linux/arch/arm64/kernel/signal.c

986 lines
24 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Based on arch/arm/kernel/signal.c
*
* Copyright (C) 1995-2009 Russell King
* Copyright (C) 2012 ARM Ltd.
*/
arm64: signal: Report signal frame size to userspace via auxv Stateful CPU architecture extensions may require the signal frame to grow to a size that exceeds the arch's MINSIGSTKSZ #define. However, changing this #define is an ABI break. To allow userspace the option of determining the signal frame size in a more forwards-compatible way, this patch adds a new auxv entry tagged with AT_MINSIGSTKSZ, which provides the maximum signal frame size that the process can observe during its lifetime. If AT_MINSIGSTKSZ is absent from the aux vector, the caller can assume that the MINSIGSTKSZ #define is sufficient. This allows for a consistent interface with older kernels that do not provide AT_MINSIGSTKSZ. The idea is that libc could expose this via sysconf() or some similar mechanism. There is deliberately no AT_SIGSTKSZ. The kernel knows nothing about userspace's own stack overheads and should not pretend to know. For arm64: The primary motivation for this interface is the Scalable Vector Extension, which can require at least 4KB or so of extra space in the signal frame for the largest hardware implementations. To determine the correct value, a "Christmas tree" mode (via the add_all argument) is added to setup_sigframe_layout(), to simulate addition of all possible records to the signal frame at maximum possible size. If this procedure goes wrong somehow, resulting in a stupidly large frame layout and hence failure of sigframe_alloc() to allocate a record to the frame, then this is indicative of a kernel bug. In this case, we WARN() and no attempt is made to populate AT_MINSIGSTKSZ for userspace. For arm64 SVE: The SVE context block in the signal frame needs to be considered too when computing the maximum possible signal frame size. Because the size of this block depends on the vector length, this patch computes the size based not on the thread's current vector length but instead on the maximum possible vector length: this determines the maximum size of SVE context block that can be observed in any signal frame for the lifetime of the process. Signed-off-by: Dave Martin <Dave.Martin@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-06-01 18:10:14 +08:00
#include <linux/cache.h>
#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/signal.h>
#include <linux/personality.h>
#include <linux/freezer.h>
#include <linux/stddef.h>
#include <linux/uaccess.h>
#include <linux/sizes.h>
#include <linux/string.h>
#include <linux/tracehook.h>
#include <linux/ratelimit.h>
arm64/syscalls: Check address limit on user-mode return Ensure the address limit is a user-mode segment before returning to user-mode. Otherwise a process can corrupt kernel-mode memory and elevate privileges [1]. The set_fs function sets the TIF_SETFS flag to force a slow path on return. In the slow path, the address limit is checked to be USER_DS if needed. [1] https://bugs.chromium.org/p/project-zero/issues/detail?id=990 Signed-off-by: Thomas Garnier <thgarnie@google.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Mark Rutland <mark.rutland@arm.com> Cc: kernel-hardening@lists.openwall.com Cc: Will Deacon <will.deacon@arm.com> Cc: David Howells <dhowells@redhat.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Miroslav Benes <mbenes@suse.cz> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Pratyush Anand <panand@redhat.com> Cc: Russell King <linux@armlinux.org.uk> Cc: Petr Mladek <pmladek@suse.com> Cc: Rik van Riel <riel@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andy Lutomirski <luto@kernel.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: linux-arm-kernel@lists.infradead.org Cc: Will Drewry <wad@chromium.org> Cc: linux-api@vger.kernel.org Cc: Oleg Nesterov <oleg@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Paolo Bonzini <pbonzini@redhat.com> Link: http://lkml.kernel.org/r/20170615011203.144108-3-thgarnie@google.com
2017-06-15 09:12:03 +08:00
#include <linux/syscalls.h>
#include <asm/daifflags.h>
#include <asm/debug-monitors.h>
#include <asm/elf.h>
#include <asm/cacheflush.h>
#include <asm/ucontext.h>
#include <asm/unistd.h>
#include <asm/fpsimd.h>
#include <asm/ptrace.h>
#include <asm/signal32.h>
#include <asm/traps.h>
#include <asm/vdso.h>
/*
* Do a signal return; undo the signal stack. These are aligned to 128-bit.
*/
struct rt_sigframe {
struct siginfo info;
struct ucontext uc;
};
struct frame_record {
u64 fp;
u64 lr;
};
struct rt_sigframe_user_layout {
struct rt_sigframe __user *sigframe;
struct frame_record __user *next_frame;
unsigned long size; /* size of allocated sigframe data */
unsigned long limit; /* largest allowed size */
unsigned long fpsimd_offset;
unsigned long esr_offset;
arm64/sve: Signal handling support This patch implements support for saving and restoring the SVE registers around signals. A fixed-size header struct sve_context is always included in the signal frame encoding the thread's vector length at the time of signal delivery, optionally followed by a variable-layout structure encoding the SVE registers. Because of the need to preserve backwards compatibility, the FPSIMD view of the SVE registers is always dumped as a struct fpsimd_context in the usual way, in addition to any sve_context. The SVE vector registers are dumped in full, including bits 127:0 of each register which alias the corresponding FPSIMD vector registers in the hardware. To avoid any ambiguity about which alias to restore during sigreturn, the kernel always restores bits 127:0 of each SVE vector register from the fpsimd_context in the signal frame (which must be present): userspace needs to take this into account if it wants to modify the SVE vector register contents on return from a signal. FPSR and FPCR, which are used by both FPSIMD and SVE, are not included in sve_context because they are always present in fpsimd_context anyway. For signal delivery, a new helper fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:51:07 +08:00
unsigned long sve_offset;
unsigned long extra_offset;
unsigned long end_offset;
};
#define BASE_SIGFRAME_SIZE round_up(sizeof(struct rt_sigframe), 16)
#define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16)
#define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16)
static void init_user_layout(struct rt_sigframe_user_layout *user)
{
const size_t reserved_size =
sizeof(user->sigframe->uc.uc_mcontext.__reserved);
memset(user, 0, sizeof(*user));
user->size = offsetof(struct rt_sigframe, uc.uc_mcontext.__reserved);
user->limit = user->size + reserved_size;
user->limit -= TERMINATOR_SIZE;
user->limit -= EXTRA_CONTEXT_SIZE;
/* Reserve space for extension and terminator ^ */
}
static size_t sigframe_size(struct rt_sigframe_user_layout const *user)
{
return round_up(max(user->size, sizeof(struct rt_sigframe)), 16);
}
/*
* Sanity limit on the approximate maximum size of signal frame we'll
* try to generate. Stack alignment padding and the frame record are
* not taken into account. This limit is not a guarantee and is
* NOT ABI.
