x86/uprobes: Fix XOL allocation failure for 32-bit tasks

This script

	#!/usr/bin/bash

	echo 0 > /proc/sys/kernel/randomize_va_space

	echo 'void main(void) {}' > TEST.c

	# -fcf-protection to ensure that the 1st endbr32 insn can't be emulated
	gcc -m32 -fcf-protection=branch TEST.c -o test

	bpftrace -e 'uprobe:./test:main {}' -c ./test

"hangs", the probed ./test task enters an endless loop.

The problem is that with randomize_va_space == 0
get_unmapped_area(TASK_SIZE - PAGE_SIZE) called by xol_add_vma() can not
just return the "addr == TASK_SIZE - PAGE_SIZE" hint, this addr is used
by the stack vma.

arch_get_unmapped_area_topdown() doesn't take TIF_ADDR32 into account and
in_32bit_syscall() is false, this leads to info.high_limit > TASK_SIZE.
vm_unmapped_area() happily returns the high address > TASK_SIZE and then
get_unmapped_area() returns -ENOMEM after the "if (addr > TASK_SIZE - len)"
check.

handle_swbp() doesn't report this failure (probably it should) and silently
restarts the probed insn. Endless loop.

I think that the right fix should change the x86 get_unmapped_area() paths
to rely on TIF_ADDR32 rather than in_32bit_syscall(). Note also that if
CONFIG_X86_X32_ABI=y, in_x32_syscall() falsely returns true in this case
because ->orig_ax = -1.

But we need a simple fix for -stable, so this patch just sets TS_COMPAT if
the probed task is 32-bit to make in_ia32_syscall() true.

Fixes: 1b028f784e8c ("x86/mm: Introduce mmap_compat_base() for 32-bit mmap()")
Reported-by: Paulo Andrade <pandrade@redhat.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/all/aV5uldEvV7pb4RA8@redhat.com/
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/aWO7Fdxn39piQnxu@redhat.com

3 files changed, 32 insertions, 3 deletions

diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 7be8e361ca55..619dddf54424 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -1823,3 +1823,27 @@ bool is_uprobe_at_func_entry(struct pt_regs *regs)
 
 	return false;
 }
+
+#ifdef CONFIG_IA32_EMULATION
+unsigned long arch_uprobe_get_xol_area(void)
+{
+	struct thread_info *ti = current_thread_info();
+	unsigned long vaddr;
+
+	/*
+	 * HACK: we are not in a syscall, but x86 get_unmapped_area() paths
+	 * ignore TIF_ADDR32 and rely on in_32bit_syscall() to calculate
+	 * vm_unmapped_area_info.high_limit.
+	 *
+	 * The #ifdef above doesn't cover the CONFIG_X86_X32_ABI=y case,
+	 * but in this case in_32bit_syscall() -> in_x32_syscall() always
+	 * (falsely) returns true because ->orig_ax == -1.
+	 */
+	if (test_thread_flag(TIF_ADDR32))
+		ti->status |= TS_COMPAT;
+	vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE, PAGE_SIZE, 0, 0);
+	ti->status &= ~TS_COMPAT;
+
+	return vaddr;
+}
+#endif
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index ee3d36eda45d..f548fea2adec 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -242,6 +242,7 @@ extern void arch_uprobe_clear_state(struct mm_struct *mm);
 extern void arch_uprobe_init_state(struct mm_struct *mm);
 extern void handle_syscall_uprobe(struct pt_regs *regs, unsigned long bp_vaddr);
 extern void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr);
+extern unsigned long arch_uprobe_get_xol_area(void);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index a7d7d83ca1d7..dfbce021fb02 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1694,6 +1694,12 @@ static const struct vm_special_mapping xol_mapping = {
 	.mremap = xol_mremap,
 };
 
+unsigned long __weak arch_uprobe_get_xol_area(void)
+{
+	/* Try to map as high as possible, this is only a hint. */
+	return get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE, PAGE_SIZE, 0, 0);
+}
+
 /* Slot allocation for XOL */
 static int xol_add_vma(struct mm_struct *mm, struct xol_area *area)
 {
@@ -1709,9 +1715,7 @@ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area)
 	}
 
 	if (!area->vaddr) {
-		/* Try to map as high as possible, this is only a hint. */
-		area->vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE,
-						PAGE_SIZE, 0, 0);
+		area->vaddr = arch_uprobe_get_xol_area();
 		if (IS_ERR_VALUE(area->vaddr)) {
 			ret = area->vaddr;
 			goto fail;