mm/core: Do not enforce PKEY permissions on remote mm access

We try to enforce protection keys in software the same way that we
do in hardware.  (See long example below).

But, we only want to do this when accessing our *own* process's
memory.  If GDB set PKRU[6].AD=1 (disable access to PKEY 6), then
tried to PTRACE_POKE a target process which just happened to have
some mprotect_pkey(pkey=6) memory, we do *not* want to deny the
debugger access to that memory.  PKRU is fundamentally a
thread-local structure and we do not want to enforce it on access
to _another_ thread's data.

This gets especially tricky when we have workqueues or other
delayed-work mechanisms that might run in a random process's context.
We can check that we only enforce pkeys when operating on our *own* mm,
but delayed work gets performed when a random user context is active.
We might end up with a situation where a delayed-work gup fails when
running randomly under its "own" task but succeeds when running under
another process.  We want to avoid that.

To avoid that, we use the new GUP flag: FOLL_REMOTE and add a
fault flag: FAULT_FLAG_REMOTE.  They indicate that we are
walking an mm which is not guranteed to be the same as
current->mm and should not be subject to protection key
enforcement.

Thanks to Jerome Glisse for pointing out this scenario.
Signed-off-by: NDave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boaz Harrosh <boaz@plexistor.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Dominik Dingel <dingel@linux.vnet.ibm.com>
Cc: Dominik Vogt <vogt@linux.vnet.ibm.com>
Cc: Eric B Munson <emunson@akamai.com>
Cc: Geliang Tang <geliangtang@163.com>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Low <jason.low2@hp.com>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Shachar Raindel <raindel@mellanox.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xie XiuQi <xiexiuqi@huawei.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-arch@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: NIngo Molnar <mingo@kernel.org>

arch/powerpc/include/asm/mmu_context.h

@@ -148,7 +148,8 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 {
 }
 
-static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write)
+static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
+		bool write, bool foreign)
 {
 	/* by default, allow everything */
 	return true;

arch/s390/include/asm/mmu_context.h

@@ -130,7 +130,8 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 {
 }
 
-static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write)
+static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
+		bool write, bool foreign)
 {
 	/* by default, allow everything */
 	return true;

arch/unicore32/include/asm/mmu_context.h

@@ -97,7 +97,8 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 {
 }
 
-static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write)
+static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
+		bool write, bool foreign)
 {
 	/* by default, allow everything */
 	return true;

arch/x86/include/asm/mmu_context.h

@@ -322,10 +322,11 @@ static inline bool vma_is_foreign(struct vm_area_struct *vma)
 	return false;
 }
 
-static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write)
+static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
+		bool write, bool foreign)
 {
 	/* allow access if the VMA is not one from this process */
-	if (vma_is_foreign(vma))
+	if (foreign || vma_is_foreign(vma))
 		return true;
 	return __pkru_allows_pkey(vma_pkey(vma), write);
 }

drivers/iommu/amd_iommu_v2.c

@@ -526,6 +526,7 @@ static void do_fault(struct work_struct *work)
 		flags |= FAULT_FLAG_USER;
 	if (fault->flags & PPR_FAULT_WRITE)
 		flags |= FAULT_FLAG_WRITE;
+	flags |= FAULT_FLAG_REMOTE;
 
 	down_read(&mm->mmap_sem);
 	vma = find_extend_vma(mm, address);

include/asm-generic/mm_hooks.h

@@ -26,7 +26,8 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 {
 }
 
-static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write)
+static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
+		bool write, bool foreign)
 {
 	/* by default, allow everything */
 	return true;

include/linux/mm.h

@@ -251,6 +251,7 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_KILLABLE	0x10	/* The fault task is in SIGKILL killable region */
 #define FAULT_FLAG_TRIED	0x20	/* Second try */
 #define FAULT_FLAG_USER		0x40	/* The fault originated in userspace */
+#define FAULT_FLAG_REMOTE	0x80	/* faulting for non current tsk/mm */
 
