWIND_HINT_FUNC
+	"	pushl %ss\n"
+	/* Save the 'sp - 8', this will be fixed later. */
+	"	pushl %esp\n"
+	"	pushfl\n"
+	SAVE_REGS_STRING
+	"	movl %esp, %eax\n"
+	"	call arch_rethook_trampoline_callback\n"
+	RESTORE_REGS_STRING
+	/* In the callback function, 'regs->flags' is copied to 'regs->ss'. */
+	"	addl $8, %esp\n"
+	"	popfl\n"
+#endif
+	ASM_RET
+	".size arch_rethook_trampoline, .-arch_rethook_trampoline\n"
+);
+NOKPROBE_SYMBOL(arch_rethook_trampoline);
+
+/*
+ * Called from arch_rethook_trampoline
+ */
+__used __visible void arch_rethook_trampoline_callback(struct pt_regs *regs)
+{
+	unsigned long *frame_pointer;
+
+	/* fixup registers */
+	regs->cs = __KERNEL_CS;
+#ifdef CONFIG_X86_32
+	regs->gs = 0;
+#endif
+	regs->ip = (unsigned long)&arch_rethook_trampoline;
+	regs->orig_ax = ~0UL;
+	regs->sp += 2*sizeof(long);
+	frame_pointer = (long *)(regs + 1);
+
+	/*
+	 * The return address at 'frame_pointer' is recovered by the
+	 * arch_rethook_fixup_return() which called from this
+	 * rethook_trampoline_handler().
+	 */
+	rethook_trampoline_handler(regs, (unsigned long)frame_pointer);
+
+	/*
+	 * Copy FLAGS to 'pt_regs::ss' so that arch_rethook_trapmoline()
+	 * can do RET right after POPF.
+	 */
+	*(unsigned long *)&regs->ss = regs->flags;
+}
+NOKPROBE_SYMBOL(arch_rethook_trampoline_callback);
+
+/*
+ * arch_rethook_trampoline() skips updating frame pointer. The frame pointer
+ * saved in arch_rethook_trampoline_callback() points to the real caller
+ * function's frame pointer. Thus the arch_rethook_trampoline() doesn't have
+ * a standard stack frame with CONFIG_FRAME_POINTER=y.
+ * Let's mark it non-standard function. Anyway, FP unwinder can correctly
+ * unwind without the hint.
+ */
+STACK_FRAME_NON_STANDARD_FP(arch_rethook_trampoline);
+
+/* This is called from rethook_trampoline_handler(). */
+void arch_rethook_fixup_return(struct pt_regs *regs,
+			       unsigned long correct_ret_addr)
+{
+	unsigned long *frame_pointer = (void *)(regs + 1);
+
+	/* Replace fake return address with real one. */
+	*frame_pointer = correct_ret_addr;
+}
+NOKPROBE_SYMBOL(arch_rethook_fixup_return);
+
+void arch_rethook_prepare(struct rethook_node *rh, struct pt_regs *regs, bool mcount)
+{
+	unsigned long *stack = (unsigned long *)regs->sp;
+
+	rh->ret_addr = stack[0];
+	rh->frame = regs->sp;
+
+	/* Replace the return addr with trampoline addr */
+	stack[0] = (unsigned long) arch_rethook_trampoline;
+}
+NOKPROBE_SYMBOL(arch_rethook_prepare);

