public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Jiri Olsa <jolsa@kernel.org>
To: Oleg Nesterov <oleg@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Andrii Nakryiko <andrii@kernel.org>
Cc: bpf@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-trace-kernel@vger.kernel.org, x86@kernel.org,
	"Song Liu" <songliubraving@fb.com>, "Yonghong Song" <yhs@fb.com>,
	"John Fastabend" <john.fastabend@gmail.com>,
	"Hao Luo" <haoluo@google.com>,
	"Steven Rostedt" <rostedt@goodmis.org>,
	"Masami Hiramatsu" <mhiramat@kernel.org>,
	"Alan Maguire" <alan.maguire@oracle.com>,
	"David Laight" <David.Laight@ACULAB.COM>,
	"Thomas Weißschuh" <thomas@t-8ch.de>
Subject: [PATCH RFCv3 08/23] uprobes/x86: Add uprobe syscall to speed up uprobe
Date: Thu, 20 Mar 2025 12:41:43 +0100	[thread overview]
Message-ID: <20250320114200.14377-9-jolsa@kernel.org> (raw)
In-Reply-To: <20250320114200.14377-1-jolsa@kernel.org>

Adding new uprobe syscall that calls uprobe handlers for given
'breakpoint' address.

The idea is that the 'breakpoint' address calls the user space
trampoline which executes the uprobe syscall.

The syscall handler reads the return address of the initial call
to retrieve the original 'breakpoint' address. With this address
we find the related uprobe object and call its consumers.

Adding the arch_uprobe_trampoline_mapping function that provides
uprobe trampoline mapping. This mapping is backed with one global
page initialized at __init time and shared by the all the mapping
instances.

We do not allow to execute uprobe syscall if the caller is not
from uprobe trampoline mapping.

The uprobe syscall ensures the consumer (bpf program) sees registers
values in the state before the trampoline was called.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 arch/x86/entry/syscalls/syscall_64.tbl |   1 +
 arch/x86/kernel/uprobes.c              | 134 +++++++++++++++++++++++++
 include/linux/syscalls.h               |   2 +
 include/linux/uprobes.h                |   1 +
 kernel/events/uprobes.c                |  22 ++++
 kernel/sys_ni.c                        |   1 +
 6 files changed, 161 insertions(+)

diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 5eb708bff1c7..88e388c7675b 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -345,6 +345,7 @@
 333	common	io_pgetevents		sys_io_pgetevents
 334	common	rseq			sys_rseq
 335	common	uretprobe		sys_uretprobe
+336	common	uprobe			sys_uprobe
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
 424	common	pidfd_send_signal	sys_pidfd_send_signal
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 39521f1c4185..b11dcd47edaa 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -429,6 +429,140 @@ SYSCALL_DEFINE0(uretprobe)
 	return -1;
 }
 
