mm: Introduce untagged_addr_remote()

untagged_addr() removes tags/metadata from the address and brings it to
the canonical form. The helper is implemented on arm64 and sparc. Both of
them do untagging based on global rules.

However, Linear Address Masking (LAM) on x86 introduces per-process
settings for untagging. As a result, untagged_addr() is now only
suitable for untagging addresses for the current proccess.

The new helper untagged_addr_remote() has to be used when the address
targets remote process. It requires the mmap lock for target mm to be
taken.

Signed-off-by: Kirill A. Shutemov <[e-mail]>
Signed-off-by: Dave Hansen <[e-mail]>
Acked-by: Peter Zijlstra (Intel) <[e-mail]>
Tested-by: Alexander Potapenko <[e-mail]>
Link: https://lore.kernel.org/all/20230312112612.31869-6-kirill.shutemov%40linux.intel.com

arch/sparc/include/asm/uaccess_64.h

···
 
 #include <linux/compiler.h>
 #include <linux/string.h>
+#include <linux/mm_types.h>
 #include <asm/asi.h>
 #include <asm/spitfire.h>
+#include <asm/pgtable.h>
 
 #include <asm/processor.h>
 #include <asm-generic/access_ok.h>

drivers/vfio/vfio_iommu_type1.c

···
 		goto done;
 	}
 
-	vaddr = untagged_addr(vaddr);
+	vaddr = untagged_addr_remote(mm, vaddr);
 
 retry:
 	vma = vma_lookup(mm, vaddr);

fs/proc/task_mmu.c

···
 
 	/* watch out for wraparound */
 	start_vaddr = end_vaddr;
-	if (svpfn <= (ULONG_MAX >> PAGE_SHIFT))
-		start_vaddr = untagged_addr(svpfn << PAGE_SHIFT);
+	if (svpfn <= (ULONG_MAX >> PAGE_SHIFT)) {
+		ret = mmap_read_lock_killable(mm);
+		if (ret)
+			goto out_free;
+		start_vaddr = untagged_addr_remote(mm, svpfn << PAGE_SHIFT);
+		mmap_read_unlock(mm);
+	}
 
 	/* Ensure the address is inside the task */
 	if (start_vaddr > mm->task_size)

include/linux/mm.h

···
 #include <asm/page.h>
 #include <asm/processor.h>
 
-/*
- * Architectures that support memory tagging (assigning tags to memory regions,
- * embedding these tags into addresses that point to these memory regions, and
- * checking that the memory and the pointer tags match on memory accesses)
- * redefine this macro to strip tags from pointers.
- * It's defined as noop for architectures that don't support memory tagging.
- */
-#ifndef untagged_addr
-#define untagged_addr(addr) (addr)
-#endif
-
 #ifndef __pa_symbol
 #define __pa_symbol(x)  __pa(RELOC_HIDE((unsigned long)(x), 0))
 #endif

include/linux/uaccess.h

···
 #include <asm/uaccess.h>
 
 /*
+ * Architectures that support memory tagging (assigning tags to memory regions,
+ * embedding these tags into addresses that point to these memory regions, and
+ * checking that the memory and the pointer tags match on memory accesses)
+ * redefine this macro to strip tags from pointers.
+ *
+ * Passing down mm_struct allows to define untagging rules on per-process
+ * basis.
+ *
+ * It's defined as noop for architectures that don't support memory tagging.
+ */
+#ifndef untagged_addr
+#define untagged_addr(addr) (addr)
+#endif
+
+#ifndef untagged_addr_remote
+#define untagged_addr_remote(mm, addr)	({		\
+	mmap_assert_locked(mm);				\
+	untagged_addr(addr);				\
+})
+#endif
+
+/*
  * Architectures should provide two primitives (raw_copy_{to,from}_user())
  * and get rid of their private instances of copy_{to,from}_user() and
  * __copy_{to,from}_user{,_inatomic}().

mm/gup.c

···
 	if (!nr_pages)
 		return 0;
 
-	start = untagged_addr(start);
+	start = untagged_addr_remote(mm, start);
 
 	VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN)));
 
···
 	struct vm_area_struct *vma;
 	vm_fault_t ret;
 
-	address = untagged_addr(address);
+	address = untagged_addr_remote(mm, address);
 
 	if (unlocked)
 		fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

mm/madvise.c

···
 	size_t len;
 	struct blk_plug plug;
 
-	start = untagged_addr(start);
-
 	if (!madvise_behavior_valid(behavior))
 		return -EINVAL;
 
···
 	} else {
 		mmap_read_lock(mm);
 	}
+
+	start = untagged_addr_remote(mm, start);
+	end = start + len;
 
 	blk_start_plug(&plug);
 	error = madvise_walk_vmas(mm, start, end, behavior,

mm/migrate.c

···
  *         target node
  *     1 - when it has been queued
  */
-static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
+static int add_page_for_migration(struct mm_struct *mm, const void __user *p,
 		int node, struct list_head *pagelist, bool migrate_all)
 {
 	struct vm_area_struct *vma;
+	unsigned long addr;
 	struct page *page;
 	int err;
 	bool isolated;
 
 	mmap_read_lock(mm);
+	addr = (unsigned long)untagged_addr_remote(mm, p);
+
 	err = -EFAULT;
 	vma = vma_lookup(mm, addr);
 	if (!vma || !vma_migratable(vma))
···
 
 	for (i = start = 0; i < nr_pages; i++) {
 		const void __user *p;
-		unsigned long addr;
 		int node;
 
 		err = -EFAULT;
···
 			goto out_flush;
 		if (get_user(node, nodes + i))
 			goto out_flush;
-		addr = (unsigned long)untagged_addr(p);
 
 		err = -ENODEV;
 		if (node < 0 || node >= MAX_NUMNODES)
···
 		 * Errors in the page lookup or isolation are not fatal and we simply
 		 * report them via status
 		 */
-		err = add_page_for_migration(mm, addr, current_node,
-				&pagelist, flags & MPOL_MF_MOVE_ALL);
+		err = add_page_for_migration(mm, p, current_node, &pagelist,
+					     flags & MPOL_MF_MOVE_ALL);
 
 		if (err > 0) {
 			/* The page is successfully queued for migration */