From 1e9877902dc7e11d2be038371c6fbf2dfcd469d7 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:01:54 -0800 Subject: mm/gup: Introduce get_user_pages_remote() For protection keys, we need to understand whether protections should be enforced in software or not. In general, we enforce protections when working on our own task, but not when on others. We call these "current" and "remote" operations. This patch introduces a new get_user_pages() variant: get_user_pages_remote() Which is a replacement for when get_user_pages() is called on non-current tsk/mm. We also introduce a new gup flag: FOLL_REMOTE which can be used for the "__" gup variants to get this new behavior. The uprobes is_trap_at_addr() location holds mmap_sem and calls get_user_pages(current->mm) on an instruction address. This makes it a pretty unique gup caller. Being an instruction access and also really originating from the kernel (vs. the app), I opted to consider this a 'remote' access where protection keys will not be enforced. Without protection keys, this patch should not change any behavior. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Andrea Arcangeli Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Kirill A. Shutemov Cc: Linus Torvalds Cc: Naoya Horiguchi Cc: Peter Zijlstra Cc: Rik van Riel Cc: Srikar Dronamraju Cc: Vlastimil Babka Cc: jack@suse.cz Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210154.3F0E51EA@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- kernel/events/uprobes.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 0167679182c0..8eef5f55d3f0 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -299,7 +299,7 @@ int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr, retry: /* Read the page with vaddr into memory */ - ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma); + ret = get_user_pages_remote(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma); if (ret <= 0) return ret; @@ -1700,7 +1700,13 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr) if (likely(result == 0)) goto out; - result = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL); + /* + * The NULL 'tsk' here ensures that any faults that occur here + * will not be accounted to the task. 'mm' *is* current->mm, + * but we treat this as a 'remote' access since it is + * essentially a kernel access to the memory. + */ + result = get_user_pages_remote(NULL, mm, vaddr, 1, 0, 1, &page, NULL); if (result < 0) return result; -- cgit v1.2.3 From cd0ea35ff5511cde299a61c21a95889b4a71464e Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Feb 2016 13:02:12 -0800 Subject: signals, pkeys: Notify userspace about protection key faults A protection key fault is very similar to any other access error. There must be a VMA, etc... We even want to take the same action (SIGSEGV) that we do with a normal access fault. However, we do need to let userspace know that something is different. We do this the same way what we did with SEGV_BNDERR with Memory Protection eXtensions (MPX): define a new SEGV code: SEGV_PKUERR. We add a siginfo field: si_pkey that reveals to userspace which protection key was set on the PTE that we faulted on. There is no other easy way for userspace to figure this out. They could parse smaps but that would be a bit cruel. We share space with in siginfo with _addr_bnd. #BR faults from MPX are completely separate from page faults (#PF) that trigger from protection key violations, so we never need both at the same time. Note that _pkey is a 64-bit value. The current hardware only supports 4-bit protection keys. We do this because there is _plenty_ of space in _sigfault and it is possible that future processors would support more than 4 bits of protection keys. The x86 code to actually fill in the siginfo is in the next patch. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: Al Viro Cc: Amanieu d'Antras Cc: Andrew Morton Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Palmer Dabbelt Cc: Peter Zijlstra Cc: Richard Weinberger Cc: Rik van Riel Cc: Sasha Levin Cc: Vegard Nossum Cc: Vladimir Davydov Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210212.3A9B83AC@viggo.jf.intel.com Signed-off-by: Ingo Molnar --- include/uapi/asm-generic/siginfo.h | 17 ++++++++++++----- kernel/signal.c | 4 ++++ 2 files changed, 16 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index 1e3552037a5a..90384d55225b 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -91,10 +91,15 @@ typedef struct siginfo { int _trapno; /* TRAP # which caused the signal */ #endif short _addr_lsb; /* LSB of the reported address */ - struct { - void __user *_lower; - void __user *_upper; - } _addr_bnd; + union { + /* used when si_code=SEGV_BNDERR */ + struct { + void __user *_lower; + void __user *_upper; + } _addr_bnd; + /* used when si_code=SEGV_PKUERR */ + u64 _pkey; + }; } _sigfault; /* SIGPOLL */ @@ -137,6 +142,7 @@ typedef struct siginfo { #define si_addr_lsb _sifields._sigfault._addr_lsb #define si_lower _sifields._sigfault._addr_bnd._lower #define si_upper _sifields._sigfault._addr_bnd._upper +#define si_pkey _sifields._sigfault._pkey #define si_band _sifields._sigpoll._band #define si_fd _sifields._sigpoll._fd #ifdef __ARCH_SIGSYS @@ -206,7 +212,8 @@ typedef struct siginfo { #define SEGV_MAPERR (__SI_FAULT|1) /* address not mapped to object */ #define SEGV_ACCERR (__SI_FAULT|2) /* invalid permissions for mapped object */ #define SEGV_BNDERR (__SI_FAULT|3) /* failed address bound checks */ -#define NSIGSEGV 3 +#define SEGV_PKUERR (__SI_FAULT|4) /* failed protection key checks */ +#define NSIGSEGV 4 /* * SIGBUS si_codes diff --git a/kernel/signal.c b/kernel/signal.c index 0508544c8ced..fe8ed298373c 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2708,6 +2708,10 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from) err |= __put_user(from->si_lower, &to->si_lower); err |= __put_user(from->si_upper, &to->si_upper); } +#endif +#ifdef SEGV_PKUERR + if (from->si_signo == SIGSEGV && from->si_code == SEGV_PKUERR) + err |= __put_user(from->si_pkey, &to->si_pkey); #endif break; case __SI_CHLD: -- cgit v1.2.3