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

2 files changed, 68 insertions, 8 deletions

diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index ad57944b6c40..8d57255e5b29 100644
--- a/kernel/events/callchain.c
+++ b/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);
 		}
 	}
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 2c83ba776fc7..99be2adedbc0 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1474,11 +1474,20 @@ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area)
 	return ret;
 }
 
+void * __weak arch_uprobe_trampoline(unsigned long *psize)
+{
+	static uprobe_opcode_t insn = UPROBE_SWBP_INSN;
+
+	*psize = UPROBE_SWBP_INSN_SIZE;
+	return &insn;
+}
+
 static struct xol_area *__create_xol_area(unsigned long vaddr)
 {
 	struct mm_struct *mm = current->mm;
-	uprobe_opcode_t insn = UPROBE_SWBP_INSN;
+	unsigned long insns_size;
 	struct xol_area *area;
+	void *insns;
 
 	area = kmalloc(sizeof(*area), GFP_KERNEL);
 	if (unlikely(!area))
@@ -1502,7 +1511,8 @@ static struct xol_area *__create_xol_area(unsigned long vaddr)
 	/* Reserve the 1st slot for get_trampoline_vaddr() */
 	set_bit(0, area->bitmap);
 	atomic_set(&area->slot_count, 1);
-	arch_uprobe_copy_ixol(area->pages[0], 0, &insn, UPROBE_SWBP_INSN_SIZE);
+	insns = arch_uprobe_trampoline(&insns_size);
+	arch_uprobe_copy_ixol(area->pages[0], 0, insns, insns_size);
 
 	if (!xol_add_vma(mm, area))
 		return area;
@@ -1827,7 +1837,7 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
  *
  * Returns -1 in case the xol_area is not allocated.
  */
-static unsigned long get_trampoline_vaddr(void)
+unsigned long uprobe_get_trampoline_vaddr(void)
 {
 	struct xol_area *area;
 	unsigned long trampoline_vaddr = -1;
@@ -1878,7 +1888,7 @@ static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs)
 	if (!ri)
 		return;
 
-	trampoline_vaddr = get_trampoline_vaddr();
+	trampoline_vaddr = uprobe_get_trampoline_vaddr();
 	orig_ret_vaddr = arch_uretprobe_hijack_return_addr(trampoline_vaddr, regs);
 	if (orig_ret_vaddr == -1)
 		goto fail;
@@ -2123,7 +2133,7 @@ static struct return_instance *find_next_ret_chain(struct return_instance *ri)
 	return ri;
 }
 
-static void handle_trampoline(struct pt_regs *regs)
+void uprobe_handle_trampoline(struct pt_regs *regs)
 {
 	struct uprobe_task *utask;
 	struct return_instance *ri, *next;
@@ -2149,6 +2159,15 @@ static void handle_trampoline(struct pt_regs *regs)
 
 		instruction_pointer_set(regs, ri->orig_ret_vaddr);
 		do {
+			/* pop current instance from the stack of pending return instances,
+			 * as it's not pending anymore: we just fixed up original
+			 * instruction pointer in regs and are about to call handlers;
+			 * this allows fixup_uretprobe_trampoline_entries() to properly fix up
+			 * captured stack traces from uretprobe handlers, in which pending
+			 * trampoline addresses on the stack are replaced with correct
+			 * original return addresses
+			 */
+			utask->return_instances = ri->next;
 			if (valid)
 				handle_uretprobe_chain(ri, regs);
 			ri = free_ret_instance(ri);
@@ -2187,8 +2206,8 @@ static void handle_swbp(struct pt_regs *regs)
 	int is_swbp;
 
 	bp_vaddr = uprobe_get_swbp_addr(regs);
-	if (bp_vaddr == get_trampoline_vaddr())
-		return handle_trampoline(regs);
+	if (bp_vaddr == uprobe_get_trampoline_vaddr())
+		return uprobe_handle_trampoline(regs);
 
 	uprobe = find_active_uprobe(bp_vaddr, &is_swbp);
 	if (!uprobe) {