+static int tramp_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma)
+{
+	return -EPERM;
+}
+
+static struct page *tramp_mapping_pages[2] __ro_after_init;
+
+static struct vm_special_mapping tramp_mapping = {
+	.name   = "[uprobes-trampoline]",
+	.mremap = tramp_mremap,
+	.pages  = tramp_mapping_pages,
+};
+
+static bool __in_uprobe_trampoline(unsigned long ip)
+{
+	struct vm_area_struct *vma = vma_lookup(current->mm, ip);
+
+	return vma && vma_is_special_mapping(vma, &tramp_mapping);
+}
+
+static bool in_uprobe_trampoline(unsigned long ip)
+{
+	struct mm_struct *mm = current->mm;
+	bool found, retry = true;
+	unsigned int seq;
+
+	rcu_read_lock();
+	if (mmap_lock_speculate_try_begin(mm, &seq)) {
+		found = __in_uprobe_trampoline(ip);
+		retry = mmap_lock_speculate_retry(mm, seq);
+	}
+	rcu_read_unlock();
+
+	if (retry) {
+		mmap_read_lock(mm);
+		found = __in_uprobe_trampoline(ip);
+		mmap_read_unlock(mm);
+	}
+	return found;
+}
+
+SYSCALL_DEFINE0(uprobe)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+	unsigned long ip, sp, ax_r11_cx_ip[4];
+	int err;
+
+	/* Allow execution only from uprobe trampolines. */
+	if (!in_uprobe_trampoline(regs->ip))
+		goto sigill;
+
+	err = copy_from_user(ax_r11_cx_ip, (void __user *)regs->sp, sizeof(ax_r11_cx_ip));
+	if (err)
+		goto sigill;
+
+	ip = regs->ip;
+
+	/*
+	 * expose the "right" values of ax/r11/cx/ip/sp to uprobe_consumer/s, plus:
+	 * - adjust ip to the probe address, call saved next instruction address
+	 * - adjust sp to the probe's stack frame (check trampoline code)
+	 */
+	regs->ax  = ax_r11_cx_ip[0];
+	regs->r11 = ax_r11_cx_ip[1];
+	regs->cx  = ax_r11_cx_ip[2];
+	regs->ip  = ax_r11_cx_ip[3] - 5;
+	regs->sp += sizeof(ax_r11_cx_ip);
+	regs->orig_ax = -1;
+
+	sp = regs->sp;
+
+	handle_syscall_uprobe(regs, regs->ip);
+
+	/*
+	 * Some of the uprobe consumers has changed sp, we can do nothing,
+	 * just return via iret.
+	 */
+	if (regs->sp != sp)
+		return regs->ax;
+
+	regs->sp -= sizeof(ax_r11_cx_ip);
+
+	/* for the case uprobe_consumer has changed ax/r11/cx */
+	ax_r11_cx_ip[0] = regs->ax;
+	ax_r11_cx_ip[1] = regs->r11;
+	ax_r11_cx_ip[2] = regs->cx;
+
+	/* keep return address unless we are instructed otherwise */
+	if (ax_r11_cx_ip[3] - 5 != regs->ip)
+		ax_r11_cx_ip[3] = regs->ip;
+
+	regs->ip = ip;
+
+	err = copy_to_user((void __user *)regs->sp, ax_r11_cx_ip, sizeof(ax_r11_cx_ip));
+	if (err)
+		goto sigill;
+
+	/* ensure sysret, see do_syscall_64() */
+	regs->r11 = regs->flags;
+	regs->cx  = regs->ip;
+	return 0;
+
+sigill:
+	force_sig(SIGILL);
+	return -1;
+}
+
+asm (
+	".pushsection .rodata\n"
+	".balign " __stringify(PAGE_SIZE) "\n"
+	"uprobe_trampoline_entry:\n"
+	"push %rcx\n"
+	"push %r11\n"
+	"push %rax\n"
+	"movq $" __stringify(__NR_uprobe) ", %rax\n"
+	"syscall\n"
+	"pop %rax\n"
+	"pop %r11\n"
+	"pop %rcx\n"
+	"ret\n"
+	".balign " __stringify(PAGE_SIZE) "\n"
+	".popsection\n"
+);
+
+extern u8 uprobe_trampoline_entry[];
+
+static int __init arch_uprobes_init(void)
+{
+	tramp_mapping_pages[0] = virt_to_page(uprobe_trampoline_entry);
+	return 0;
+}
+
+late_initcall(arch_uprobes_init);
+
 /*
  * If arch_uprobe->insn doesn't use rip-relative addressing, return
  * immediately.  Otherwise, rewrite the instruction so that it accesses
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index c6333204d451..002f4e1debe5 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -994,6 +994,8 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on);
 
 asmlinkage long sys_uretprobe(void);
 
+asmlinkage long sys_uprobe(void);
+
 /* pciconfig: alpha, arm, arm64, ia64, sparc */
 asmlinkage long sys_pciconfig_read(unsigned long bus, unsigned long dfn,
 				unsigned long off, unsigned long len,
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 1b6a4e2b5464..4a2b950beefd 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -232,6 +232,7 @@ extern void uprobe_handle_trampoline(struct pt_regs *regs);
 extern void *arch_uretprobe_trampoline(unsigned long *psize);
 extern unsigned long uprobe_get_trampoline_vaddr(void);
 extern void uprobe_copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len);
+extern void handle_syscall_uprobe(struct pt_regs *regs, unsigned long bp_vaddr);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index bd4bc62f80d7..4de04075576c 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -2742,6 +2742,28 @@ static void handle_swbp(struct pt_regs *regs)
 	rcu_read_unlock_trace();
 }
 
