riscv: Add support for the tagged address ABI

When pointer masking is enabled for userspace, the kernel can accept
tagged pointers as arguments to some system calls. Allow this by
untagging the pointers in access_ok() and the uaccess routines. The
uaccess routines must peform untagging in software because U-mode and
S-mode have entirely separate pointer masking configurations. In fact,
hardware may not even implement pointer masking for S-mode.

Since the number of tag bits is variable, untagged_addr_remote() needs
to know what PMLEN to use for the remote mm. Therefore, the pointer
masking mode must be the same for all threads sharing an mm. Enforce
this with a lock flag in the mm context, as x86 does for LAM. The flag
gets reset in init_new_context() during fork(), as the new mm is no
longer multithreaded.

Reviewed-by: Charlie Jenkins <[email protected]>
Tested-by: Charlie Jenkins <[email protected]>
Signed-off-by: Samuel Holland <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Palmer Dabbelt <[email protected]>

Author: SiFiveHolland

Documentation/arch/riscv/uabi.rst

@@ -80,3 +80,7 @@ number of mask/tag bits needed by the application. ``PR_PMLEN`` is interpreted
 as a lower bound; if the kernel is unable to satisfy the request, the
 ``PR_SET_TAGGED_ADDR_CTRL`` operation will fail. The actual number of tag bits
 is returned in ``PR_PMLEN`` by the ``PR_GET_TAGGED_ADDR_CTRL`` operation.
+
+Additionally, when pointer masking is enabled (``PR_PMLEN`` is greater than 0),
+a tagged address ABI is supported, with the same interface and behavior as
+documented for AArch64 (Documentation/arch/arm64/tagged-address-abi.rst).

arch/riscv/include/asm/mmu.h

@@ -25,9 +25,16 @@ typedef struct {
 #ifdef CONFIG_BINFMT_ELF_FDPIC
 	unsigned long exec_fdpic_loadmap;
 	unsigned long interp_fdpic_loadmap;
+#endif
+	unsigned long flags;
+#ifdef CONFIG_RISCV_ISA_SUPM
+	u8 pmlen;
 #endif
 } mm_context_t;
 
+/* Lock the pointer masking mode because this mm is multithreaded */
+#define MM_CONTEXT_LOCK_PMLEN	0
+
 #define cntx2asid(cntx)		((cntx) & SATP_ASID_MASK)
 #define cntx2version(cntx)	((cntx) & ~SATP_ASID_MASK)
 

arch/riscv/include/asm/mmu_context.h

@@ -20,6 +20,9 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 static inline void activate_mm(struct mm_struct *prev,
 			       struct mm_struct *next)
 {
+#ifdef CONFIG_RISCV_ISA_SUPM
+	next->context.pmlen = 0;
+#endif
 	switch_mm(prev, next, NULL);
 }
 
@@ -30,11 +33,21 @@ static inline int init_new_context(struct task_struct *tsk,
 #ifdef CONFIG_MMU
 	atomic_long_set(&mm->context.id, 0);
 #endif
+	if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM))
+		clear_bit(MM_CONTEXT_LOCK_PMLEN, &mm->context.flags);
 	return 0;
 }
 
 DECLARE_STATIC_KEY_FALSE(use_asid_allocator);
 
+#ifdef CONFIG_RISCV_ISA_SUPM
+#define mm_untag_mask mm_untag_mask
+static inline unsigned long mm_untag_mask(struct mm_struct *mm)
+{
+	return -1UL >> mm->context.pmlen;
+}
+#endif
+
 #include <asm-generic/mmu_context.h>
 
 #endif /* _ASM_RISCV_MMU_CONTEXT_H */

arch/riscv/include/asm/uaccess.h

@@ -9,8 +9,41 @@
 #define _ASM_RISCV_UACCESS_H
 
 #include <asm/asm-extable.h>
+#include <asm/cpufeature.h>
 #include <asm/pgtable.h>		/* for TASK_SIZE */
 
