X-Git-Url: http://git.cascardo.info/?a=blobdiff_plain;f=mm%2Fmprotect.c;h=bcdbe62f3e6da12766f0d96a24aa4c2111614e6b;hb=9f7d416c36124667c406978bcb39746589c35d7f;hp=a4830f0325fe255ef4e106bb9b982bf7a2747415;hpb=4a1ff03faf0562665c5b0d7130658bf13d65426e;p=cascardo%2Flinux.git

diff --git a/mm/mprotect.c b/mm/mprotect.c
index a4830f0325fe..bcdbe62f3e6d 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -23,11 +23,13 @@
 #include <linux/mmu_notifier.h>
 #include <linux/migrate.h>
 #include <linux/perf_event.h>
+#include <linux/pkeys.h>
 #include <linux/ksm.h>
 #include <linux/pkeys.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
 
 #include "internal.h"
@@ -304,6 +306,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 			   vma->vm_userfaultfd_ctx);
 	if (*pprev) {
 		vma = *pprev;
+		VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY);
 		goto success;
 	}
 
@@ -327,7 +330,7 @@ success:
 	 * held in write mode.
 	 */
 	vma->vm_flags = newflags;
-	dirty_accountable = vma_wants_writenotify(vma);
+	dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot);
 	vma_set_page_prot(vma);
 
 	change_protection(vma, start, end, vma->vm_page_prot,
@@ -352,8 +355,11 @@ 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;
@@ -382,6 +388,14 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 	if (down_write_killable(&current->mm->mmap_sem))
 		return -EINTR;
 
+	/*
+	 * If userspace did not allocate the pkey, do not let
+	 * them use it here.
+	 */
+	error = -EINVAL;
+	if ((pkey != -1) && !mm_pkey_is_allocated(current->mm, pkey))
+		goto out;
+
 	vma = find_vma(current->mm, start);
 	error = -ENOMEM;
 	if (!vma)
@@ -408,8 +422,9 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 		prev = vma;
 
 	for (nstart = start ; ; ) {
+		unsigned long mask_off_old_flags;
 		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. */
 
@@ -417,8 +432,17 @@ 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);
-		newflags |= (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
+		/*
+		 * Each mprotect() call explicitly passes r/w/x permissions.
+		 * If a permission is not passed to mprotect(), it must be
+		 * cleared from the VMA.
+		 */
+		mask_off_old_flags = VM_READ | VM_WRITE | VM_EXEC |
+					ARCH_VM_PKEY_FLAGS;
+
+		new_vma_pkey = arch_override_mprotect_pkey(vma, prot, pkey);
+		newflags = calc_vm_prot_bits(prot, new_vma_pkey);
+		newflags |= (vma->vm_flags & ~mask_off_old_flags);
 
 		/* newflags >> 4 shift VM_MAY% in place of VM_% */
 		if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) {
@@ -454,3 +478,60 @@ 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);
+}
+
+SYSCALL_DEFINE2(pkey_alloc, unsigned long, flags, unsigned long, init_val)
+{
+	int pkey;
+	int ret;
+
+	/* No flags supported yet. */
+	if (flags)
+		return -EINVAL;
+	/* check for unsupported init values */
+	if (init_val & ~PKEY_ACCESS_MASK)
+		return -EINVAL;
+
+	down_write(&current->mm->mmap_sem);
+	pkey = mm_pkey_alloc(current->mm);
+
+	ret = -ENOSPC;
+	if (pkey == -1)
+		goto out;
+
+	ret = arch_set_user_pkey_access(current, pkey, init_val);
+	if (ret) {
+		mm_pkey_free(current->mm, pkey);
+		goto out;
+	}
+	ret = pkey;
+out:
+	up_write(&current->mm->mmap_sem);
+	return ret;
+}
+
+SYSCALL_DEFINE1(pkey_free, int, pkey)
+{
+	int ret;
+
+	down_write(&current->mm->mmap_sem);
+	ret = mm_pkey_free(current->mm, pkey);
+	up_write(&current->mm->mmap_sem);
+
+	/*
+	 * We could provie warnings or errors if any VMA still
+	 * has the pkey set here.
+	 */
+	return ret;
+}