mm: untag user pointers passed to memory syscalls

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>

8 files changed, 23 insertions, 1 deletions

diff --git a/mm/madvise.c b/mm/madvise.c
index 68ab988ad433..1f8a6fdc6878 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -784,6 +784,8 @@ 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;
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 464406e8da91..de27d08b1ff8 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1405,6 +1405,7 @@ static long kernel_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)
@@ -1558,6 +1559,8 @@ static int kernel_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;
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 73d476d690b1..4fe45d1428c8 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1612,7 +1612,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 			goto out_flush;
 		if (get_user(node, nodes + i))
 			goto out_flush;
-		addr = (unsigned long)p;
+		addr = (unsigned long)untagged_addr(p);
 
 		err = -ENODEV;
 		if (node < 0 || node >= MAX_NUMNODES)
diff --git a/mm/mincore.c b/mm/mincore.c
index f9a9dbe8cd33..49b6fa2f6aa1 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -256,6 +256,8 @@ 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;
diff --git a/mm/mlock.c b/mm/mlock.c
index a90099da4fb4..a72c1eeded77 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -674,6 +674,8 @@ 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;
 
@@ -735,6 +737,8 @@ 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;
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 675e5d34a507..7967825f6d33 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -459,6 +459,8 @@ 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;
diff --git a/mm/mremap.c b/mm/mremap.c
index fc241d23cd97..64c9a3b8be0a 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -606,6 +606,13 @@ 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;
 
diff --git a/mm/msync.c b/mm/msync.c
index ef30a429623a..c3bd3e75f687 100644
--- a/mm/msync.c
+++ b/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))