BACKPORT: mm: untag user pointers passed to memory syscalls

(Upstream commit 057d3389108eda8a20c7f496f011846932680d88).

This patch is a part of a series that extends kernel ABI to allow to pass
tagged user pointers (with the top byte set to something else other than
0x00) as syscall arguments.

This patch allows tagged pointers to be passed to the following memory
syscalls: get_mempolicy, madvise, mbind, mincore, mlock, mlock2, mprotect,
mremap, msync, munlock, move_pages.

The mmap and mremap syscalls do not currently accept tagged addresses.
Architectures may interpret the tag as a background colour for the
corresponding vma.

Link: http://lkml.kernel.org/r/aaf0c0969d46b2feb9017f3e1b3ef3970b633d91.1563904656.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Khalid Aziz <khalid.aziz@oracle.com>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Eric Auger <eric.auger@redhat.com>
Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Cc: Jens Wiklander <jens.wiklander@linaro.org>
Cc: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Change-Id: I1a2d89eedb45e618e85ca515f4c9121460711efb
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Bug: 135692346

mm/madvise.c

@@ -798,6 +798,8 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	size_t len;
 	struct blk_plug plug;
 
+	start = untagged_addr(start);
+
 	if (!madvise_behavior_valid(behavior))
 		return error;
 

mm/mempolicy.c

@@ -1372,6 +1372,7 @@ SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
 	int err;
 	unsigned short mode_flags;
 
+	start = untagged_addr(start);
 	mode_flags = mode & MPOL_MODE_FLAGS;
 	mode &= ~MPOL_MODE_FLAGS;
 	if (mode >= MPOL_MAX)
@@ -1513,6 +1514,8 @@ SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
 	int uninitialized_var(pval);
 	nodemask_t nodes;
 
+	addr = untagged_addr(addr);
+
 	if (nmask != NULL && maxnode < nr_node_ids)
 		return -EINVAL;
 

mm/migrate.c

@@ -1651,7 +1651,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 			err = -EFAULT;
 			if (get_user(p, pages + j + chunk_start))
 				goto out_pm;
-			pm[j].addr = (unsigned long) p;
+			pm[j].addr = (unsigned long)untagged_addr(p);
 
 			if (get_user(node, nodes + j + chunk_start))
 				goto out_pm;

mm/mincore.c

@@ -249,6 +249,8 @@ SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
 	unsigned long pages;
 	unsigned char *tmp;
 
+	start = untagged_addr(start);
+
 	/* Check the start address: needs to be page-aligned.. */
 	if (start & ~PAGE_MASK)
 		return -EINVAL;

mm/mlock.c

@@ -667,6 +667,8 @@ static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t fla
 	unsigned long lock_limit;
 	int error = -ENOMEM;
 
+	start = untagged_addr(start);
+
 	if (!can_do_mlock())
 		return -EPERM;
 
@@ -730,6 +732,8 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
 {
 	int ret;
 
+	start = untagged_addr(start);
+
 	len = PAGE_ALIGN(len + (offset_in_page(start)));
 	start &= PAGE_MASK;
 

mm/mprotect.c

@@ -449,6 +449,8 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 	const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
 				(prot & PROT_READ);
 
+	start = untagged_addr(start);
+
 	prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
 	if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
 		return -EINVAL;

mm/mremap.c

@@ -529,6 +529,13 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	LIST_HEAD(uf_unmap_early);
 	LIST_HEAD(uf_unmap);
 
+	/*
+	 * Architectures may interpret the tag passed to mmap as a background
+	 * colour for the corresponding vma. For mremap we don't allow tagged
+	 * new_addr to preserve similar behaviour to mmap.
+	 */
+	addr = untagged_addr(addr);
+
 	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
 		return ret;
 

mm/msync.c

@@ -37,6 +37,8 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
 	int unmapped_error = 0;
 	int error = -EINVAL;
 
+	start = untagged_addr(start);
+
 	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
 		goto out;
 	if (offset_in_page(start))