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.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 150 insertions, 121 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 6462e3dd98f4..c41ef42adbe8 100644
--- a/arch/x86/kernel/Makefile
+++ b/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
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index 7d3a2e2daf01..c993521d4933 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/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
 
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 8ef933c03afa..7c4ab8870da4 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/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();
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index b4a54a52aa59..e6b8c5362b94 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/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
diff --git a/arch/x86/kernel/rethook.c b/arch/x86/kernel/rethook.c
new file mode 100644
index 000000000000..8a1c0111ae79
--- /dev/null
+++ b/arch/x86/kernel/rethook.c
@@ -0,0 +1,127 @@
+// 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);
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 2de3c8c5eba9..794fdef2501a 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/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)