summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorDave Hansen <dave.hansen@linux.intel.com>2016-07-29 09:30:12 -0700
committerThomas Gleixner <tglx@linutronix.de>2016-09-09 13:02:26 +0200
commit7d06d9c9bd813fc956b9c7bffc1b9724009983eb (patch)
treeef8572b3d79e694cbd30ea6971dc64db93919ac4 /mm
parente8c6226d483cb28f55cab718065ea1b7226d40e8 (diff)
downloadlinux-7d06d9c9bd813fc956b9c7bffc1b9724009983eb.tar.gz
linux-7d06d9c9bd813fc956b9c7bffc1b9724009983eb.tar.bz2
linux-7d06d9c9bd813fc956b9c7bffc1b9724009983eb.zip
mm: Implement new pkey_mprotect() system call
pkey_mprotect() is just like mprotect, except it also takes a protection key as an argument. On systems that do not support protection keys, it still works, but requires that key=0. Otherwise it does exactly what mprotect does. I expect it to get used like this, if you want to guarantee that any mapping you create can *never* be accessed without the right protection keys set up. int real_prot = PROT_READ|PROT_WRITE; pkey = pkey_alloc(0, PKEY_DENY_ACCESS); ptr = mmap(NULL, PAGE_SIZE, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); ret = pkey_mprotect(ptr, PAGE_SIZE, real_prot, pkey); This way, there is *no* window where the mapping is accessible since it was always either PROT_NONE or had a protection key set that denied all access. We settled on 'unsigned long' for the type of the key here. We only need 4 bits on x86 today, but I figured that other architectures might need some more space. Semantically, we have a bit of a problem if we combine this syscall with our previously-introduced execute-only support: What do we do when we mix execute-only pkey use with pkey_mprotect() use? For instance: pkey_mprotect(ptr, PAGE_SIZE, PROT_WRITE, 6); // set pkey=6 mprotect(ptr, PAGE_SIZE, PROT_EXEC); // set pkey=X_ONLY_PKEY? mprotect(ptr, PAGE_SIZE, PROT_WRITE); // is pkey=6 again? To solve that, we make the plain-mprotect()-initiated execute-only support only apply to VMAs that have the default protection key (0) set on them. Proposed semantics: 1. protection key 0 is special and represents the default, "unassigned" protection key. It is always allocated. 2. mprotect() never affects a mapping's pkey_mprotect()-assigned protection key. A protection key of 0 (even if set explicitly) represents an unassigned protection key. 2a. mprotect(PROT_EXEC) on a mapping with an assigned protection key may or may not result in a mapping with execute-only properties. pkey_mprotect() plus pkey_set() on all threads should be used to _guarantee_ execute-only semantics if this is not a strong enough semantic. 3. mprotect(PROT_EXEC) may result in an "execute-only" mapping. The kernel will internally attempt to allocate and dedicate a protection key for the purpose of execute-only mappings. This may not be possible in cases where there are no free protection keys available. It can also happen, of course, in situations where there is no hardware support for protection keys. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Acked-by: Mel Gorman <mgorman@techsingularity.net> Cc: linux-arch@vger.kernel.org Cc: Dave Hansen <dave@sr71.net> Cc: arnd@arndb.de Cc: linux-api@vger.kernel.org Cc: linux-mm@kvack.org Cc: luto@kernel.org Cc: akpm@linux-foundation.org Cc: torvalds@linux-foundation.org Link: http://lkml.kernel.org/r/20160729163012.3DDD36C4@viggo.jf.intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Diffstat (limited to 'mm')
-rw-r--r--mm/mprotect.c30
1 files changed, 26 insertions, 4 deletions
diff --git a/mm/mprotect.c b/mm/mprotect.c
index a4830f0325fe..dd3f40a2935f 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -352,8 +352,11 @@ fail:
return error;
}
-SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
- unsigned long, prot)
+/*
+ * pkey==-1 when doing a legacy mprotect()
+ */
+static int do_mprotect_pkey(unsigned long start, size_t len,
+ unsigned long prot, int pkey)
{
unsigned long nstart, end, tmp, reqprot;
struct vm_area_struct *vma, *prev;
@@ -361,6 +364,12 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP);
const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
(prot & PROT_READ);
+ /*
+ * A temporary safety check since we are not validating
+ * the pkey before we introduce the allocation code.
+ */
+ if (pkey != -1)
+ return -EINVAL;
prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
@@ -409,7 +418,7 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
for (nstart = start ; ; ) {
unsigned long newflags;
- int pkey = arch_override_mprotect_pkey(vma, prot, -1);
+ int new_vma_pkey;
/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
@@ -417,7 +426,8 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
if (rier && (vma->vm_flags & VM_MAYEXEC))
prot |= PROT_EXEC;
- newflags = calc_vm_prot_bits(prot, pkey);
+ new_vma_pkey = arch_override_mprotect_pkey(vma, prot, pkey);
+ newflags = calc_vm_prot_bits(prot, new_vma_pkey);
newflags |= (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
/* newflags >> 4 shift VM_MAY% in place of VM_% */
@@ -454,3 +464,15 @@ out:
up_write(&current->mm->mmap_sem);
return error;
}
+
+SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
+ unsigned long, prot)
+{
+ return do_mprotect_pkey(start, len, prot, -1);
+}
+
+SYSCALL_DEFINE4(pkey_mprotect, unsigned long, start, size_t, len,
+ unsigned long, prot, int, pkey)
+{
+ return do_mprotect_pkey(start, len, prot, pkey);
+}