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>,
        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: [PATCHv3 5/8] x86/uaccess: Provide untagged_addr() and remove tags before address check
Date:   Fri, 10 Jun 2022 17:35:24 +0300
Message-Id: <20220610143527.22974-6-kirill.shutemov@linux.intel.com>
In-Reply-To: <20220610143527.22974-1-kirill.shutemov@linux.intel.com>
References: <20220610143527.22974-1-kirill.shutemov@linux.intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

untagged_addr() is a helper used by the core-mm to strip tag bits and
get the address to the canonical shape. In only handles userspace
addresses. The untagging mask is stored in mmu_context and will be set
on enabling LAM for the process.

The tags must not be included into check whether it's okay to access the
userspace address.

Strip tags in access_ok().

get_user() and put_user() don't use access_ok(), but check access
against TASK_SIZE directly in assembly. Strip tags, before calling into
the assembly helper.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/include/asm/mmu.h         |  1 +
 arch/x86/include/asm/mmu_context.h | 11 ++++++++
 arch/x86/include/asm/uaccess.h     | 44 ++++++++++++++++++++++++++++--
 arch/x86/kernel/process.c          |  3 ++
 4 files changed, 56 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index d150e92163b6..59c617fc7c6f 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -41,6 +41,7 @@ typedef struct {
 #ifdef CONFIG_X86_64
 	unsigned short flags;
 	u64 lam_cr3_mask;
+	u64 untag_mask;
 #endif
 
 	struct mutex lock;
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index e6eac047c728..05821534aadc 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -100,6 +100,12 @@ static inline u64 mm_cr3_lam_mask(struct mm_struct *mm)
 static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm)
 {
 	mm->context.lam_cr3_mask = oldmm->context.lam_cr3_mask;
+	mm->context.untag_mask = oldmm->context.untag_mask;
+}
+
+static inline void mm_reset_untag_mask(struct mm_struct *mm)
+{
+	mm->context.untag_mask = -1UL;
 }
 
 #else
@@ -112,6 +118,10 @@ static inline u64 mm_cr3_lam_mask(struct mm_struct *mm)
 static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm)
 {
 }
+
+static inline void mm_reset_untag_mask(struct mm_struct *mm)
+{
+}
 #endif
 
 #define enter_lazy_tlb enter_lazy_tlb
@@ -138,6 +148,7 @@ static inline int init_new_context(struct task_struct *tsk,
 		mm->context.execute_only_pkey = -1;
 	}
 #endif
+	mm_reset_untag_mask(mm);
 	init_new_context_ldt(mm);
 	return 0;
 }
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 35f222aa66bf..ca754521a4db 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -6,6 +6,7 @@
  */
 #include <linux/compiler.h>
 #include <linux/kasan-checks.h>
+#include <linux/mm_types.h>
 #include <linux/string.h>
 #include <asm/asm.h>
 #include <asm/page.h>
@@ -20,6 +21,32 @@ static inline bool pagefault_disabled(void);
 # define WARN_ON_IN_IRQ()
 #endif
 
+#ifdef CONFIG_X86_64
+/*
+ * Mask out tag bits from the address.
+ *
+ * Magic with the 'sign' allows to untag userspace pointer without any branches
+ * while leaving kernel addresses intact.
+ */
+#define untagged_addr(mm, addr)	({					\
+	u64 __addr = (__force u64)(addr);				\
+	s64 sign = (s64)__addr >> 63;					\
+	__addr ^= sign;							\
+	__addr &= (mm)->context.untag_mask;				\
+	__addr ^= sign;							\
+	(__force __typeof__(addr))__addr;				\
+})
+
+#define untagged_ptr(mm, ptr)	({					\
+	u64 __ptrval = (__force u64)(ptr);				\
+	__ptrval = untagged_addr(mm, __ptrval);				\
+	(__force __typeof__(*(ptr)) *)__ptrval;				\
+})
+#else
+#define untagged_addr(mm, addr)	(addr)
+#define untagged_ptr(mm, ptr)	(ptr)
+#endif
+
 /**
  * access_ok - Checks if a user space pointer is valid
  * @addr: User space pointer to start of block to check
@@ -40,7 +67,7 @@ static inline bool pagefault_disabled(void);
 #define access_ok(addr, size)					\
 ({									\
 	WARN_ON_IN_IRQ();						\
-	likely(__access_ok(addr, size));				\
+	likely(__access_ok(untagged_addr(current->mm, addr), size));	\
 })
 
 #include <asm-generic/access_ok.h>
@@ -125,7 +152,13 @@ extern int __get_user_bad(void);
  * Return: zero on success, or -EFAULT on error.
  * On error, the variable @x is set to zero.
  */
-#define get_user(x,ptr) ({ might_fault(); do_get_user_call(get_user,x,ptr); })
+#define get_user(x,ptr)							\
+({									\
+	__typeof__(*(ptr)) __user *__ptr_clean;				\
+	__ptr_clean = untagged_ptr(current->mm, ptr);			\
+	might_fault();							\
+	do_get_user_call(get_user,x,__ptr_clean);			\
+})
 
 /**
  * __get_user - Get a simple variable from user space, with less checking.
@@ -222,7 +255,12 @@ extern void __put_user_nocheck_8(void);
  *
  * Return: zero on success, or -EFAULT on error.
  */
-#define put_user(x, ptr) ({ might_fault(); do_put_user_call(put_user,x,ptr); })
+#define put_user(x, ptr) ({						\
+	__typeof__(*(ptr)) __user *__ptr_clean;				\
+	__ptr_clean = untagged_ptr(current->mm, ptr);			\
+	might_fault();							\
+	do_put_user_call(put_user,x,__ptr_clean);			\
+})
 
 /**
  * __put_user - Write a simple value into user space, with less checking.
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9b2772b7e1f3..18b2bfdf7b9b 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -47,6 +47,7 @@
 #include <asm/frame.h>
 #include <asm/unwind.h>
 #include <asm/tdx.h>
+#include <asm/mmu_context.h>
 
 #include "process.h"
 
@@ -367,6 +368,8 @@ void arch_setup_new_exec(void)
 		task_clear_spec_ssb_noexec(current);
 		speculation_ctrl_update(read_thread_flags());
 	}
+
+	mm_reset_untag_mask(current->mm);
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
-- 
2.35.1