Merge tag 'probes-v6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull probes updates from Masami Hiramatsu:
 "Uprobes:

   - x86/shstk: Make return uprobe work with shadow stack

   - Add uretprobe syscall which speeds up the uretprobe 10-30% faster.
     This syscall is automatically used from user-space trampolines
     which are generated by the uretprobe. If this syscall is used by
     normal user program, it will cause SIGILL. Note that this is
     currently only implemented on x86_64.

     (This also has two fixes for adjusting the syscall number to avoid
     conflict with new *attrat syscalls.)

   - uprobes/perf: fix user stack traces in the presence of pending
     uretprobe. This corrects the uretprobe's trampoline address in the
     stacktrace with correct return address

   - selftests/x86: Add a return uprobe with shadow stack test

   - selftests/bpf: Add uretprobe syscall related tests.
      - test case for register integrity check
      - test case with register changing case
      - test case for uretprobe syscall without uprobes (expected to fail)
      - test case for uretprobe with shadow stack

   - selftests/bpf: add test validating uprobe/uretprobe stack traces

   - MAINTAINERS: Add uprobes entry. This does not specify the tree but
     to clarify who maintains and reviews the uprobes

  Kprobes:

   - tracing/kprobes: Test case cleanups.

     Replace redundant WARN_ON_ONCE() + pr_warn() with WARN_ONCE() and
     remove unnecessary code from selftest

   - tracing/kprobes: Add symbol counting check when module loads.

     This checks the uniqueness of the probed symbol on modules. The
     same check has already done for kernel symbols

     (This also has a fix for build error with CONFIG_MODULES=n)

  Cleanup:

   - Add MODULE_DESCRIPTION() macros for fprobe and kprobe examples"

* tag 'probes-v6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  MAINTAINERS: Add uprobes entry
  selftests/bpf: Change uretprobe syscall number in uprobe_syscall test
  uprobe: Change uretprobe syscall scope and number
  tracing/kprobes: Fix build error when find_module() is not available
  tracing/kprobes: Add symbol counting check when module loads
  selftests/bpf: add test validating uprobe/uretprobe stack traces
  perf,uprobes: fix user stack traces in the presence of pending uretprobes
  tracing/kprobe: Remove cleanup code unrelated to selftest
  tracing/kprobe: Integrate test warnings into WARN_ONCE
  selftests/bpf: Add uretprobe shadow stack test
  selftests/bpf: Add uretprobe syscall call from user space test
  selftests/bpf: Add uretprobe syscall test for regs changes
  selftests/bpf: Add uretprobe syscall test for regs integrity
  selftests/x86: Add return uprobe shadow stack test
  uprobe: Add uretprobe syscall to speed up return probe
  uprobe: Wire up uretprobe system call
  x86/shstk: Make return uprobe work with shadow stack
  samples: kprobes: add missing MODULE_DESCRIPTION() macros
  fprobe: add missing MODULE_DESCRIPTION() macro

Author: torvalds

MAINTAINERS

@@ -23367,6 +23367,19 @@ F:	drivers/mtd/ubi/
 F:	include/linux/mtd/ubi.h
 F:	include/uapi/mtd/ubi-user.h
 
+UPROBES
+M:	Masami Hiramatsu <[email protected]>
+M:	Oleg Nesterov <[email protected]>
+M:	Peter Zijlstra <[email protected]>
+L:	[email protected]
+L:	[email protected]
+S:	Maintained
+F:	arch/*/include/asm/uprobes.h
+F:	arch/*/kernel/probes/uprobes.c
+F:	arch/*/kernel/uprobes.c
+F:	include/linux/uprobes.h
+F:	kernel/events/uprobes.c
+
 USB "USBNET" DRIVER FRAMEWORK
 M:	Oliver Neukum <[email protected]>
 L:	[email protected]

arch/x86/entry/syscalls/syscall_64.tbl

@@ -385,6 +385,7 @@
 460	common	lsm_set_self_attr	sys_lsm_set_self_attr
 461	common	lsm_list_modules	sys_lsm_list_modules
 462 	common  mseal			sys_mseal
+467	common	uretprobe		sys_uretprobe
 
 #
 # Due to a historical design error, certain syscalls are numbered differently

arch/x86/include/asm/shstk.h

@@ -21,6 +21,8 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *p, unsigned long clon
 void shstk_free(struct task_struct *p);
 int setup_signal_shadow_stack(struct ksignal *ksig);
 int restore_signal_shadow_stack(void);
+int shstk_update_last_frame(unsigned long val);
+bool shstk_is_enabled(void);
 #else
 static inline long shstk_prctl(struct task_struct *task, int option,
 			       unsigned long arg2) { return -EINVAL; }
@@ -31,6 +33,8 @@ static inline unsigned long shstk_alloc_thread_stack(struct task_struct *p,
 static inline void shstk_free(struct task_struct *p) {}
 static inline int setup_signal_shadow_stack(struct ksignal *ksig) { return 0; }
 static inline int restore_signal_shadow_stack(void) { return 0; }
+static inline int shstk_update_last_frame(unsigned long val) { return 0; }
+static inline bool shstk_is_enabled(void) { return false; }
 #endif /* CONFIG_X86_USER_SHADOW_STACK */
 