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's

mm/gup.c

@@ -365,6 +365,8 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 		return -ENOENT;
 	if (*flags & FOLL_WRITE)
 		fault_flags |= FAULT_FLAG_WRITE;
+	if (*flags & FOLL_REMOTE)
+		fault_flags |= FAULT_FLAG_REMOTE;
 	if (nonblocking)
 		fault_flags |= FAULT_FLAG_ALLOW_RETRY;
 	if (*flags & FOLL_NOWAIT)
@@ -415,11 +417,13 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 {
 	vm_flags_t vm_flags = vma->vm_flags;
+	int write = (gup_flags & FOLL_WRITE);
+	int foreign = (gup_flags & FOLL_REMOTE);
 
 	if (vm_flags & (VM_IO | VM_PFNMAP))
 		return -EFAULT;
 
-	if (gup_flags & FOLL_WRITE) {
+	if (write) {
 		if (!(vm_flags & VM_WRITE)) {
 			if (!(gup_flags & FOLL_FORCE))
 				return -EFAULT;
@@ -445,7 +449,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 		if (!(vm_flags & VM_MAYREAD))
 			return -EFAULT;
 	}
-	if (!arch_vma_access_permitted(vma, (gup_flags & FOLL_WRITE)))
+	if (!arch_vma_access_permitted(vma, write, foreign))
 		return -EFAULT;
 	return 0;
 }
@@ -615,7 +619,8 @@ EXPORT_SYMBOL(__get_user_pages);
 
 bool vma_permits_fault(struct vm_area_struct *vma, unsigned int fault_flags)
 {
-	bool write = !!(fault_flags & FAULT_FLAG_WRITE);
+	bool write   = !!(fault_flags & FAULT_FLAG_WRITE);
+	bool foreign = !!(fault_flags & FAULT_FLAG_REMOTE);
 	vm_flags_t vm_flags = write ? VM_WRITE : VM_READ;
 
 	if (!(vm_flags & vma->vm_flags))
@@ -623,9 +628,9 @@ bool vma_permits_fault(struct vm_area_struct *vma, unsigned int fault_flags)
 
 	/*
 	 * The architecture might have a hardware protection
-	 * mechanism other than read/write that can deny access
+	 * mechanism other than read/write that can deny access.
 	 */
-	if (!arch_vma_access_permitted(vma, write))
+	if (!arch_vma_access_permitted(vma, write, foreign))
 		return false;
 
 	return true;

mm/ksm.c

@@ -359,6 +359,10 @@ static inline bool ksm_test_exit(struct mm_struct *mm)
  * in case the application has unmapped and remapped mm,addr meanwhile.
  * Could a ksm page appear anywhere else?  Actually yes, in a VM_PFNMAP
  * mmap of /dev/mem or /dev/kmem, where we would not want to touch it.
+ *
+ * FAULT_FLAG/FOLL_REMOTE are because we do this outside the context
+ * of the process that owns 'vma'.  We also do not want to enforce
+ * protection keys here anyway.
  */
 static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 {
@@ -367,12 +371,14 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 
 	do {
 		cond_resched();
-		page = follow_page(vma, addr, FOLL_GET | FOLL_MIGRATION);
+		page = follow_page(vma, addr,
+				FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE);
 		if (IS_ERR_OR_NULL(page))
 			break;
 		if (PageKsm(page))
 			ret = handle_mm_fault(vma->vm_mm, vma, addr,
-							FAULT_FLAG_WRITE);
+							FAULT_FLAG_WRITE |
+							FAULT_FLAG_REMOTE);
 		else
 			ret = VM_FAULT_WRITE;
 		put_page(page);

mm/memory.c

@@ -3379,7 +3379,8 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	pmd_t *pmd;
 	pte_t *pte;
 
-	if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE))
+	if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE,
+					    flags & FAULT_FLAG_REMOTE))
 		return VM_FAULT_SIGSEGV;
 
 	if (unlikely(is_vm_hugetlb_page(vma)))