[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250821123656.935559566@infradead.org>
Date: Thu, 21 Aug 2025 14:28:25 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: jolsa@...nel.org,
oleg@...hat.com,
andrii@...nel.org,
mhiramat@...nel.org
Cc: linux-kernel@...r.kernel.org,
peterz@...radead.org,
alx@...nel.org,
eyal.birger@...il.com,
kees@...nel.org,
bpf@...r.kernel.org,
linux-trace-kernel@...r.kernel.org,
x86@...nel.org,
songliubraving@...com,
yhs@...com,
john.fastabend@...il.com,
haoluo@...gle.com,
rostedt@...dmis.org,
alan.maguire@...cle.com,
David.Laight@...LAB.COM,
thomas@...ch.de,
mingo@...nel.org,
rick.p.edgecombe@...el.com
Subject: [PATCH 3/6] uprobes/x86: Accept more NOP forms
Instead of only accepting the x86_64 nop5 chosen by the kernel, accept
any x86_64 NOP or NOPL instruction that is 5 bytes.
Notably, the x86_64 nop5 pattern is valid in 32bit apps and could get
compiler generated when build for i686 (which introduced NOPL). Since
the trampoline is x86_64 only, make sure to limit to x86_64 code.
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
---
arch/x86/kernel/uprobes.c | 37 ++++++++++++++++++++++++++++++++-----
1 file changed, 32 insertions(+), 5 deletions(-)
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -1157,10 +1157,37 @@ void arch_uprobe_optimize(struct arch_up
mmap_write_unlock(mm);
}
-static bool can_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
+static bool insn_is_nop(struct insn *insn)
{
- if (memcmp(&auprobe->insn, x86_nops[5], 5))
+ return insn->opcode.nbytes == 1 && insn->opcode.bytes[0] == 0x90;
+}
+
+static bool insn_is_nopl(struct insn *insn)
+{
+ if (insn->opcode.nbytes != 2)
+ return false;
+
+ if (insn->opcode.bytes[0] != 0x0f || insn->opcode.bytes[1] != 0x1f)
+ return false;
+
+ if (!insn->modrm.nbytes)
+ return false;
+
+ if (X86_MODRM_REG(insn->modrm.bytes[0]) != 0)
+ return false;
+
+ /* 0f 1f /0 - NOPL */
+ return true;
+}
+
+static bool can_optimize(struct insn *insn, unsigned long vaddr)
+{
+ if (!insn->x86_64 || insn->length != 5)
return false;
+
+ if (!insn_is_nop(insn) && !insn_is_nopl(insn))
+ return false;
+
/* We can't do cross page atomic writes yet. */
return PAGE_SIZE - (vaddr & ~PAGE_MASK) >= 5;
}
@@ -1177,7 +1204,7 @@ static void riprel_pre_xol(struct arch_u
static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
{
}
-static bool can_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
+static bool can_optimize(struct insn *insn, unsigned long vaddr)
{
return false;
}
@@ -1539,15 +1566,15 @@ static int push_setup_xol_ops(struct arc
*/
int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long addr)
{
- struct insn insn;
u8 fix_ip_or_call = UPROBE_FIX_IP;
+ struct insn insn;
int ret;
ret = uprobe_init_insn(auprobe, &insn, is_64bit_mm(mm));
if (ret)
return ret;
- if (can_optimize(auprobe, addr))
+ if (can_optimize(&insn, addr))
set_bit(ARCH_UPROBE_FLAG_CAN_OPTIMIZE, &auprobe->flags);
ret = branch_setup_xol_ops(auprobe, &insn);
Powered by blists - more mailing lists