+#ifdef CONFIG_RISCV_ISA_SUPM
+static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, unsigned long addr)
+{
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) {
+		u8 pmlen = mm->context.pmlen;
+
+		/* Virtual addresses are sign-extended; physical addresses are zero-extended. */
+		if (IS_ENABLED(CONFIG_MMU))
+			return (long)(addr << pmlen) >> pmlen;
+		else
+			return (addr << pmlen) >> pmlen;
+	}
+
+	return addr;
+}
+
+#define untagged_addr(addr) ({							\
+	unsigned long __addr = (__force unsigned long)(addr);			\
+	(__force __typeof__(addr))__untagged_addr_remote(current->mm, __addr);	\
+})
+
+#define untagged_addr_remote(mm, addr) ({					\
+	unsigned long __addr = (__force unsigned long)(addr);			\
+	mmap_assert_locked(mm);							\
+	(__force __typeof__(addr))__untagged_addr_remote(mm, __addr);		\
+})
+
+#define access_ok(addr, size) likely(__access_ok(untagged_addr(addr), size))
+#else
+#define untagged_addr(addr) (addr)
+#endif
+
 /*
  * User space memory access functions
  */
@@ -130,7 +163,7 @@ do {								\
  */
 #define __get_user(x, ptr)					\
 ({								\
-	const __typeof__(*(ptr)) __user *__gu_ptr = (ptr);	\
+	const __typeof__(*(ptr)) __user *__gu_ptr = untagged_addr(ptr); \
 	long __gu_err = 0;					\
 								\
 	__chk_user_ptr(__gu_ptr);				\
@@ -246,7 +279,7 @@ do {								\
  */
 #define __put_user(x, ptr)					\
 ({								\
-	__typeof__(*(ptr)) __user *__gu_ptr = (ptr);		\
+	__typeof__(*(ptr)) __user *__gu_ptr = untagged_addr(ptr); \
 	__typeof__(*__gu_ptr) __val = (x);			\
 	long __pu_err = 0;					\
 								\
@@ -293,13 +326,13 @@ unsigned long __must_check __asm_copy_from_user(void *to,
 static inline unsigned long
 raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	return __asm_copy_from_user(to, from, n);
+	return __asm_copy_from_user(to, untagged_addr(from), n);
 }
 
 static inline unsigned long
 raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	return __asm_copy_to_user(to, from, n);
+	return __asm_copy_to_user(untagged_addr(to), from, n);
 }
 
 extern long strncpy_from_user(char *dest, const char __user *src, long count);
@@ -314,7 +347,7 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
 {
 	might_fault();
 	return access_ok(to, n) ?
-		__clear_user(to, n) : n;
+		__clear_user(untagged_addr(to), n) : n;
 }
 
 #define __get_kernel_nofault(dst, src, type, err_label)			\

arch/riscv/kernel/process.c

@@ -213,6 +213,10 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 
+	/* Ensure all threads in this mm have the same pointer masking mode. */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM) && p->mm && (clone_flags & CLONE_VM))
+		set_bit(MM_CONTEXT_LOCK_PMLEN, &p->mm->context.flags);
+
 	memset(&p->thread.s, 0, sizeof(p->thread.s));
 
 	/* p->thread holds context to be restored by __switch_to() */
@@ -258,10 +262,16 @@ enum {
 static bool have_user_pmlen_7;
 static bool have_user_pmlen_16;
 
+/*
+ * Control the relaxed ABI allowing tagged user addresses into the kernel.
+ */
+static unsigned int tagged_addr_disabled;
+
 long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
 {
-	unsigned long valid_mask = PR_PMLEN_MASK;
+	unsigned long valid_mask = PR_PMLEN_MASK | PR_TAGGED_ADDR_ENABLE;
 	struct thread_info *ti = task_thread_info(task);
+	struct mm_struct *mm = task->mm;
 	unsigned long pmm;
 	u8 pmlen;
 
