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, Andrey Ryabinin <aryabinin@virtuozzo.com>,
        Alexander Potapenko <glider@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>,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [RFCv2 07/10] x86/mm: Handle tagged memory accesses from kernel threads
Date:   Wed, 11 May 2022 05:27:48 +0300
Message-Id: <20220511022751.65540-9-kirill.shutemov@linux.intel.com>
In-Reply-To: <20220511022751.65540-1-kirill.shutemov@linux.intel.com>
References: <20220511022751.65540-1-kirill.shutemov@linux.intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

When a kernel thread performs memory access on behalf of a process (like
in async I/O, io_uring, etc.) it has to respect tagging setup of the
process as user addresses can include tags.

Normally, LAM setup is per-thread and recorded in thread features, but
for this use case kernel also tracks LAM setup per-mm. mm->context.lam
would record LAM that allows the most tag bits among the threads of
the mm.

The info used by switch_mm_irqs_off() to construct CR3 if the task is
kernel thread. Thread featrues of the kernel thread get updated
according to mm->context.lam. It allows untagged_addr() to work
correctly.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/include/asm/mmu.h |  1 +
 arch/x86/mm/tlb.c          | 28 ++++++++++++++++++++++++++++
 2 files changed, 29 insertions(+)

diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 5d7494631ea9..52f3749f14e8 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -40,6 +40,7 @@ typedef struct {
 
 #ifdef CONFIG_X86_64
 	unsigned short flags;
+	u8 lam;
 #endif
 
 	struct mutex lock;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index f9fe71d1f42c..b320556e1c22 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -185,6 +185,34 @@ static u8 gen_lam(struct task_struct *tsk, struct mm_struct *mm)
 	if (!tsk)
 		return LAM_NONE;
 
+	if (tsk->flags & PF_KTHREAD) {
+		/*
+		 * For kernel thread use the most permissive LAM
+		 * used by the mm. It's required to handle kernel thread
+		 * memory accesses on behalf of a process.
+		 *
+		 * Adjust thread flags accodringly, so untagged_addr() would
+		 * work correctly.
+		 */
+
+		tsk->thread.features &= ~(X86_THREAD_LAM_U48 |
+					  X86_THREAD_LAM_U57);
+
+		switch (mm->context.lam) {
+		case LAM_NONE:
+			return LAM_NONE;
+		case LAM_U57:
+			tsk->thread.features |= X86_THREAD_LAM_U57;
+			return LAM_U57;
+		case LAM_U48:
+			tsk->thread.features |= X86_THREAD_LAM_U48;
+			return LAM_U48;
+		default:
+			WARN_ON_ONCE(1);
+			return LAM_NONE;
+		}
+	}
+
 	if (tsk->thread.features & X86_THREAD_LAM_U57)
 		return LAM_U57;
 	if (tsk->thread.features & X86_THREAD_LAM_U48)
-- 
2.35.1