| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20151117033600.D9061172@viggo.jf.intel.com>
Date: Mon, 16 Nov 2015 19:36:00 -0800
From: Dave Hansen <dave@...1.net>
To: linux-kernel@...r.kernel.org
Cc: x86@...nel.org, Dave Hansen <dave@...1.net>,
dave.hansen@...ux.intel.com, linux-api@...r.kernel.org
Subject: [PATCH 35/37] x86, pkeys: add pkey set/get syscalls
From: Dave Hansen <dave.hansen@...ux.intel.com>
This establishes two more system calls for protection key management:
unsigned long pkey_get(int pkey);
int pkey_set(int pkey, unsigned long access_rights);
The return value from pkey_get() and the 'access_rights' passed
to pkey_set() are the same format: a bitmask containing
PKEY_DENY_WRITE and/or PKEY_DENY_ACCESS, or nothing set at all.
These replace userspace's direct use of rdpkru/wrpkru.
With current hardware, the kernel can not enforce that it has
control over a given key. But, this at least allows the kernel
to indicate to userspace that userspace does not control a given
protection key.
The kernel does _not_ enforce that this interface must be used for
changes to PKRU, even for keys it has not "allocated".
Signed-off-by: Dave Hansen <dave.hansen@...ux.intel.com>
Cc: linux-api@...r.kernel.org
---
b/arch/x86/entry/syscalls/syscall_32.tbl | 2 +
b/arch/x86/entry/syscalls/syscall_64.tbl | 2 +
b/arch/x86/include/asm/mmu_context.h | 2 +
b/arch/x86/include/asm/pkeys.h | 2 -
b/arch/x86/kernel/fpu/xstate.c | 55 +++++++++++++++++++++++++++++--
b/include/linux/pkeys.h | 8 ++++
b/mm/mprotect.c | 34 +++++++++++++++++++
7 files changed, 102 insertions(+), 3 deletions(-)
diff -puN arch/x86/entry/syscalls/syscall_32.tbl~pkey-syscalls-set-get arch/x86/entry/syscalls/syscall_32.tbl
--- a/arch/x86/entry/syscalls/syscall_32.tbl~pkey-syscalls-set-get 2015-11-16 12:36:34.851873071 -0800
+++ b/arch/x86/entry/syscalls/syscall_32.tbl 2015-11-16 12:36:34.863873616 -0800
@@ -386,3 +386,5 @@
377 i386 pkey_mprotect sys_pkey_mprotect
378 i386 pkey_alloc sys_pkey_alloc
379 i386 pkey_free sys_pkey_free
+380 i386 pkey_get sys_pkey_get
+381 i386 pkey_set sys_pkey_set
diff -puN arch/x86/entry/syscalls/syscall_64.tbl~pkey-syscalls-set-get arch/x86/entry/syscalls/syscall_64.tbl
--- a/arch/x86/entry/syscalls/syscall_64.tbl~pkey-syscalls-set-get 2015-11-16 12:36:34.852873116 -0800
+++ b/arch/x86/entry/syscalls/syscall_64.tbl 2015-11-16 12:36:34.864873661 -0800
@@ -335,6 +335,8 @@
326 common pkey_mprotect sys_pkey_mprotect
327 common pkey_alloc sys_pkey_alloc
328 common pkey_free sys_pkey_free
+329 common pkey_get sys_pkey_get
+330 common pkey_set sys_pkey_set
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff -puN arch/x86/include/asm/mmu_context.h~pkey-syscalls-set-get arch/x86/include/asm/mmu_context.h
--- a/arch/x86/include/asm/mmu_context.h~pkey-syscalls-set-get 2015-11-16 12:36:34.854873207 -0800
+++ b/arch/x86/include/asm/mmu_context.h 2015-11-16 12:36:34.864873661 -0800
@@ -340,5 +340,7 @@ static inline bool arch_pte_access_permi
extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
unsigned long init_val);
+extern unsigned long arch_get_user_pkey_access(struct task_struct *tsk,
+ int pkey);
#endif /* _ASM_X86_MMU_CONTEXT_H */
diff -puN arch/x86/include/asm/pkeys.h~pkey-syscalls-set-get arch/x86/include/asm/pkeys.h
--- a/arch/x86/include/asm/pkeys.h~pkey-syscalls-set-get 2015-11-16 12:36:34.855873253 -0800
+++ b/arch/x86/include/asm/pkeys.h 2015-11-16 19:14:09.231117816 -0800
@@ -16,7 +16,7 @@
} while (0)
static inline
-bool mm_pkey_is_allocated(struct mm_struct *mm, unsigned long pkey)
+bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey)
{
if (!arch_validate_pkey(pkey))
return true;
diff -puN arch/x86/kernel/fpu/xstate.c~pkey-syscalls-set-get arch/x86/kernel/fpu/xstate.c
--- a/arch/x86/kernel/fpu/xstate.c~pkey-syscalls-set-get 2015-11-16 12:36:34.857873343 -0800
+++ b/arch/x86/kernel/fpu/xstate.c 2015-11-16 12:36:34.865873706 -0800
@@ -687,7 +687,7 @@ void fpu__resume_cpu(void)
*
* Note: does not work for compacted buffers.
*/
-void *__raw_xsave_addr(struct xregs_state *xsave, int xstate_feature_mask)
+static void *__raw_xsave_addr(struct xregs_state *xsave, int xstate_feature_mask)
{
int feature_nr = fls64(xstate_feature_mask) - 1;
@@ -871,6 +871,7 @@ static void fpu__xfeature_set_state(int
#define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2)
#define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1)
+#define PKRU_INIT_STATE 0
/*
* This will go out and modify the XSAVE buffer so that PKRU is
@@ -889,6 +890,9 @@ int arch_set_user_pkey_access(struct tas
int pkey_shift = (pkey * PKRU_BITS_PER_PKEY);
u32 new_pkru_bits = 0;
+ /* Only support manipulating current task for now */
+ if (tsk != current)
+ return -EINVAL;
if (!arch_validate_pkey(pkey))
return -EINVAL;
/*
@@ -916,7 +920,7 @@ int arch_set_user_pkey_access(struct tas
* state.
*/
if (!old_pkru_state)
- new_pkru_state.pkru = 0;
+ new_pkru_state.pkru = PKRU_INIT_STATE;
else
new_pkru_state.pkru = old_pkru_state->pkru;
@@ -941,4 +945,51 @@ int arch_set_user_pkey_access(struct tas
return 0;
}
+
+/*
+ * Figures out what the rights are currently for 'pkey'.
+ * Converts from PKRU's format to the user-visible PKEY_DISABLE_*
+ * format.
+ */
+unsigned long arch_get_user_pkey_access(struct task_struct *tsk, int pkey)
+{
+ struct fpu *fpu = ¤t->thread.fpu;
+ u32 pkru_reg;
+ int ret = 0;
+
+ /* Only support manipulating current task for now */
+ if (tsk != current)
+ return -1;
+ if (!boot_cpu_has(X86_FEATURE_OSPKE))
+ return -1;
+ /*
+ * The contents of PKRU itself are invalid. Consult the
+ * task's XSAVE buffer for PKRU contents. This is much
+ * more expensive than reading PKRU directly, but should
+ * be rare or impossible with eagerfpu mode.
+ */
+ if (!fpu->fpregs_active) {
+ struct xregs_state *xsave = &fpu->state.xsave;
+ struct pkru_state *pkru_state =
+ get_xsave_addr(xsave, XFEATURE_MASK_PKRU);
+ /*
+ * PKRU is in its init state and not present in
+ * the buffer in a saved form.
+ */
+ if (!pkru_state)
+ return PKRU_INIT_STATE;
+
+ return pkru_state->pkru;
+ }
+ /*
+ * Consult the user register directly.
+ */
+ pkru_reg = read_pkru();
+ if (!__pkru_allows_read(pkru_reg, pkey))
+ ret |= PKEY_DISABLE_ACCESS;
+ if (!__pkru_allows_write(pkru_reg, pkey))
+ ret |= PKEY_DISABLE_WRITE;
+
+ return ret;
+}
#endif /* CONFIG_ARCH_HAS_PKEYS */
diff -puN include/linux/pkeys.h~pkey-syscalls-set-get include/linux/pkeys.h
--- a/include/linux/pkeys.h~pkey-syscalls-set-get 2015-11-16 12:36:34.858873389 -0800
+++ b/include/linux/pkeys.h 2015-11-16 12:36:34.865873706 -0800
@@ -43,6 +43,14 @@ static inline int mm_pkey_free(struct mm
static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
unsigned long init_val)
{
+ return -EINVAL;
+}
+
+static inline
+unsigned long arch_get_user_pkey_access(struct task_struct *tsk, int pkey)
+{
+ if (pkey)
+ return -1;
return 0;
}
diff -puN mm/mprotect.c~pkey-syscalls-set-get mm/mprotect.c
--- a/mm/mprotect.c~pkey-syscalls-set-get 2015-11-16 12:36:34.860873479 -0800
+++ b/mm/mprotect.c 2015-11-16 12:36:34.865873706 -0800
@@ -529,3 +529,37 @@ SYSCALL_DEFINE1(pkey_free, int, pkey)
*/
return ret;
}
+
+SYSCALL_DEFINE1(pkey_get, int, pkey)
+{
+ unsigned long ret = 0;
+
+ down_write(¤t->mm->mmap_sem);
+ if (!mm_pkey_is_allocated(current->mm, pkey))
+ ret = -EBADF;
+ up_write(¤t->mm->mmap_sem);
+
+ if (ret)
+ return ret;
+
+ ret = arch_get_user_pkey_access(current, pkey);
+
+ return ret;
+}
+
+SYSCALL_DEFINE2(pkey_set, int, pkey, unsigned long, access_rights)
+{
+ unsigned long ret = 0;
+
+ down_write(¤t->mm->mmap_sem);
+ if (!mm_pkey_is_allocated(current->mm, pkey))
+ ret = -EBADF;
+ up_write(¤t->mm->mmap_sem);
+
+ if (ret)
+ return ret;
+
+ ret = arch_set_user_pkey_access(current, pkey, access_rights);
+
+ return ret;
+}
_
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists