Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To:     Dave Hansen <dave.hansen@linux.intel.com>,
        Andy Lutomirski <luto@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>
Cc:     x86@kernel.org, Kostya Serebryany <kcc@google.com>,
        Andrey Ryabinin <ryabinin.a.a@gmail.com>,
        Andrey Konovalov <andreyknvl@gmail.com>,
        Alexander Potapenko <glider@google.com>,
        Taras Madan <tarasmadan@google.com>,
        Dmitry Vyukov <dvyukov@google.com>,
        "H . J . Lu" <hjl.tools@gmail.com>,
        Andi Kleen <ak@linux.intel.com>,
        Rick Edgecombe <rick.p.edgecombe@intel.com>,
        Bharata B Rao <bharata@amd.com>,
        Jacob Pan <jacob.jun.pan@linux.intel.com>,
        Ashok Raj <ashok.raj@intel.com>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCHv14 07/17] x86/mm: Provide arch_prctl() interface for LAM
Date:   Wed, 11 Jan 2023 15:37:26 +0300
Message-Id: <20230111123736.20025-8-kirill.shutemov@linux.intel.com>
In-Reply-To: <20230111123736.20025-1-kirill.shutemov@linux.intel.com>
References: <20230111123736.20025-1-kirill.shutemov@linux.intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Add a few of arch_prctl() handles:

 - ARCH_ENABLE_TAGGED_ADDR enabled LAM. The argument is required number
   of tag bits. It is rounded up to the nearest LAM mode that can
   provide it. For now only LAM_U57 is supported, with 6 tag bits.

 - ARCH_GET_UNTAG_MASK returns untag mask. It can indicates where tag
   bits located in the address.

 - ARCH_GET_MAX_TAG_BITS returns the maximum tag bits user can request.
   Zero if LAM is not supported.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/include/asm/mmu.h        |  2 ++
 arch/x86/include/uapi/asm/prctl.h |  4 +++
 arch/x86/kernel/process.c         |  3 ++
 arch/x86/kernel/process_64.c      | 55 ++++++++++++++++++++++++++++++-
 4 files changed, 63 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 9cac8c45a647..e80762e998ce 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -12,6 +12,8 @@
 #define MM_CONTEXT_UPROBE_IA32		0
 /* vsyscall page is accessible on this MM */
 #define MM_CONTEXT_HAS_VSYSCALL		1
+/* Do not allow changing LAM mode */
+#define MM_CONTEXT_LOCK_LAM		2
 
 /*
  * x86 has arch-specific MMU state beyond what lives in mm_struct.
diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h
index 500b96e71f18..a31e27b95b19 100644
--- a/arch/x86/include/uapi/asm/prctl.h
+++ b/arch/x86/include/uapi/asm/prctl.h
@@ -20,4 +20,8 @@
 #define ARCH_MAP_VDSO_32		0x2002
 #define ARCH_MAP_VDSO_64		0x2003
 
+#define ARCH_GET_UNTAG_MASK		0x4001
+#define ARCH_ENABLE_TAGGED_ADDR		0x4002
+#define ARCH_GET_MAX_TAG_BITS		0x4003
+
 #endif /* _ASM_X86_PRCTL_H */
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ef6bde1d40d8..cc0677f58f42 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -162,6 +162,9 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 
 	savesegment(es, p->thread.es);
 	savesegment(ds, p->thread.ds);
+
+	if (p->mm && (clone_flags & (CLONE_VM | CLONE_VFORK)) == CLONE_VM)
+		set_bit(MM_CONTEXT_LOCK_LAM, &p->mm->context.flags);
 #else
 	p->thread.sp0 = (unsigned long) (childregs + 1);
 	savesegment(gs, p->thread.gs);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 8b06034e8c70..88aae519c8f8 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -743,6 +743,48 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr)
 }
 #endif
 
+#ifdef CONFIG_ADDRESS_MASKING
+
+#define LAM_U57_BITS 6
+
+static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_LAM))
+		return -ENODEV;
+
+	/* PTRACE_ARCH_PRCTL */
+	if (current->mm != mm)
+		return -EINVAL;
+
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	if (test_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags)) {
+		mmap_write_unlock(mm);
+		return -EBUSY;
+	}
+
+	if (!nr_bits) {
+		mmap_write_unlock(mm);
+		return -EINVAL;
+	} else if (nr_bits <= LAM_U57_BITS) {
+		mm->context.lam_cr3_mask = X86_CR3_LAM_U57;
+		mm->context.untag_mask =  ~GENMASK(62, 57);
+	} else {
+		mmap_write_unlock(mm);
+		return -EINVAL;
+	}
+
+	write_cr3(__read_cr3() | mm->context.lam_cr3_mask);
+	set_tlbstate_lam_mode(mm);
+	set_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags);
+
+	mmap_write_unlock(mm);
+
+	return 0;
+}
+#endif
+
 long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 {
 	int ret = 0;
@@ -830,7 +872,18 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 	case ARCH_MAP_VDSO_64:
 		return prctl_map_vdso(&vdso_image_64, arg2);
 #endif
-
+#ifdef CONFIG_ADDRESS_MASKING
+	case ARCH_GET_UNTAG_MASK:
+		return put_user(task->mm->context.untag_mask,
+				(unsigned long __user *)arg2);
+	case ARCH_ENABLE_TAGGED_ADDR:
+		return prctl_enable_tagged_addr(task->mm, arg2);
+	case ARCH_GET_MAX_TAG_BITS:
+		if (!cpu_feature_enabled(X86_FEATURE_LAM))
+			return put_user(0, (unsigned long __user *)arg2);
+		else
+			return put_user(LAM_U57_BITS, (unsigned long __user *)arg2);
+#endif
 	default:
 		ret = -EINVAL;
 		break;
-- 
2.38.2