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: [PATCHv13 07/16] x86/mm: Reduce untagged_addr() overhead until the first LAM user
Date:   Tue, 27 Dec 2022 06:08:20 +0300
Message-Id: <20221227030829.12508-8-kirill.shutemov@linux.intel.com>
In-Reply-To: <20221227030829.12508-1-kirill.shutemov@linux.intel.com>
References: <20221227030829.12508-1-kirill.shutemov@linux.intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Use static key to reduce untagged_addr() overhead.

The key only gets enabled when the first process enables LAM.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/include/asm/uaccess.h | 9 +++++++--
 arch/x86/kernel/process_64.c   | 4 ++++
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index cbb463e9344f..1d931c7f6741 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -23,6 +23,8 @@ static inline bool pagefault_disabled(void);
 #endif
 
 #ifdef CONFIG_X86_64
+DECLARE_STATIC_KEY_FALSE(tagged_addr_key);
+
 /*
  * Mask out tag bits from the address.
  *
@@ -31,8 +33,11 @@ static inline bool pagefault_disabled(void);
  */
 #define __untagged_addr(mm, addr)	({				\
 	u64 __addr = (__force u64)(addr);				\
-	s64 sign = (s64)__addr >> 63;					\
-	__addr &= READ_ONCE((mm)->context.untag_mask) | sign;		\
+	if (static_branch_likely(&tagged_addr_key)) {			\
+		s64 sign = (s64)__addr >> 63;				\
+		u64 mask = READ_ONCE((mm)->context.untag_mask);		\
+		__addr &= mask | sign;					\
+	}								\
 	(__force __typeof__(addr))__addr;				\
 })
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index fef127ed79b6..09e7f3d3fb5c 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -743,6 +743,9 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr)
 }
 #endif
 
+DEFINE_STATIC_KEY_FALSE(tagged_addr_key);
+EXPORT_SYMBOL_GPL(tagged_addr_key);
+
 #define LAM_U57_BITS 6
 
 static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
@@ -773,6 +776,7 @@ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
 
 	mmap_write_unlock(mm);
 
+	static_branch_enable(&tagged_addr_key);
 	return 0;
 }
 
-- 
2.38.2