arch/x86/kernel/unwind_orc.c

@@ -550,15 +550,15 @@ bool unwind_next_frame(struct unwind_state *state)
 		}
 		/*
 		 * There is a small chance to interrupt at the entry of
-		 * __kretprobe_trampoline() where the ORC info doesn't exist.
-		 * That point is right after the RET to __kretprobe_trampoline()
+		 * arch_rethook_trampoline() where the ORC info doesn't exist.
+		 * That point is right after the RET to arch_rethook_trampoline()
 		 * which was modified return address.
-		 * At that point, the @addr_p of the unwind_recover_kretprobe()
+		 * At that point, the @addr_p of the unwind_recover_rethook()
 		 * (this has to point the address of the stack entry storing
 		 * the modified return address) must be "SP - (a stack entry)"
 		 * because SP is incremented by the RET.
 		 */
-		state->ip = unwind_recover_kretprobe(state, state->ip,
+		state->ip = unwind_recover_rethook(state, state->ip,
 				(unsigned long *)(state->sp - sizeof(long)));
 		state->regs = (struct pt_regs *)sp;
 		state->prev_regs = NULL;
@@ -573,7 +573,7 @@ bool unwind_next_frame(struct unwind_state *state)
 			goto err;
 		}
 		/* See UNWIND_HINT_TYPE_REGS case comment. */
-		state->ip = unwind_recover_kretprobe(state, state->ip,
+		state->ip = unwind_recover_rethook(state, state->ip,
 				(unsigned long *)(state->sp - sizeof(long)));
 
 		if (state->full_regs)

drivers/net/ethernet/intel/ice/ice.h

@@ -710,7 +710,7 @@ static inline struct xsk_buff_pool *ice_tx_xsk_pool(struct ice_tx_ring *ring)
 	struct ice_vsi *vsi = ring->vsi;
 	u16 qid;
 
-	qid = ring->q_index - vsi->num_xdp_txq;
+	qid = ring->q_index - vsi->alloc_txq;
 
 	if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps))
 		return NULL;

drivers/net/ethernet/intel/ice/ice_xsk.c

@@ -608,6 +608,9 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
+		if (unlikely(rx_ring->next_to_clean == rx_ring->next_to_use))
+			break;
+
 		xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean);
 
 		size = le16_to_cpu(rx_desc->wb.pkt_len) &
@@ -754,7 +757,7 @@ static u16 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring, int napi_budget)
 		next_dd = next_dd + tx_thresh;
 		if (next_dd >= desc_cnt)
 			next_dd = tx_thresh - 1;
-	} while (budget--);
+	} while (--budget);
 
 	xdp_ring->next_dd = next_dd;
 

include/linux/kprobes.h

@@ -28,6 +28,7 @@
 #include <linux/ftrace.h>
 #include <linux/refcount.h>
 #include <linux/freelist.h>
+#include <linux/rethook.h>
 #include <asm/kprobes.h>
 
 #ifdef CONFIG_KPROBES
@@ -149,13 +150,20 @@ struct kretprobe {
 	int maxactive;
 	int nmissed;
 	size_t data_size;
+#ifdef CONFIG_KRETPROBE_ON_RETHOOK
+	struct rethook *rh;
+#else
 	struct freelist_head freelist;
 	struct kretprobe_holder *rph;
+#endif
 };
 
 #define KRETPROBE_MAX_DATA_SIZE	4096
 
 struct kretprobe_instance {
+#ifdef CONFIG_KRETPROBE_ON_RETHOOK
+	struct rethook_node node;
+#else
 	union {
 		struct freelist_node freelist;
 		struct rcu_head rcu;
@@ -164,6 +172,7 @@ struct kretprobe_instance {
 	struct kretprobe_holder *rph;
 	kprobe_opcode_t *ret_addr;
 	void *fp;
+#endif
 	char data[];
 };
 
@@ -186,10 +195,24 @@ extern void kprobe_busy_begin(void);
 extern void kprobe_busy_end(void);
 
 #ifdef CONFIG_KRETPROBES
-extern void arch_prepare_kretprobe(struct kretprobe_instance *ri,
-				   struct pt_regs *regs);
+/* Check whether @p is used for implementing a trampoline. */
 extern int arch_trampoline_kprobe(struct kprobe *p);
 
+#ifdef CONFIG_KRETPROBE_ON_RETHOOK
+static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri)
+{
+	RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(),
+		"Kretprobe is accessed from instance under preemptive context");
+
+	return (struct kretprobe *)READ_ONCE(ri->node.rethook->data);
+}
+static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri)
+{
+	return ri->node.ret_addr;
+}
+#else
+extern void arch_prepare_kretprobe(struct kretprobe_instance *ri,
+				   struct pt_regs *regs);
 void arch_kretprobe_fixup_return(struct pt_regs *regs,
 				 kprobe_opcode_t *correct_ret_addr);
 
@@ -232,6 +255,12 @@ static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance
 	return READ_ONCE(ri->rph->rp);
 }
 
+static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri)
+{
+	return (unsigned long)ri->ret_addr;
+}
+#endif /* CONFIG_KRETPROBE_ON_RETHOOK */
+
 #else /* !CONFIG_KRETPROBES */
 static inline void arch_prepare_kretprobe(struct kretprobe *rp,
 					struct pt_regs *regs)
@@ -395,7 +424,11 @@ void unregister_kretprobe(struct kretprobe *rp);
 int register_kretprobes(struct kretprobe **rps, int num);
 void unregister_kretprobes(struct kretprobe **rps, int num);
 
+#ifdef CONFIG_KRETPROBE_ON_RETHOOK
+#define kprobe_flush_task(tk)	do {} while (0)
+#else
 void kprobe_flush_task(struct task_struct *tk);
+#endif
 
 void kprobe_free_init_mem(void);
 
@@ -509,6 +542,19 @@ static inline bool is_kprobe_optinsn_slot(unsigned long addr)
 #endif /* !CONFIG_OPTPROBES */
 
 #ifdef CONFIG_KRETPROBES
+#ifdef CONFIG_KRETPROBE_ON_RETHOOK
+static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr)
+{
+	return is_rethook_trampoline(addr);
+}
+
+static nokprobe_inline
+unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp,
+				      struct llist_node **cur)
+{
+	return rethook_find_ret_addr(tsk, (unsigned long)fp, cur);
+}
+#else
 static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr)
 {
 	return (void *)addr == kretprobe_trampoline_addr();
@@ -516,6 +562,7 @@ static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr)
 
 unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp,
 				      struct llist_node **cur);
+#endif
 #else
 static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr)
 {

kernel/Makefile

@@ -108,6 +108,7 @@ obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_TRACE_CLOCK) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_TRACEPOINTS) += trace/
+obj-$(CONFIG_RETHOOK) += trace/
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
 obj-$(CONFIG_CPU_PM) += cpu_pm.o
 obj-$(CONFIG_BPF) += bpf/

kernel/bpf/btf.c

@@ -5507,7 +5507,7 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
 	}
 	args = (const struct btf_param *)(func + 1);
 	nargs = btf_type_vlen(func);
-	if (nargs >= MAX_BPF_FUNC_ARGS) {
+	if (nargs > MAX_BPF_FUNC_ARGS) {
 		bpf_log(log,
 			"The function %s has %d arguments. Too many.\n",
 			tname, nargs);

kernel/kprobes.c

@@ -1237,6 +1237,27 @@ void kprobes_inc_nmissed_count(struct kprobe *p)
 }
 NOKPROBE_SYMBOL(kprobes_inc_nmissed_count);
 
+static struct kprobe kprobe_busy = {
+	.addr = (void *) get_kprobe,
+};
+
+void kprobe_busy_begin(void)
+{
+	struct kprobe_ctlblk *kcb;
+
+	preempt_disable();
+	__this_cpu_write(current_kprobe, &kprobe_busy);
+	kcb = get_kprobe_ctlblk();
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+}
+
+void kprobe_busy_end(void)
+{
+	__this_cpu_write(current_kprobe, NULL);
+	preempt_enable();
+}
+
+#if !defined(CONFIG_KRETPROBE_ON_RETHOOK)
 static void free_rp_inst_rcu(struct rcu_head *head)
 {
 	struct kretprobe_instance *ri = container_of(head, struct kretprobe_instance, rcu);
@@ -1258,26 +1279,6 @@ static void recycle_rp_inst(struct kretprobe_instance *ri)
 }
 NOKPROBE_SYMBOL(recycle_rp_inst);
 
-static struct kprobe kprobe_busy = {
-	.addr = (void *) get_kprobe,
-};
-
-void kprobe_busy_begin(void)
-{
-	struct kprobe_ctlblk *kcb;
-
-	preempt_disable();
-	__this_cpu_write(current_kprobe, &kprobe_busy);
-	kcb = get_kprobe_ctlblk();
-	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-}
-
-void kprobe_busy_end(void)
-{
-	__this_cpu_write(current_kprobe, NULL);
-	preempt_enable();
-}
-
 /*
  * This function is called from delayed_put_task_struct() when a task is
  * dead and cleaned up to recycle any kretprobe instances associated with
@@ -1327,6 +1328,7 @@ static inline void free_rp_inst(struct kretprobe *rp)
 		rp->rph = NULL;
 	}
 }
+#endif	/* !CONFIG_KRETPROBE_ON_RETHOOK */
 
 /* Add the new probe to 'ap->list'. */
 static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
@@ -1925,6 +1927,7 @@ static struct notifier_block kprobe_exceptions_nb = {
 
 #ifdef CONFIG_KRETPROBES
 
+#if !defined(CONFIG_KRETPROBE_ON_RETHOOK)
 /* This assumes the 'tsk' is the current task or the is not running. */
 static kprobe_opcode_t *__kretprobe_find_ret_addr(struct task_struct *tsk,
 						  struct llist_node **cur)
@@ -2087,6 +2090,57 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 	return 0;
 }
 NOKPROBE_SYMBOL(pre_handler_kretprobe);
+#else /* CONFIG_KRETPROBE_ON_RETHOOK */
+/*
+ * This kprobe pre_handler is registered with every kretprobe. When probe
+ * hits it will set up the return probe.
+ */
+static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kretprobe *rp = container_of(p, struct kretprobe, kp);
+	struct kretprobe_instance *ri;
+	struct rethook_node *rhn;
+
+	rhn = rethook_try_get(rp->rh);
+	if (!rhn) {
+		rp->nmissed++;
+		return 0;
+	}
+
+	ri = container_of(rhn, struct kretprobe_instance, node);
+
+	if (rp->entry_handler && rp->entry_handler(ri, regs))
+		rethook_recycle(rhn);
+	else
+		rethook_hook(rhn, regs, kprobe_ftrace(p));
+
+	return 0;
+}
+NOKPROBE_SYMBOL(pre_handler_kretprobe);
+
+static void kretprobe_rethook_handler(struct rethook_node *rh, void *data,
+				      struct pt_regs *regs)
+{
+	struct kretprobe *rp = (struct kretprobe *)data;
+	struct kretprobe_instance *ri;
+	struct kprobe_ctlblk *kcb;
+
+	/* The data must NOT be null. This means rethook data structure is broken. */
+	if (WARN_ON_ONCE(!data))
+		return;
+
+	__this_cpu_write(current_kprobe, &rp->kp);
+	kcb = get_kprobe_ctlblk();
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+
+	ri = container_of(rh, struct kretprobe_instance, node);
+	rp->handler(ri, regs);
+
+	__this_cpu_write(current_kprobe, NULL);
+}
+NOKPROBE_SYMBOL(kretprobe_rethook_handler);
+
+#endif /* !CONFIG_KRETPROBE_ON_RETHOOK */
 
 /**
  * kprobe_on_func_entry() -- check whether given address is function entry
@@ -2155,6 +2209,29 @@ int register_kretprobe(struct kretprobe *rp)
 		rp->maxactive = num_possible_cpus();
 #endif
 	}
+#ifdef CONFIG_KRETPROBE_ON_RETHOOK
+	rp->rh = rethook_alloc((void *)rp, kretprobe_rethook_handler);
+	if (!rp->rh)
+		return -ENOMEM;
+
+	for (i = 0; i < rp->maxactive; i++) {
+		inst = kzalloc(sizeof(struct kretprobe_instance) +
+			       rp->data_size, GFP_KERNEL);
+		if (inst == NULL) {
+			rethook_free(rp->rh);
+			rp->rh = NULL;
+			return -ENOMEM;
+		}
+		rethook_add_node(rp->rh, &inst->node);
+	}
+	rp->nmissed = 0;
+	/* Establish function entry probe point */
+	ret = register_kprobe(&rp->kp);
+	if (ret != 0) {
+		rethook_free(rp->rh);
+		rp->rh = NULL;
+	}
+#else	/* !CONFIG_KRETPROBE_ON_RETHOOK */
 	rp->freelist.head = NULL;
 	rp->rph = kzalloc(sizeof(struct kretprobe_holder), GFP_KERNEL);
 	if (!rp->rph)
@@ -2179,6 +2256,7 @@ int register_kretprobe(struct kretprobe *rp)
 	ret = register_kprobe(&rp->kp);
 	if (ret != 0)
 		free_rp_inst(rp);
+#endif
 	return ret;
 }
 EXPORT_SYMBOL_GPL(register_kretprobe);
@@ -2217,7 +2295,11 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
 	for (i = 0; i < num; i++) {
 		if (__unregister_kprobe_top(&rps[i]->kp) < 0)
 			rps[i]->kp.addr = NULL;
+#ifdef CONFIG_KRETPROBE_ON_RETHOOK
+		rethook_free(rps[i]->rh);
+#else
 		rps[i]->rph->rp = NULL;
+#endif
 	}
 	mutex_unlock(&kprobe_mutex);
 
@@ -2225,7 +2307,9 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
 	for (i = 0; i < num; i++) {
 		if (rps[i]->kp.addr) {
 			__unregister_kprobe_bottom(&rps[i]->kp);
+#ifndef CONFIG_KRETPROBE_ON_RETHOOK
 			free_rp_inst(rps[i]);
+#endif
 		}
 	}
 }

kernel/trace/fprobe.c

@@ -150,15 +150,15 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
 
 	fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler);
 	for (i = 0; i < size; i++) {
-		struct rethook_node *node;
+		struct fprobe_rethook_node *node;
 
-		node = kzalloc(sizeof(struct fprobe_rethook_node), GFP_KERNEL);
+		node = kzalloc(sizeof(*node), GFP_KERNEL);
 		if (!node) {
 			rethook_free(fp->rethook);
 			fp->rethook = NULL;
 			return -ENOMEM;
 		}
-		rethook_add_node(fp->rethook, node);
+		rethook_add_node(fp->rethook, &node->node);
 	}
 	return 0;
 }
@@ -215,7 +215,7 @@ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter
 	 * correctly calculate the total number of filtered symbols
 	 * from both filter and notfilter.
 	 */
-	hash = fp->ops.local_hash.filter_hash;
+	hash = rcu_access_pointer(fp->ops.local_hash.filter_hash);
 	if (WARN_ON_ONCE(!hash))
 		goto out;
 

kernel/trace/trace_kprobe.c

@@ -1433,7 +1433,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 	fbuffer.regs = regs;
 	entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
 	entry->func = (unsigned long)tk->rp.kp.addr;
-	entry->ret_ip = (unsigned long)ri->ret_addr;
+	entry->ret_ip = get_kretprobe_retaddr(ri);
 	store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
 
 	trace_event_buffer_commit(&fbuffer);
@@ -1628,7 +1628,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 		return;
 
 	entry->func = (unsigned long)tk->rp.kp.addr;
-	entry->ret_ip = (unsigned long)ri->ret_addr;
+	entry->ret_ip = get_kretprobe_retaddr(ri);
 	store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
 			      head, NULL);

net/xdp/xsk_buff_pool.c

@@ -591,9 +591,13 @@ u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
 	u32 nb_entries1 = 0, nb_entries2;
 
 	if (unlikely(pool->dma_need_sync)) {
+		struct xdp_buff *buff;
+
 		/* Slow path */
-		*xdp = xp_alloc(pool);
-		return !!*xdp;
+		buff = xp_alloc(pool);
+		if (buff)
+			*xdp = buff;
+		return !!buff;
 	}
 
 	if (unlikely(pool->free_list_cnt)) {

tools/bpf/bpftool/feature.c

@@ -207,7 +207,10 @@ static void probe_unprivileged_disabled(void)
 			printf("bpf() syscall for unprivileged users is enabled\n");
 			break;
 		case 1:
-			printf("bpf() syscall restricted to privileged users\n");
+			printf("bpf() syscall restricted to privileged users (without recovery)\n");
+			break;
+		case 2:
+			printf("bpf() syscall restricted to privileged users (admin can change)\n");
 			break;
 		case -1:
 			printf("Unable to retrieve required privileges for bpf() syscall\n");

tools/bpf/bpftool/gen.c

@@ -477,7 +477,7 @@ static void codegen_asserts(struct bpf_object *obj, const char *obj_name)
 	codegen("\
 		\n\
 		__attribute__((unused)) static void			    \n\
-		%1$s__assert(struct %1$s *s)				    \n\
+		%1$s__assert(struct %1$s *s __attribute__((unused)))	    \n\
 		{							    \n\
 		#ifdef __cplusplus					    \n\
 		#define _Static_assert static_assert			    \n\

tools/include/uapi/linux/bpf.h

@@ -3009,8 +3009,8 @@ union bpf_attr {
  *
  * 			# sysctl kernel.perf_event_max_stack=<new value>
  * 	Return
- * 		A non-negative value equal to or less than *size* on success,
- * 		or a negative error in case of failure.
+ * 		The non-negative copied *buf* length equal to or less than
+ * 		*size* on success, or a negative error in case of failure.
  *
  * long bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header)
  * 	Description
@@ -4316,8 +4316,8 @@ union bpf_attr {
  *
  *			# sysctl kernel.perf_event_max_stack=<new value>
  *	Return
- *		A non-negative value equal to or less than *size* on success,
- *		or a negative error in case of failure.
+ * 		The non-negative copied *buf* length equal to or less than
+ * 		*size* on success, or a negative error in case of failure.
  *
  * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags)
  *	Description

tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c

@@ -29,11 +29,8 @@ static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size)
 	 */
 	struct get_stack_trace_t e;
 	int i, num_stack;
-	static __u64 cnt;
 	struct ksym *ks;
 
-	cnt++;
-
 	memset(&e, 0, sizeof(e));
 	memcpy(&e, data, size <= sizeof(e) ? size : sizeof(e));
 

tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c

@@ -39,16 +39,8 @@ struct {
 	__type(value, stack_trace_t);
 } stack_amap SEC(".maps");
 
-/* taken from /sys/kernel/debug/tracing/events/random/urandom_read/format */
-struct random_urandom_args {
-	unsigned long long pad;
-	int got_bits;
-	int pool_left;
-	int input_left;
-};
-
-SEC("tracepoint/random/urandom_read")
-int oncpu(struct random_urandom_args *args)
+SEC("kprobe/urandom_read")
+int oncpu(struct pt_regs *args)
 {
 	__u32 max_len = sizeof(struct bpf_stack_build_id)
 			* PERF_MAX_STACK_DEPTH;

tools/testing/selftests/bpf/test_lpm_map.c

@@ -209,7 +209,8 @@ static void test_lpm_order(void)
 static void test_lpm_map(int keysize)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC);
-	size_t i, j, n_matches, n_matches_after_delete, n_nodes, n_lookups;
+	volatile size_t n_matches, n_matches_after_delete;
+	size_t i, j, n_nodes, n_lookups;
 	struct tlpm_node *t, *list = NULL;
 	struct bpf_lpm_trie_key *key;
 	uint8_t *data, *value;