+void handle_syscall_uprobe(struct pt_regs *regs, unsigned long bp_vaddr)
+{
+	struct uprobe *uprobe;
+	int is_swbp;
+
+	rcu_read_lock_trace();
+	uprobe = find_active_uprobe_rcu(bp_vaddr, &is_swbp);
+	if (!uprobe)
+		goto unlock;
+
+	if (!get_utask())
+		goto unlock;
+
+	if (arch_uprobe_ignore(&uprobe->arch, regs))
+		goto unlock;
+
+	handler_chain(uprobe, regs);
+
+ unlock:
+	rcu_read_unlock_trace();
+}
+
 /*
  * Perform required fix-ups and disable singlestep.
  * Allow pending signals to take effect.
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index c00a86931f8c..bf5d05c635ff 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -392,3 +392,4 @@ COND_SYSCALL(setuid16);
 COND_SYSCALL(rseq);
 
 COND_SYSCALL(uretprobe);
+COND_SYSCALL(uprobe);
-- 
2.49.0


  parent reply	other threads:[~2025-03-20 11:43 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-03-20 11:41 [PATCH RFCv3 00/23] uprobes: Add support to optimize usdt probes on x86_64 Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 01/23] uprobes: Rename arch_uretprobe_trampoline function Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 02/23] uprobes: Make copy_from_page global Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 03/23] uprobes: Move ref_ctr_offset update out of uprobe_write_opcode Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 04/23] uprobes: Add uprobe_write function Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 05/23] uprobes: Add nbytes argument to uprobe_write_opcode Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 06/23] uprobes: Add orig argument to uprobe_write and uprobe_write_opcode Jiri Olsa
2025-04-04 20:33   ` Andrii Nakryiko
2025-04-07 11:13     ` Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 07/23] uprobes: Remove breakpoint in unapply_uprobe under mmap_write_lock Jiri Olsa
2025-03-20 11:41 ` Jiri Olsa [this message]
2025-04-04 20:33   ` [PATCH RFCv3 08/23] uprobes/x86: Add uprobe syscall to speed up uprobe Andrii Nakryiko
2025-04-07 10:58     ` Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 09/23] uprobes/x86: Add mapping for optimized uprobe trampolines Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 10/23] uprobes/x86: Add support to emulate nop5 instruction Jiri Olsa
2025-04-04 20:33   ` Andrii Nakryiko
2025-04-07 11:07     ` Jiri Olsa
2025-04-08 20:21       ` Jiri Olsa
2025-04-09 18:19         ` Andrii Nakryiko
2025-04-11 12:18           ` Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 11/23] uprobes/x86: Add support to optimize uprobes Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 12/23] selftests/bpf: Use 5-byte nop for x86 usdt probes Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 13/23] selftests/bpf: Reorg the uprobe_syscall test function Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 14/23] selftests/bpf: Rename uprobe_syscall_executed prog to test_uretprobe_multi Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 15/23] selftests/bpf: Add uprobe/usdt syscall tests Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 16/23] selftests/bpf: Add hit/attach/detach race optimized uprobe test Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 17/23] selftests/bpf: Add uprobe syscall sigill signal test Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 18/23] selftests/bpf: Add optimized usdt variant for basic usdt test Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 19/23] selftests/bpf: Add uprobe_regs_equal test Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 20/23] selftests/bpf: Change test_uretprobe_regs_change for uprobe and uretprobe Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 21/23] selftests/bpf: Add 5-byte nop uprobe trigger bench Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 22/23] seccomp: passthrough uprobe systemcall without filtering Jiri Olsa
2025-03-20 11:41 ` [PATCH RFCv3 23/23] selftests/seccomp: validate uprobe syscall passes through seccomp Jiri Olsa
2025-03-20 12:23 ` [PATCH RFCv3 00/23] uprobes: Add support to optimize usdt probes on x86_64 Oleg Nesterov
2025-03-20 13:51   ` Jiri Olsa
2025-04-04 20:36 ` Andrii Nakryiko
2025-04-07 11:17   ` Jiri Olsa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250320114200.14377-9-jolsa@kernel.org \
    --to=jolsa@kernel.org \
    --cc=David.Laight@ACULAB.COM \
    --cc=alan.maguire@oracle.com \
    --cc=andrii@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=haoluo@google.com \
    --cc=john.fastabend@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-trace-kernel@vger.kernel.org \
    --cc=mhiramat@kernel.org \
    --cc=oleg@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=songliubraving@fb.com \
    --cc=thomas@t-8ch.de \
    --cc=x86@kernel.org \
    --cc=yhs@fb.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox