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>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org,
        "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCHv10 07/15] x86/mm: Provide arch_prctl() interface for LAM
Date:   Tue, 18 Oct 2022 14:33:50 +0300
Message-Id: <20221018113358.7833-8-kirill.shutemov@linux.intel.com>
In-Reply-To: <20221018113358.7833-1-kirill.shutemov@linux.intel.com>
References: <20221018113358.7833-1-kirill.shutemov@linux.intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Add a couple 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>
Tested-by: Alexander Potapenko <glider@google.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/include/uapi/asm/prctl.h |  4 ++
 arch/x86/kernel/process_64.c      | 65 ++++++++++++++++++++++++++++++-
 2 files changed, 68 insertions(+), 1 deletion(-)

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_64.c b/arch/x86/kernel/process_64.c
index 6b3418bff326..a98536101447 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -743,6 +743,60 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr)
 }
 #endif
 
+static void enable_lam_func(void *mm)
+{
+	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+	unsigned long lam_mask;
+	unsigned long cr3;
+
+	if (loaded_mm != mm)
+		return;
+
+	lam_mask = READ_ONCE(loaded_mm->context.lam_cr3_mask);
+
+	/* Update CR3 to get LAM active on the CPU */
+	cr3 = __read_cr3();
+	cr3 &= ~(X86_CR3_LAM_U48 | X86_CR3_LAM_U57);
+	cr3 |= lam_mask;
+	write_cr3(cr3);
+	set_tlbstate_cr3_lam_mask(lam_mask);
+}
+
+#define LAM_U57_BITS 6
+
+static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
+{
+	int ret = 0;
+
+	if (!cpu_feature_enabled(X86_FEATURE_LAM))
+		return -ENODEV;
+
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	/* Already enabled? */
+	if (mm->context.lam_cr3_mask) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	if (!nr_bits) {
+		ret = -EINVAL;
+		goto out;
+	} else if (nr_bits <= LAM_U57_BITS) {
+		mm->context.lam_cr3_mask = X86_CR3_LAM_U57;
+		mm->context.untag_mask =  ~GENMASK(62, 57);
+	} else {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	on_each_cpu_mask(mm_cpumask(mm), enable_lam_func, mm, true);
+out:
+	mmap_write_unlock(mm);
+	return ret;
+}
+
 long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 {
 	int ret = 0;
@@ -830,7 +884,16 @@ 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
-
+	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);
 	default:
 		ret = -EINVAL;
 		break;
-- 
2.38.0