 #endif /* __ASSEMBLY__ */

arch/x86/kernel/shstk.c

@@ -577,3 +577,19 @@ long shstk_prctl(struct task_struct *task, int option, unsigned long arg2)
 		return wrss_control(true);
 	return -EINVAL;
 }
+
+int shstk_update_last_frame(unsigned long val)
+{
+	unsigned long ssp;
+
+	if (!features_enabled(ARCH_SHSTK_SHSTK))
+		return 0;
+
+	ssp = get_user_shstk_addr();
+	return write_user_shstk_64((u64 __user *)ssp, (u64)val);
+}
+
+bool shstk_is_enabled(void)
+{
+	return features_enabled(ARCH_SHSTK_SHSTK);
+}

arch/x86/kernel/uprobes.c

@@ -12,6 +12,7 @@
 #include <linux/ptrace.h>
 #include <linux/uprobes.h>
 #include <linux/uaccess.h>
+#include <linux/syscalls.h>
 
 #include <linux/kdebug.h>
 #include <asm/processor.h>
@@ -308,6 +309,122 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
 }
 
 #ifdef CONFIG_X86_64
+
+asm (
+	".pushsection .rodata\n"
+	".global uretprobe_trampoline_entry\n"
+	"uretprobe_trampoline_entry:\n"
+	"pushq %rax\n"
+	"pushq %rcx\n"
+	"pushq %r11\n"
+	"movq $" __stringify(__NR_uretprobe) ", %rax\n"
+	"syscall\n"
+	".global uretprobe_syscall_check\n"
+	"uretprobe_syscall_check:\n"
+	"popq %r11\n"
+	"popq %rcx\n"
+
+	/* The uretprobe syscall replaces stored %rax value with final
+	 * return address, so we don't restore %rax in here and just
+	 * call ret.
+	 */
+	"retq\n"
+	".global uretprobe_trampoline_end\n"
+	"uretprobe_trampoline_end:\n"
+	".popsection\n"
+);
+
+extern u8 uretprobe_trampoline_entry[];
+extern u8 uretprobe_trampoline_end[];
+extern u8 uretprobe_syscall_check[];
+
+void *arch_uprobe_trampoline(unsigned long *psize)
+{
+	static uprobe_opcode_t insn = UPROBE_SWBP_INSN;
+	struct pt_regs *regs = task_pt_regs(current);
+
+	/*
+	 * At the moment the uretprobe syscall trampoline is supported
+	 * only for native 64-bit process, the compat process still uses
+	 * standard breakpoint.
+	 */
+	if (user_64bit_mode(regs)) {
+		*psize = uretprobe_trampoline_end - uretprobe_trampoline_entry;
+		return uretprobe_trampoline_entry;
+	}
+
+	*psize = UPROBE_SWBP_INSN_SIZE;
+	return &insn;
+}
+
+static unsigned long trampoline_check_ip(void)
+{
+	unsigned long tramp = uprobe_get_trampoline_vaddr();
+
+	return tramp + (uretprobe_syscall_check - uretprobe_trampoline_entry);
+}
+
+SYSCALL_DEFINE0(uretprobe)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+	unsigned long err, ip, sp, r11_cx_ax[3];
+
+	if (regs->ip != trampoline_check_ip())
+		goto sigill;
+
+	err = copy_from_user(r11_cx_ax, (void __user *)regs->sp, sizeof(r11_cx_ax));
+	if (err)
+		goto sigill;
+
+	/* expose the "right" values of r11/cx/ax/sp to uprobe_consumer/s */
+	regs->r11 = r11_cx_ax[0];
+	regs->cx  = r11_cx_ax[1];
+	regs->ax  = r11_cx_ax[2];
+	regs->sp += sizeof(r11_cx_ax);
+	regs->orig_ax = -1;
+
+	ip = regs->ip;
+	sp = regs->sp;
+
+	uprobe_handle_trampoline(regs);
+
+	/*
+	 * Some of the uprobe consumers has changed sp, we can do nothing,
+	 * just return via iret.
+	 * .. or shadow stack is enabled, in which case we need to skip
+	 * return through the user space stack address.
+	 */
+	if (regs->sp != sp || shstk_is_enabled())
+		return regs->ax;
+	regs->sp -= sizeof(r11_cx_ax);
+
+	/* for the case uprobe_consumer has changed r11/cx */
+	r11_cx_ax[0] = regs->r11;
+	r11_cx_ax[1] = regs->cx;
+
+	/*
+	 * ax register is passed through as return value, so we can use
+	 * its space on stack for ip value and jump to it through the
+	 * trampoline's ret instruction
+	 */
+	r11_cx_ax[2] = regs->ip;
+	regs->ip = ip;
+
+	err = copy_to_user((void __user *)regs->sp, r11_cx_ax, sizeof(r11_cx_ax));
+	if (err)
+		goto sigill;
+
+	/* ensure sysret, see do_syscall_64() */
+	regs->r11 = regs->flags;
+	regs->cx  = regs->ip;
+
+	return regs->ax;
+
+sigill:
+	force_sig(SIGILL);
+	return -1;
+}
+
 /*
  * If arch_uprobe->insn doesn't use rip-relative addressing, return
  * immediately.  Otherwise, rewrite the instruction so that it accesses
@@ -1076,8 +1193,13 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs
 		return orig_ret_vaddr;
 
 	nleft = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize);
-	if (likely(!nleft))
+	if (likely(!nleft)) {
+		if (shstk_update_last_frame(trampoline_vaddr)) {
+			force_sig(SIGSEGV);
+			return -1;
+		}
 		return orig_ret_vaddr;
+	}
 
 	if (nleft != rasize) {
 		pr_err("return address clobbered: pid=%d, %%sp=%#lx, %%ip=%#lx\n",

include/linux/syscalls.h

@@ -979,6 +979,8 @@ asmlinkage long sys_lsm_list_modules(u64 __user *ids, u32 __user *size, u32 flag
 /* x86 */
 asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on);
 
+asmlinkage long sys_uretprobe(void);
+
 /* pciconfig: alpha, arm, arm64, ia64, sparc */
 asmlinkage long sys_pciconfig_read(unsigned long bus, unsigned long dfn,
 				unsigned long off, unsigned long len,

include/linux/uprobes.h

@@ -138,6 +138,9 @@ extern bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check c
 extern bool arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs);
 extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 					 void *src, unsigned long len);
+extern void uprobe_handle_trampoline(struct pt_regs *regs);
+extern void *arch_uprobe_trampoline(unsigned long *psize);
+extern unsigned long uprobe_get_trampoline_vaddr(void);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };

include/uapi/asm-generic/unistd.h

@@ -841,8 +841,11 @@ __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
 #define __NR_mseal 462
 __SYSCALL(__NR_mseal, sys_mseal)
 
+#define __NR_uretprobe 463
+__SYSCALL(__NR_uretprobe, sys_uretprobe)
+
 #undef __NR_syscalls
-#define __NR_syscalls 463
+#define __NR_syscalls 464
 
 /*
  * 32 bit systems traditionally used different

kernel/events/callchain.c

@@ -11,6 +11,7 @@
 #include <linux/perf_event.h>
 #include <linux/slab.h>
 #include <linux/sched/task_stack.h>
+#include <linux/uprobes.h>
 
 #include "internal.h"
 
@@ -176,13 +177,51 @@ put_callchain_entry(int rctx)
 	put_recursion_context(this_cpu_ptr(callchain_recursion), rctx);
 }
 
+static void fixup_uretprobe_trampoline_entries(struct perf_callchain_entry *entry,
+					       int start_entry_idx)
+{
+#ifdef CONFIG_UPROBES
+	struct uprobe_task *utask = current->utask;
+	struct return_instance *ri;
+	__u64 *cur_ip, *last_ip, tramp_addr;
+
+	if (likely(!utask || !utask->return_instances))
+		return;
+
+	cur_ip = &entry->ip[start_entry_idx];
+	last_ip = &entry->ip[entry->nr - 1];
+	ri = utask->return_instances;
+	tramp_addr = uprobe_get_trampoline_vaddr();
+
+	/*
+	 * If there are pending uretprobes for the current thread, they are
+	 * recorded in a list inside utask->return_instances; each such
+	 * pending uretprobe replaces traced user function's return address on
+	 * the stack, so when stack trace is captured, instead of seeing
+	 * actual function's return address, we'll have one or many uretprobe
+	 * trampoline addresses in the stack trace, which are not helpful and
+	 * misleading to users.
+	 * So here we go over the pending list of uretprobes, and each
+	 * encountered trampoline address is replaced with actual return
+	 * address.
+	 */
+	while (ri && cur_ip <= last_ip) {
+		if (*cur_ip == tramp_addr) {
+			*cur_ip = ri->orig_ret_vaddr;
+			ri = ri->next;
+		}
+		cur_ip++;
+	}
+#endif
+}
+
 struct perf_callchain_entry *
 get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 		   u32 max_stack, bool crosstask, bool add_mark)
 {
 	struct perf_callchain_entry *entry;
 	struct perf_callchain_entry_ctx ctx;
-	int rctx;
+	int rctx, start_entry_idx;
 
 	entry = get_callchain_entry(&rctx);
 	if (!entry)
@@ -215,7 +254,9 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 			if (add_mark)
 				perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
 
+			start_entry_idx = entry->nr;
 			perf_callchain_user(&ctx, regs);
+			fixup_uretprobe_trampoline_entries(entry, start_entry_idx);
 		}
 	}