bpf: Prevent KASAN false positive with bpf_throw

The KASAN stack instrumentation when CONFIG_KASAN_STACK is true poisons
the stack of a function when it is entered and unpoisons it when
leaving. However, in the case of bpf_throw, we will never return as we
switch our stack frame to the BPF exception callback. Later, this
discrepancy will lead to confusing KASAN splats when kernel resumes
execution on return from the BPF program.

Fix this by unpoisoning everything below the stack pointer of the BPF
program, which should cover the range that would not be unpoisoned. An
example splat is below:

BUG: KASAN: stack-out-of-bounds in stack_trace_consume_entry+0x14e/0x170
Write of size 8 at addr ffffc900013af958 by task test_progs/227

CPU: 0 PID: 227 Comm: test_progs Not tainted 6.5.0-rc2-g43f1c6c9052a-dirty #26
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-2.fc39 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl+0x4a/0x80
 print_report+0xcf/0x670
 ? arch_stack_walk+0x79/0x100
 kasan_report+0xda/0x110
 ? stack_trace_consume_entry+0x14e/0x170
 ? stack_trace_consume_entry+0x14e/0x170
 ? __pfx_stack_trace_consume_entry+0x10/0x10
 stack_trace_consume_entry+0x14e/0x170
 ? __sys_bpf+0xf2e/0x41b0
 arch_stack_walk+0x8b/0x100
 ? __sys_bpf+0xf2e/0x41b0
 ? bpf_prog_test_run_skb+0x341/0x1c70
 ? bpf_prog_test_run_skb+0x341/0x1c70
 stack_trace_save+0x9b/0xd0
 ? __pfx_stack_trace_save+0x10/0x10
 ? __kasan_slab_free+0x109/0x180
 ? bpf_prog_test_run_skb+0x341/0x1c70
 ? __sys_bpf+0xf2e/0x41b0
 ? __x64_sys_bpf+0x78/0xc0
 ? do_syscall_64+0x3c/0x90
 ? entry_SYSCALL_64_after_hwframe+0x6e/0xd8
 kasan_save_stack+0x33/0x60
 ? kasan_save_stack+0x33/0x60
 ? kasan_set_track+0x25/0x30
 ? kasan_save_free_info+0x2b/0x50
 ? __kasan_slab_free+0x109/0x180
 ? kmem_cache_free+0x191/0x460
 ? bpf_prog_test_run_skb+0x341/0x1c70
 kasan_set_track+0x25/0x30
 kasan_save_free_info+0x2b/0x50
 __kasan_slab_free+0x109/0x180
 kmem_cache_free+0x191/0x460
 bpf_prog_test_run_skb+0x341/0x1c70
 ? __pfx_bpf_prog_test_run_skb+0x10/0x10
 ? __fget_light+0x51/0x220
 __sys_bpf+0xf2e/0x41b0
 ? __might_fault+0xa2/0x170
 ? __pfx___sys_bpf+0x10/0x10
 ? lock_release+0x1de/0x620
 ? __might_fault+0xcd/0x170
 ? __pfx_lock_release+0x10/0x10
 ? __pfx_blkcg_maybe_throttle_current+0x10/0x10
 __x64_sys_bpf+0x78/0xc0
 ? syscall_enter_from_user_mode+0x20/0x50
 do_syscall_64+0x3c/0x90
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8
RIP: 0033:0x7f0fbb38880d
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d
89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d f3 45 12 00 f7 d8 64
89 01 48
RSP: 002b:00007ffe13907de8 EFLAGS: 00000206 ORIG_RAX: 0000000000000141
RAX: ffffffffffffffda RBX: 00007ffe13908708 RCX: 00007f0fbb38880d
RDX: 0000000000000050 RSI: 00007ffe13907e20 RDI: 000000000000000a
RBP: 00007ffe13907e00 R08: 0000000000000000 R09: 00007ffe13907e20
R10: 0000000000000064 R11: 0000000000000206 R12: 0000000000000003
R13: 0000000000000000 R14: 00007f0fbb532000 R15: 0000000000cfbd90
 </TASK>

The buggy address belongs to stack of task test_progs/227
KASAN internal error: frame info validation failed; invalid marker: 0

The buggy address belongs to the virtual mapping at
 [ffffc900013a8000, ffffc900013b1000) created by:
 kernel_clone+0xcd/0x600

The buggy address belongs to the physical page:
page:00000000b70f4332 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x11418f
flags: 0x2fffe0000000000(node=0|zone=2|lastcpupid=0x7fff)
page_type: 0xffffffff()
raw: 02fffe0000000000 0000000000000000 dead000000000122 0000000000000000
raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffffc900013af800: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffffc900013af880: 00 00 00 f1 f1 f1 f1 00 00 00 f3 f3 f3 f3 f3 00
>ffffc900013af900: 00 00 00 00 00 00 00 00 00 00 00 f1 00 00 00 00
                                                    ^
 ffffc900013af980: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffffc900013afa00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
==================================================================
Disabling lock debugging due to kernel taint

Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Acked-by: Andrey Konovalov <andreyknvl@gmail.com>
Link: https://lore.kernel.org/r/20230912233214.1518551-11-memxor@gmail.comSigned-off-by: Alexei Starovoitov <ast@kernel.org>

kernel/bpf/helpers.c

@@ -22,6 +22,7 @@
 #include <linux/security.h>
 #include <linux/btf_ids.h>
 #include <linux/bpf_mem_alloc.h>
+#include <linux/kasan.h>
 
 #include "../../lib/kstrtox.h"
 
@@ -2483,6 +2484,11 @@ __bpf_kfunc void bpf_throw(u64 cookie)
 		WARN_ON_ONCE(!ctx.aux->exception_boundary);
 	WARN_ON_ONCE(!ctx.bp);
 	WARN_ON_ONCE(!ctx.cnt);
+	/* Prevent KASAN false positives for CONFIG_KASAN_STACK by unpoisoning
+	 * deeper stack depths than ctx.sp as we do not return from bpf_throw,
+	 * which skips compiler generated instrumentation to do the same.
+	 */
+	kasan_unpoison_task_stack_below((void *)ctx.sp);
 	ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp);
 }