@@ -276,16 +286,41 @@ long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
 	 * in case choosing a larger PMLEN has a performance impact.
 	 */
 	pmlen = FIELD_GET(PR_PMLEN_MASK, arg);
-	if (pmlen == PMLEN_0)
+	if (pmlen == PMLEN_0) {
 		pmm = ENVCFG_PMM_PMLEN_0;
-	else if (pmlen <= PMLEN_7 && have_user_pmlen_7)
+	} else if (pmlen <= PMLEN_7 && have_user_pmlen_7) {
+		pmlen = PMLEN_7;
 		pmm = ENVCFG_PMM_PMLEN_7;
-	else if (pmlen <= PMLEN_16 && have_user_pmlen_16)
+	} else if (pmlen <= PMLEN_16 && have_user_pmlen_16) {
+		pmlen = PMLEN_16;
 		pmm = ENVCFG_PMM_PMLEN_16;
-	else
+	} else {
 		return -EINVAL;
+	}
+
+	/*
+	 * Do not allow the enabling of the tagged address ABI if globally
+	 * disabled via sysctl abi.tagged_addr_disabled, if pointer masking
+	 * is disabled for userspace.
+	 */
+	if (arg & PR_TAGGED_ADDR_ENABLE && (tagged_addr_disabled || !pmlen))
+		return -EINVAL;
+
+	if (!(arg & PR_TAGGED_ADDR_ENABLE))
+		pmlen = PMLEN_0;
+
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	if (test_bit(MM_CONTEXT_LOCK_PMLEN, &mm->context.flags) && mm->context.pmlen != pmlen) {
+		mmap_write_unlock(mm);
+		return -EBUSY;
+	}
 
 	envcfg_update_bits(task, ENVCFG_PMM, pmm);
+	mm->context.pmlen = pmlen;
+
+	mmap_write_unlock(mm);
 
 	return 0;
 }
@@ -298,6 +333,10 @@ long get_tagged_addr_ctrl(struct task_struct *task)
 	if (is_compat_thread(ti))
 		return -EINVAL;
 
+	/*
+	 * The mm context's pmlen is set only when the tagged address ABI is
+	 * enabled, so the effective PMLEN must be extracted from envcfg.PMM.
+	 */
 	switch (task->thread.envcfg & ENVCFG_PMM) {
 	case ENVCFG_PMM_PMLEN_7:
 		ret = FIELD_PREP(PR_PMLEN_MASK, PMLEN_7);
@@ -307,6 +346,9 @@ long get_tagged_addr_ctrl(struct task_struct *task)
 		break;
 	}
 
+	if (task->mm->context.pmlen)
+		ret |= PR_TAGGED_ADDR_ENABLE;
+
 	return ret;
 }
 
@@ -316,6 +358,24 @@ static bool try_to_set_pmm(unsigned long value)
 	return (csr_read_clear(CSR_ENVCFG, ENVCFG_PMM) & ENVCFG_PMM) == value;
 }
 
+/*
+ * Global sysctl to disable the tagged user addresses support. This control
+ * only prevents the tagged address ABI enabling via prctl() and does not
+ * disable it for tasks that already opted in to the relaxed ABI.
+ */
+
+static struct ctl_table tagged_addr_sysctl_table[] = {
+	{
+		.procname	= "tagged_addr_disabled",
+		.mode		= 0644,
+		.data		= &tagged_addr_disabled,
+		.maxlen		= sizeof(int),
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+};
+
 static int __init tagged_addr_init(void)
 {
 	if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM))
@@ -329,6 +389,9 @@ static int __init tagged_addr_init(void)
 	have_user_pmlen_7 = try_to_set_pmm(ENVCFG_PMM_PMLEN_7);
 	have_user_pmlen_16 = try_to_set_pmm(ENVCFG_PMM_PMLEN_16);
 
+	if (!register_sysctl("abi", tagged_addr_sysctl_table))
+		return -EINVAL;
+
 	return 0;
 }
 core_initcall(tagged_addr_init);