*/
#define SIGFRAME_MAXSZ SZ_64K
static int __sigframe_alloc(struct rt_sigframe_user_layout *user,
unsigned long *offset, size_t size, bool extend)
{
size_t padded_size = round_up(size, 16);
if (padded_size > user->limit - user->size &&
!user->extra_offset &&
extend) {
int ret;
user->limit += EXTRA_CONTEXT_SIZE;
ret = __sigframe_alloc(user, &user->extra_offset,
sizeof(struct extra_context), false);
if (ret) {
user->limit -= EXTRA_CONTEXT_SIZE;
return ret;
}
/* Reserve space for the __reserved[] terminator */
user->size += TERMINATOR_SIZE;
/*
* Allow expansion up to SIGFRAME_MAXSZ, ensuring space for
* the terminator:
*/
user->limit = SIGFRAME_MAXSZ - TERMINATOR_SIZE;
}
/* Still not enough space? Bad luck! */
if (padded_size > user->limit - user->size)
return -ENOMEM;
*offset = user->size;
user->size += padded_size;
return 0;
}
/*
* Allocate space for an optional record of <size> bytes in the user
* signal frame. The offset from the signal frame base address to the
* allocated block is assigned to *offset.
*/
static int sigframe_alloc(struct rt_sigframe_user_layout *user,
unsigned long *offset, size_t size)
{
return __sigframe_alloc(user, offset, size, true);
}
/* Allocate the null terminator record and prevent further allocations */
static int sigframe_alloc_end(struct rt_sigframe_user_layout *user)
{
int ret;
/* Un-reserve the space reserved for the terminator: */
user->limit += TERMINATOR_SIZE;
ret = sigframe_alloc(user, &user->end_offset,
sizeof(struct _aarch64_ctx));
if (ret)
return ret;
/* Prevent further allocation: */
user->limit = user->size;
return 0;
}
static void __user *apply_user_offset(
struct rt_sigframe_user_layout const *user, unsigned long offset)
{
char __user *base = (char __user *)user->sigframe;
return base + offset;
}
static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
{
arm64: uaccess: Fix omissions from usercopy whitelist When the hardend usercopy support was added for arm64, it was concluded that all cases of usercopy into and out of thread_struct were statically sized and so didn't require explicit whitelisting of the appropriate fields in thread_struct. Testing with usercopy hardening enabled has revealed that this is not the case for certain ptrace regset manipulation calls on arm64. This occurs because the sizes of usercopies associated with the regset API are dynamic by construction, and because arm64 does not always stage such copies via the stack: indeed the regset API is designed to avoid the need for that by adding some bounds checking. This is currently believed to affect only the fpsimd and TLS registers. Because the whitelisted fields in thread_struct must be contiguous, this patch groups them together in a nested struct. It is also necessary to be able to determine the location and size of that struct, so rather than making the struct anonymous (which would save on edits elsewhere) or adding an anonymous union containing named and unnamed instances of the same struct (gross), this patch gives the struct a name and makes the necessary edits to code that references it (noisy but simple). Care is needed to ensure that the new struct does not contain padding (which the usercopy hardening would fail to protect). For this reason, the presence of tp2_value is made unconditional, since a padding field would be needed there in any case. This pads up to the 16-byte alignment required by struct user_fpsimd_state. Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Mark Rutland <mark.rutland@arm.com> Fixes: 9e8084d3f761 ("arm64: Implement thread_struct whitelist for hardened usercopy") Signed-off-by: Dave Martin <Dave.Martin@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2018-03-28 17:50:49 +08:00
struct user_fpsimd_state const *fpsimd =
&current->thread.uw.fpsimd_state;
int err;
/* copy the FP and status/control registers */
err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs));
__put_user_error(fpsimd->fpsr, &ctx->fpsr, err);
__put_user_error(fpsimd->fpcr, &ctx->fpcr, err);
/* copy the magic/size information */
__put_user_error(FPSIMD_MAGIC, &ctx->head.magic, err);
__put_user_error(sizeof(struct fpsimd_context), &ctx->head.size, err);
return err ? -EFAULT : 0;
}
static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
{
arm64: fpsimd: Fix state leakage when migrating after sigreturn When refactoring the sigreturn code to handle SVE, I changed the sigreturn implementation to store the new FPSIMD state from the user sigframe into task_struct before reloading the state into the CPU regs. This makes it easier to convert the data for SVE when needed. However, it turns out that the fpsimd_state structure passed into fpsimd_update_current_state is not fully initialised, so assigning the structure as a whole corrupts current->thread.fpsimd_state.cpu with uninitialised data. This means that if the garbage data written to .cpu happens to be a valid cpu number, and the task is subsequently migrated to the cpu identified by the that number, and then tries to enter userspace, the CPU FPSIMD regs will be assumed to be correct for the task and not reloaded as they should be. This can result in returning to userspace with the FPSIMD registers containing data that is stale or that belongs to another task or to the kernel. Knowingly handing around a kernel structure that is incompletely initialised with user data is a potential source of mistakes, especially across source file boundaries. To help avoid a repeat of this issue, this patch adapts the relevant internal API to hand around the user-accessible subset only: struct user_fpsimd_state. To avoid future surprises, this patch also converts all uses of struct fpsimd_state that really only access the user subset, to use struct user_fpsimd_state. A few missing consts are added to function prototypes for good measure. Thanks to Will for spotting the cause of the bug here. Reported-by: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2017-12-16 02:34:38 +08:00
struct user_fpsimd_state fpsimd;
__u32 magic, size;
int err = 0;
/* check the magic/size information */
__get_user_error(magic, &ctx->head.magic, err);
__get_user_error(size, &ctx->head.size, err);
if (err)
return -EFAULT;
if (magic != FPSIMD_MAGIC || size != sizeof(struct fpsimd_context))
return -EINVAL;
/* copy the FP and status/control registers */
err = __copy_from_user(fpsimd.vregs, ctx->vregs,
sizeof(fpsimd.vregs));
__get_user_error(fpsimd.fpsr, &ctx->fpsr, err);
__get_user_error(fpsimd.fpcr, &ctx->fpcr, err);
arm64/sve: Signal handling support This patch implements support for saving and restoring the SVE registers around signals. A fixed-size header struct sve_context is always included in the signal frame encoding the thread's vector length at the time of signal delivery, optionally followed by a variable-layout structure encoding the SVE registers. Because of the need to preserve backwards compatibility, the FPSIMD view of the SVE registers is always dumped as a struct fpsimd_context in the usual way, in addition to any sve_context. The SVE vector registers are dumped in full, including bits 127:0 of each register which alias the corresponding FPSIMD vector registers in the hardware. To avoid any ambiguity about which alias to restore during sigreturn, the kernel always restores bits 127:0 of each SVE vector register from the fpsimd_context in the signal frame (which must be present): userspace needs to take this into account if it wants to modify the SVE vector register contents on return from a signal. FPSR and FPCR, which are used by both FPSIMD and SVE, are not included in sve_context because they are always present in fpsimd_context anyway. For signal delivery, a new helper fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:51:07 +08:00
clear_thread_flag(TIF_SVE);
/* load the hardware registers from the fpsimd_state structure */
if (!err)
fpsimd_update_current_state(&fpsimd);
return err ? -EFAULT : 0;
}
arm64/sve: Signal handling support This patch implements support for saving and restoring the SVE registers around signals. A fixed-size header struct sve_context is always included in the signal frame encoding the thread's vector length at the time of signal delivery, optionally followed by a variable-layout structure encoding the SVE registers. Because of the need to preserve backwards compatibility, the FPSIMD view of the SVE registers is always dumped as a struct fpsimd_context in the usual way, in addition to any sve_context. The SVE vector registers are dumped in full, including bits 127:0 of each register which alias the corresponding FPSIMD vector registers in the hardware. To avoid any ambiguity about which alias to restore during sigreturn, the kernel always restores bits 127:0 of each SVE vector register from the fpsimd_context in the signal frame (which must be present): userspace needs to take this into account if it wants to modify the SVE vector register contents on return from a signal. FPSR and FPCR, which are used by both FPSIMD and SVE, are not included in sve_context because they are always present in fpsimd_context anyway. For signal delivery, a new helper fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:51:07 +08:00
struct user_ctxs {
struct fpsimd_context __user *fpsimd;
arm64/sve: Signal handling support This patch implements support for saving and restoring the SVE registers around signals. A fixed-size header struct sve_context is always included in the signal frame encoding the thread's vector length at the time of signal delivery, optionally followed by a variable-layout structure encoding the SVE registers. Because of the need to preserve backwards compatibility, the FPSIMD view of the SVE registers is always dumped as a struct fpsimd_context in the usual way, in addition to any sve_context. The SVE vector registers are dumped in full, including bits 127:0 of each register which alias the corresponding FPSIMD vector registers in the hardware. To avoid any ambiguity about which alias to restore during sigreturn, the kernel always restores bits 127:0 of each SVE vector register from the fpsimd_context in the signal frame (which must be present): userspace needs to take this into account if it wants to modify the SVE vector register contents on return from a signal. FPSR and FPCR, which are used by both FPSIMD and SVE, are not included in sve_context because they are always present in fpsimd_context anyway. For signal delivery, a new helper fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:51:07 +08:00
struct sve_context __user *sve;
};
arm64/sve: Signal handling support This patch implements support for saving and restoring the SVE registers around signals. A fixed-size header struct sve_context is always included in the signal frame encoding the thread's vector length at the time of signal delivery, optionally followed by a variable-layout structure encoding the SVE registers. Because of the need to preserve backwards compatibility, the FPSIMD view of the SVE registers is always dumped as a struct fpsimd_context in the usual way, in addition to any sve_context. The SVE vector registers are dumped in full, including bits 127:0 of each register which alias the corresponding FPSIMD vector registers in the hardware. To avoid any ambiguity about which alias to restore during sigreturn, the kernel always restores bits 127:0 of each SVE vector register from the fpsimd_context in the signal frame (which must be present): userspace needs to take this into account if it wants to modify the SVE vector register contents on return from a signal. FPSR and FPCR, which are used by both FPSIMD and SVE, are not included in sve_context because they are always present in fpsimd_context anyway. For signal delivery, a new helper fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:51:07 +08:00
#ifdef CONFIG_ARM64_SVE
static int preserve_sve_context(struct sve_context __user *ctx)
{
int err = 0;
u16 reserved[ARRAY_SIZE(ctx->__reserved)];
unsigned int vl = current->thread.sve_vl;
unsigned int vq = 0;
if (test_thread_flag(TIF_SVE))
vq = sve_vq_from_vl(vl);
memset(reserved, 0, sizeof(reserved));
__put_user_error(SVE_MAGIC, &ctx->head.magic, err);
__put_user_error(round_up(SVE_SIG_CONTEXT_SIZE(vq), 16),
&ctx->head.size, err);
__put_user_error(vl, &ctx->vl, err);
BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
if (vq) {
/*
* This assumes that the SVE state has already been saved to
* the task struct by calling the function
* fpsimd_signal_preserve_current_state().
arm64/sve: Signal handling support This patch implements support for saving and restoring the SVE registers around signals. A fixed-size header struct sve_context is always included in the signal frame encoding the thread's vector length at the time of signal delivery, optionally followed by a variable-layout structure encoding the SVE registers. Because of the need to preserve backwards compatibility, the FPSIMD view of the SVE registers is always dumped as a struct fpsimd_context in the usual way, in addition to any sve_context. The SVE vector registers are dumped in full, including bits 127:0 of each register which alias the corresponding FPSIMD vector registers in the hardware. To avoid any ambiguity about which alias to restore during sigreturn, the kernel always restores bits 127:0 of each SVE vector register from the fpsimd_context in the signal frame (which must be present): userspace needs to take this into account if it wants to modify the SVE vector register contents on return from a signal. FPSR and FPCR, which are used by both FPSIMD and SVE, are not included in sve_context because they are always present in fpsimd_context anyway. For signal delivery, a new helper fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:51:07 +08:00
*/
err |= __copy_to_user((char __user *)ctx + SVE_SIG_REGS_OFFSET,
current->thread.sve_state,
SVE_SIG_REGS_SIZE(vq));
}
return err ? -EFAULT : 0;
}
static int restore_sve_fpsimd_context(struct user_ctxs *user)
{
int err;
unsigned int vq;
arm64: fpsimd: Fix state leakage when migrating after sigreturn When refactoring the sigreturn code to handle SVE, I changed the sigreturn implementation to store the new FPSIMD state from the user sigframe into task_struct before reloading the state into the CPU regs. This makes it easier to convert the data for SVE when needed. However, it turns out that the fpsimd_state structure passed into fpsimd_update_current_state is not fully initialised, so assigning the structure as a whole corrupts current->thread.fpsimd_state.cpu with uninitialised data. This means that if the garbage data written to .cpu happens to be a valid cpu number, and the task is subsequently migrated to the cpu identified by the that number, and then tries to enter userspace, the CPU FPSIMD regs will be assumed to be correct for the task and not reloaded as they should be. This can result in returning to userspace with the FPSIMD registers containing data that is stale or that belongs to another task or to the kernel. Knowingly handing around a kernel structure that is incompletely initialised with user data is a potential source of mistakes, especially across source file boundaries. To help avoid a repeat of this issue, this patch adapts the relevant internal API to hand around the user-accessible subset only: struct user_fpsimd_state. To avoid future surprises, this patch also converts all uses of struct fpsimd_state that really only access the user subset, to use struct user_fpsimd_state. A few missing consts are added to function prototypes for good measure. Thanks to Will for spotting the cause of the bug here. Reported-by: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2017-12-16 02:34:38 +08:00
struct user_fpsimd_state fpsimd;
arm64/sve: Signal handling support This patch implements support for saving and restoring the SVE registers around signals. A fixed-size header struct sve_context is always included in the signal frame encoding the thread's vector length at the time of signal delivery, optionally followed by a variable-layout structure encoding the SVE registers. Because of the need to preserve backwards compatibility, the FPSIMD view of the SVE registers is always dumped as a struct fpsimd_context in the usual way, in addition to any sve_context. The SVE vector registers are dumped in full, including bits 127:0 of each register which alias the corresponding FPSIMD vector registers in the hardware. To avoid any ambiguity about which alias to restore during sigreturn, the kernel always restores bits 127:0 of each SVE vector register from the fpsimd_context in the signal frame (which must be present): userspace needs to take this into account if it wants to modify the SVE vector register contents on return from a signal. FPSR and FPCR, which are used by both FPSIMD and SVE, are not included in sve_context because they are always present in fpsimd_context anyway. For signal delivery, a new helper fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:51:07 +08:00
struct sve_context sve;
if (__copy_from_user(&sve, user->sve, sizeof(sve)))
return -EFAULT;
if (sve.vl != current->thread.sve_vl)
return -EINVAL;
if (sve.head.size <= sizeof(*user->sve)) {
clear_thread_flag(TIF_SVE);
goto fpsimd_only;
}
vq = sve_vq_from_vl(sve.vl);
if (sve.head.size < SVE_SIG_CONTEXT_SIZE(vq))
return -EINVAL;
/*
* Careful: we are about __copy_from_user() directly into
* thread.sve_state with preemption enabled, so protection is
* needed to prevent a racing context switch from writing stale
* registers back over the new data.
*/
fpsimd_flush_task_state(current);
/* From now, fpsimd_thread_switch() won't touch thread.sve_state */
sve_alloc(current);
err = __copy_from_user(current->thread.sve_state,
(char __user const *)user->sve +
SVE_SIG_REGS_OFFSET,
SVE_SIG_REGS_SIZE(vq));
if (err)
return -EFAULT;
set_thread_flag(TIF_SVE);
fpsimd_only:
/* copy the FP and status/control registers */
/* restore_sigframe() already checked that user->fpsimd != NULL. */
err = __copy_from_user(fpsimd.vregs, user->fpsimd->vregs,
sizeof(fpsimd.vregs));
__get_user_error(fpsimd.fpsr, &user->fpsimd->fpsr, err);
__get_user_error(fpsimd.fpcr, &user->fpsimd->fpcr, err);
/* load the hardware registers from the fpsimd_state structure */
if (!err)
fpsimd_update_current_state(&fpsimd);
return err ? -EFAULT : 0;
}
#else /* ! CONFIG_ARM64_SVE */
/* Turn any non-optimised out attempts to use these into a link error: */
extern int preserve_sve_context(void __user *ctx);
extern int restore_sve_fpsimd_context(struct user_ctxs *user);
#endif /* ! CONFIG_ARM64_SVE */
static int parse_user_sigframe(struct user_ctxs *user,
struct rt_sigframe __user *sf)
{
struct sigcontext __user *const sc = &sf->uc.uc_mcontext;
struct _aarch64_ctx __user *head;
char __user *base = (char __user *)&sc->__reserved;
size_t offset = 0;
size_t limit = sizeof(sc->__reserved);
bool have_extra_context = false;
char const __user *const sfp = (char const __user *)sf;
user->fpsimd = NULL;
arm64/sve: Signal handling support This patch implements support for saving and restoring the SVE registers around signals. A fixed-size header struct sve_context is always included in the signal frame encoding the thread's vector length at the time of signal delivery, optionally followed by a variable-layout structure encoding the SVE registers. Because of the need to preserve backwards compatibility, the FPSIMD view of the SVE registers is always dumped as a struct fpsimd_context in the usual way, in addition to any sve_context. The SVE vector registers are dumped in full, including bits 127:0 of each register which alias the corresponding FPSIMD vector registers in the hardware. To avoid any ambiguity about which alias to restore during sigreturn, the kernel always restores bits 127:0 of each SVE vector register from the fpsimd_context in the signal frame (which must be present): userspace needs to take this into account if it wants to modify the SVE vector register contents on return from a signal. FPSR and FPCR, which are used by both FPSIMD and SVE, are not included in sve_context because they are always present in fpsimd_context anyway. For signal delivery, a new helper fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:51:07 +08:00
user->sve = NULL;
if (!IS_ALIGNED((unsigned long)base, 16))
goto invalid;
while (1) {
int err = 0;
u32 magic, size;
char const __user *userp;
struct extra_context const __user *extra;
u64 extra_datap;
u32 extra_size;
struct _aarch64_ctx const __user *end;
u32 end_magic, end_size;
if (limit - offset < sizeof(*head))
goto invalid;
if (!IS_ALIGNED(offset, 16))
goto invalid;
head = (struct _aarch64_ctx __user *)(base + offset);
__get_user_error(magic, &head->magic, err);
__get_user_error(size, &head->size, err);
if (err)
return err;
if (limit - offset < size)
goto invalid;
switch (magic) {
case 0:
if (size)
goto invalid;
goto done;
case FPSIMD_MAGIC:
if (!system_supports_fpsimd())
goto invalid;
if (user->fpsimd)
goto invalid;
if (size < sizeof(*user->fpsimd))
goto invalid;
user->fpsimd = (struct fpsimd_context __user *)head;
break;
case ESR_MAGIC:
/* ignore */
break;
arm64/sve: Signal handling support This patch implements support for saving and restoring the SVE registers around signals. A fixed-size header struct sve_context is always included in the signal frame encoding the thread's vector length at the time of signal delivery, optionally followed by a variable-layout structure encoding the SVE registers. Because of the need to preserve backwards compatibility, the FPSIMD view of the SVE registers is always dumped as a struct fpsimd_context in the usual way, in addition to any sve_context. The SVE vector registers are dumped in full, including bits 127:0 of each register which alias the corresponding FPSIMD vector registers in the hardware. To avoid any ambiguity about which alias to restore during sigreturn, the kernel always restores bits 127:0 of each SVE vector register from the fpsimd_context in the signal frame (which must be present): userspace needs to take this into account if it wants to modify the SVE vector register contents on return from a signal. FPSR and FPCR, which are used by both FPSIMD and SVE, are not included in sve_context because they are always present in fpsimd_context anyway. For signal delivery, a new helper fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:51:07 +08:00
case SVE_MAGIC:
if (!system_supports_sve())
goto invalid;
if (user->sve)
goto invalid;
if (size < sizeof(*user->sve))
goto invalid;
user->sve = (struct sve_context __user *)head;
break;
case EXTRA_MAGIC:
if (have_extra_context)
goto invalid;
if (size < sizeof(*extra))
goto invalid;
userp = (char const __user *)head;
extra = (struct extra_context const __user *)userp;
userp += size;
__get_user_error(extra_datap, &extra->datap, err);
__get_user_error(extra_size, &extra->size, err);
if (err)
return err;
/* Check for the dummy terminator in __reserved[]: */
if (limit - offset - size < TERMINATOR_SIZE)
goto invalid;
end = (struct _aarch64_ctx const __user *)userp;
userp += TERMINATOR_SIZE;
__get_user_error(end_magic, &end->magic, err);
__get_user_error(end_size, &end->size, err);
if (err)
return err;
if (end_magic || end_size)
goto invalid;
/* Prevent looping/repeated parsing of extra_context */
have_extra_context = true;
base = (__force void __user *)extra_datap;
if (!IS_ALIGNED((unsigned long)base, 16))
goto invalid;
if (!IS_ALIGNED(extra_size, 16))
goto invalid;
if (base != userp)
goto invalid;
/* Reject "unreasonably large" frames: */
if (extra_size > sfp + SIGFRAME_MAXSZ - userp)
goto invalid;
/*
* Ignore trailing terminator in __reserved[]
* and start parsing extra data:
*/
offset = 0;
limit = extra_size;
arm64: signal: Verify extra data is user-readable in sys_rt_sigreturn Currently sys_rt_sigreturn() verifies that the base sigframe is readable, but no similar check is performed on the extra data to which an extra_context record points. This matters because the extra data will be read with the unprotected user accessors. However, this is not a problem at present because the extra data base address is required to be exactly at the end of the base sigframe. So, there would need to be a non-user-readable kernel address within about 59K (SIGFRAME_MAXSZ - sizeof(struct rt_sigframe)) of some address for which access_ok(VERIFY_READ) returns true, in order for sigreturn to be able to read kernel memory that should be inaccessible to the user task. This is currently impossible due to the untranslatable address hole between the TTBR0 and TTBR1 address ranges. Disappearance of the hole between the TTBR0 and TTBR1 mapping ranges would require the VA size for TTBR0 and TTBR1 to grow to at least 55 bits, and either the disabling of tagged pointers for userspace or enabling of tagged pointers for kernel space; none of which is currently envisaged. Even so, it is wrong to use the unprotected user accessors without an accompanying access_ok() check. To avoid the potential for future surprises, this patch does an explicit access_ok() check on the extra data space when parsing an extra_context record. Fixes: 33f082614c34 ("arm64: signal: Allow expansion of the signal frame") Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:50:55 +08:00
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 10:57:57 +08:00
if (!access_ok(base, limit))
arm64: signal: Verify extra data is user-readable in sys_rt_sigreturn Currently sys_rt_sigreturn() verifies that the base sigframe is readable, but no similar check is performed on the extra data to which an extra_context record points. This matters because the extra data will be read with the unprotected user accessors. However, this is not a problem at present because the extra data base address is required to be exactly at the end of the base sigframe. So, there would need to be a non-user-readable kernel address within about 59K (SIGFRAME_MAXSZ - sizeof(struct rt_sigframe)) of some address for which access_ok(VERIFY_READ) returns true, in order for sigreturn to be able to read kernel memory that should be inaccessible to the user task. This is currently impossible due to the untranslatable address hole between the TTBR0 and TTBR1 address ranges. Disappearance of the hole between the TTBR0 and TTBR1 mapping ranges would require the VA size for TTBR0 and TTBR1 to grow to at least 55 bits, and either the disabling of tagged pointers for userspace or enabling of tagged pointers for kernel space; none of which is currently envisaged. Even so, it is wrong to use the unprotected user accessors without an accompanying access_ok() check. To avoid the potential for future surprises, this patch does an explicit access_ok() check on the extra data space when parsing an extra_context record. Fixes: 33f082614c34 ("arm64: signal: Allow expansion of the signal frame") Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:50:55 +08:00
goto invalid;
continue;
default:
goto invalid;
}
if (size < sizeof(*head))
goto invalid;
if (limit - offset < size)
goto invalid;
offset += size;
}
done:
return 0;
invalid:
return -EINVAL;
}
static int restore_sigframe(struct pt_regs *regs,
struct rt_sigframe __user *sf)
{
sigset_t set;
int i, err;
struct user_ctxs user;
err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
if (err == 0)
set_current_blocked(&set);
for (i = 0; i < 31; i++)
__get_user_error(regs->regs[i], &sf->uc.uc_mcontext.regs[i],
err);
__get_user_error(regs->sp, &sf->uc.uc_mcontext.sp, err);
__get_user_error(regs->pc, &sf->uc.uc_mcontext.pc, err);
__get_user_error(regs->pstate, &sf->uc.uc_mcontext.pstate, err);
/*
* Avoid sys_rt_sigreturn() restarting.
*/
forget_syscall(regs);
err |= !valid_user_regs(&regs->user_regs, current);
if (err == 0)
err = parse_user_sigframe(&user, sf);
if (err == 0 && system_supports_fpsimd()) {
arm64/sve: Signal handling support This patch implements support for saving and restoring the SVE registers around signals. A fixed-size header struct sve_context is always included in the signal frame encoding the thread's vector length at the time of signal delivery, optionally followed by a variable-layout structure encoding the SVE registers. Because of the need to preserve backwards compatibility, the FPSIMD view of the SVE registers is always dumped as a struct fpsimd_context in the usual way, in addition to any sve_context. The SVE vector registers are dumped in full, including bits 127:0 of each register which alias the corresponding FPSIMD vector registers in the hardware. To avoid any ambiguity about which alias to restore during sigreturn, the kernel always restores bits 127:0 of each SVE vector register from the fpsimd_context in the signal frame (which must be present): userspace needs to take this into account if it wants to modify the SVE vector register contents on return from a signal. FPSR and FPCR, which are used by both FPSIMD and SVE, are not included in sve_context because they are always present in fpsimd_context anyway. For signal delivery, a new helper fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:51:07 +08:00
if (!user.fpsimd)
return -EINVAL;
if (user.sve) {
if (!system_supports_sve())
return -EINVAL;
err = restore_sve_fpsimd_context(&user);
} else {
err = restore_fpsimd_context(user.fpsimd);
}
}
return err;
}
SYSCALL_DEFINE0(rt_sigreturn)
{
struct pt_regs *regs = current_pt_regs();
struct rt_sigframe __user *frame;
/* Always make any pending restarted system calls return -EINTR */
all arches, signal: move restart_block to struct task_struct If an attacker can cause a controlled kernel stack overflow, overwriting the restart block is a very juicy exploit target. This is because the restart_block is held in the same memory allocation as the kernel stack. Moving the restart block to struct task_struct prevents this exploit by making the restart_block harder to locate. Note that there are other fields in thread_info that are also easy targets, at least on some architectures. It's also a decent simplification, since the restart code is more or less identical on all architectures. [james.hogan@imgtec.com: metag: align thread_info::supervisor_stack] Signed-off-by: Andy Lutomirski <luto@amacapital.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: David Miller <davem@davemloft.net> Acked-by: Richard Weinberger <richard@nod.at> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Matt Turner <mattst88@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Haavard Skinnemoen <hskinnemoen@gmail.com> Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no> Cc: Steven Miao <realmz6@gmail.com> Cc: Mark Salter <msalter@redhat.com> Cc: Aurelien Jacquiot <a-jacquiot@ti.com> Cc: Mikael Starvik <starvik@axis.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Michal Simek <monstr@monstr.eu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Jonas Bonn <jonas@southpole.se> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Helge Deller <deller@gmx.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Tested-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Chen Liqin <liqin.linux@gmail.com> Cc: Lennox Wu <lennox.wu@gmail.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: Chris Zankel <chris@zankel.net> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Guenter Roeck <linux@roeck-us.net> Signed-off-by: James Hogan <james.hogan@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-13 07:01:14 +08:00
current->restart_block.fn = do_no_restart_syscall;
/*
* Since we stacked the signal on a 128-bit boundary, then 'sp' should
* be word aligned here.
*/
if (regs->sp & 15)
goto badframe;
frame = (struct rt_sigframe __user *)regs->sp;
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 10:57:57 +08:00
if (!access_ok(frame, sizeof (*frame)))
goto badframe;
if (restore_sigframe(regs, frame))
goto badframe;
if (restore_altstack(&frame->uc.uc_stack))
goto badframe;
return regs->regs[0];
badframe:
arm64_notify_segfault(regs->sp);
return 0;
}
arm64: signal: Report signal frame size to userspace via auxv Stateful CPU architecture extensions may require the signal frame to grow to a size that exceeds the arch's MINSIGSTKSZ #define. However, changing this #define is an ABI break. To allow userspace the option of determining the signal frame size in a more forwards-compatible way, this patch adds a new auxv entry tagged with AT_MINSIGSTKSZ, which provides the maximum signal frame size that the process can observe during its lifetime. If AT_MINSIGSTKSZ is absent from the aux vector, the caller can assume that the MINSIGSTKSZ #define is sufficient. This allows for a consistent interface with older kernels that do not provide AT_MINSIGSTKSZ. The idea is that libc could expose this via sysconf() or some similar mechanism. There is deliberately no AT_SIGSTKSZ. The kernel knows nothing about userspace's own stack overheads and should not pretend to know. For arm64: The primary motivation for this interface is the Scalable Vector Extension, which can require at least 4KB or so of extra space in the signal frame for the largest hardware implementations. To determine the correct value, a "Christmas tree" mode (via the add_all argument) is added to setup_sigframe_layout(), to simulate addition of all possible records to the signal frame at maximum possible size. If this procedure goes wrong somehow, resulting in a stupidly large frame layout and hence failure of sigframe_alloc() to allocate a record to the frame, then this is indicative of a kernel bug. In this case, we WARN() and no attempt is made to populate AT_MINSIGSTKSZ for userspace. For arm64 SVE: The SVE context block in the signal frame needs to be considered too when computing the maximum possible signal frame size. Because the size of this block depends on the vector length, this patch computes the size based not on the thread's current vector length but instead on the maximum possible vector length: this determines the maximum size of SVE context block that can be observed in any signal frame for the lifetime of the process. Signed-off-by: Dave Martin <Dave.Martin@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-06-01 18:10:14 +08:00
/*
* Determine the layout of optional records in the signal frame
*
* add_all: if true, lays out the biggest possible signal frame for
* this task; otherwise, generates a layout for the current state
* of the task.
*/
static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
bool add_all)
{
int err;
err = sigframe_alloc(user, &user->fpsimd_offset,
sizeof(struct fpsimd_context));
if (err)
return err;
/* fault information, if valid */
arm64: signal: Report signal frame size to userspace via auxv Stateful CPU architecture extensions may require the signal frame to grow to a size that exceeds the arch's MINSIGSTKSZ #define. However, changing this #define is an ABI break. To allow userspace the option of determining the signal frame size in a more forwards-compatible way, this patch adds a new auxv entry tagged with AT_MINSIGSTKSZ, which provides the maximum signal frame size that the process can observe during its lifetime. If AT_MINSIGSTKSZ is absent from the aux vector, the caller can assume that the MINSIGSTKSZ #define is sufficient. This allows for a consistent interface with older kernels that do not provide AT_MINSIGSTKSZ. The idea is that libc could expose this via sysconf() or some similar mechanism. There is deliberately no AT_SIGSTKSZ. The kernel knows nothing about userspace's own stack overheads and should not pretend to know. For arm64: The primary motivation for this interface is the Scalable Vector Extension, which can require at least 4KB or so of extra space in the signal frame for the largest hardware implementations. To determine the correct value, a "Christmas tree" mode (via the add_all argument) is added to setup_sigframe_layout(), to simulate addition of all possible records to the signal frame at maximum possible size. If this procedure goes wrong somehow, resulting in a stupidly large frame layout and hence failure of sigframe_alloc() to allocate a record to the frame, then this is indicative of a kernel bug. In this case, we WARN() and no attempt is made to populate AT_MINSIGSTKSZ for userspace. For arm64 SVE: The SVE context block in the signal frame needs to be considered too when computing the maximum possible signal frame size. Because the size of this block depends on the vector length, this patch computes the size based not on the thread's current vector length but instead on the maximum possible vector length: this determines the maximum size of SVE context block that can be observed in any signal frame for the lifetime of the process. Signed-off-by: Dave Martin <Dave.Martin@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-06-01 18:10:14 +08:00
if (add_all || current->thread.fault_code) {
err = sigframe_alloc(user, &user->esr_offset,
sizeof(struct esr_context));
if (err)
return err;
}
arm64/sve: Signal handling support This patch implements support for saving and restoring the SVE registers around signals. A fixed-size header struct sve_context is always included in the signal frame encoding the thread's vector length at the time of signal delivery, optionally followed by a variable-layout structure encoding the SVE registers. Because of the need to preserve backwards compatibility, the FPSIMD view of the SVE registers is always dumped as a struct fpsimd_context in the usual way, in addition to any sve_context. The SVE vector registers are dumped in full, including bits 127:0 of each register which alias the corresponding FPSIMD vector registers in the hardware. To avoid any ambiguity about which alias to restore during sigreturn, the kernel always restores bits 127:0 of each SVE vector register from the fpsimd_context in the signal frame (which must be present): userspace needs to take this into account if it wants to modify the SVE vector register contents on return from a signal. FPSR and FPCR, which are used by both FPSIMD and SVE, are not included in sve_context because they are always present in fpsimd_context anyway. For signal delivery, a new helper fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:51:07 +08:00
if (system_supports_sve()) {
unsigned int vq = 0;
arm64: signal: Report signal frame size to userspace via auxv Stateful CPU architecture extensions may require the signal frame to grow to a size that exceeds the arch's MINSIGSTKSZ #define. However, changing this #define is an ABI break. To allow userspace the option of determining the signal frame size in a more forwards-compatible way, this patch adds a new auxv entry tagged with AT_MINSIGSTKSZ, which provides the maximum signal frame size that the process can observe during its lifetime. If AT_MINSIGSTKSZ is absent from the aux vector, the caller can assume that the MINSIGSTKSZ #define is sufficient. This allows for a consistent interface with older kernels that do not provide AT_MINSIGSTKSZ. The idea is that libc could expose this via sysconf() or some similar mechanism. There is deliberately no AT_SIGSTKSZ. The kernel knows nothing about userspace's own stack overheads and should not pretend to know. For arm64: The primary motivation for this interface is the Scalable Vector Extension, which can require at least 4KB or so of extra space in the signal frame for the largest hardware implementations. To determine the correct value, a "Christmas tree" mode (via the add_all argument) is added to setup_sigframe_layout(), to simulate addition of all possible records to the signal frame at maximum possible size. If this procedure goes wrong somehow, resulting in a stupidly large frame layout and hence failure of sigframe_alloc() to allocate a record to the frame, then this is indicative of a kernel bug. In this case, we WARN() and no attempt is made to populate AT_MINSIGSTKSZ for userspace. For arm64 SVE: The SVE context block in the signal frame needs to be considered too when computing the maximum possible signal frame size. Because the size of this block depends on the vector length, this patch computes the size based not on the thread's current vector length but instead on the maximum possible vector length: this determines the maximum size of SVE context block that can be observed in any signal frame for the lifetime of the process. Signed-off-by: Dave Martin <Dave.Martin@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-06-01 18:10:14 +08:00
if (add_all || test_thread_flag(TIF_SVE)) {
int vl = sve_max_vl;
if (!add_all)
vl = current->thread.sve_vl;
vq = sve_vq_from_vl(vl);
}
arm64/sve: Signal handling support This patch implements support for saving and restoring the SVE registers around signals. A fixed-size header struct sve_context is always included in the signal frame encoding the thread's vector length at the time of signal delivery, optionally followed by a variable-layout structure encoding the SVE registers. Because of the need to preserve backwards compatibility, the FPSIMD view of the SVE registers is always dumped as a struct fpsimd_context in the usual way, in addition to any sve_context. The SVE vector registers are dumped in full, including bits 127:0 of each register which alias the corresponding FPSIMD vector registers in the hardware. To avoid any ambiguity about which alias to restore during sigreturn, the kernel always restores bits 127:0 of each SVE vector register from the fpsimd_context in the signal frame (which must be present): userspace needs to take this into account if it wants to modify the SVE vector register contents on return from a signal. FPSR and FPCR, which are used by both FPSIMD and SVE, are not included in sve_context because they are always present in fpsimd_context anyway. For signal delivery, a new helper fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:51:07 +08:00
err = sigframe_alloc(user, &user->sve_offset,
SVE_SIG_CONTEXT_SIZE(vq));
if (err)
return err;
}
return sigframe_alloc_end(user);
}
static int setup_sigframe(struct rt_sigframe_user_layout *user,
struct pt_regs *regs, sigset_t *set)
{
int i, err = 0;
struct rt_sigframe __user *sf = user->sigframe;
/* set up the stack frame for unwinding */
__put_user_error(regs->regs[29], &user->next_frame->fp, err);
__put_user_error(regs->regs[30], &user->next_frame->lr, err);
for (i = 0; i < 31; i++)
__put_user_error(regs->regs[i], &sf->uc.uc_mcontext.regs[i],
err);
__put_user_error(regs->sp, &sf->uc.uc_mcontext.sp, err);
__put_user_error(regs->pc, &sf->uc.uc_mcontext.pc, err);
__put_user_error(regs->pstate, &sf->uc.uc_mcontext.pstate, err);
__put_user_error(current->thread.fault_address, &sf->uc.uc_mcontext.fault_address, err);
err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set));
if (err == 0 && system_supports_fpsimd()) {
struct fpsimd_context __user *fpsimd_ctx =
apply_user_offset(user, user->fpsimd_offset);
err |= preserve_fpsimd_context(fpsimd_ctx);
}
/* fault information, if valid */
if (err == 0 && user->esr_offset) {
struct esr_context __user *esr_ctx =
apply_user_offset(user, user->esr_offset);
__put_user_error(ESR_MAGIC, &esr_ctx->head.magic, err);
__put_user_error(sizeof(*esr_ctx), &esr_ctx->head.size, err);
__put_user_error(current->thread.fault_code, &esr_ctx->esr, err);
}
arm64/sve: Signal handling support This patch implements support for saving and restoring the SVE registers around signals. A fixed-size header struct sve_context is always included in the signal frame encoding the thread's vector length at the time of signal delivery, optionally followed by a variable-layout structure encoding the SVE registers. Because of the need to preserve backwards compatibility, the FPSIMD view of the SVE registers is always dumped as a struct fpsimd_context in the usual way, in addition to any sve_context. The SVE vector registers are dumped in full, including bits 127:0 of each register which alias the corresponding FPSIMD vector registers in the hardware. To avoid any ambiguity about which alias to restore during sigreturn, the kernel always restores bits 127:0 of each SVE vector register from the fpsimd_context in the signal frame (which must be present): userspace needs to take this into account if it wants to modify the SVE vector register contents on return from a signal. FPSR and FPCR, which are used by both FPSIMD and SVE, are not included in sve_context because they are always present in fpsimd_context anyway. For signal delivery, a new helper fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:51:07 +08:00
/* Scalable Vector Extension state, if present */
if (system_supports_sve() && err == 0 && user->sve_offset) {
struct sve_context __user *sve_ctx =
apply_user_offset(user, user->sve_offset);
err |= preserve_sve_context(sve_ctx);
}
if (err == 0 && user->extra_offset) {
char __user *sfp = (char __user *)user->sigframe;
char __user *userp =
apply_user_offset(user, user->extra_offset);
struct extra_context __user *extra;
struct _aarch64_ctx __user *end;
u64 extra_datap;
u32 extra_size;
extra = (struct extra_context __user *)userp;
userp += EXTRA_CONTEXT_SIZE;
end = (struct _aarch64_ctx __user *)userp;
userp += TERMINATOR_SIZE;
/*
* extra_datap is just written to the signal frame.
* The value gets cast back to a void __user *
* during sigreturn.
*/
extra_datap = (__force u64)userp;
extra_size = sfp + round_up(user->size, 16) - userp;
__put_user_error(EXTRA_MAGIC, &extra->head.magic, err);
__put_user_error(EXTRA_CONTEXT_SIZE, &extra->head.size, err);
__put_user_error(extra_datap, &extra->datap, err);
__put_user_error(extra_size, &extra->size, err);
/* Add the terminator */
__put_user_error(0, &end->magic, err);
__put_user_error(0, &end->size, err);
}
/* set the "end" magic */
if (err == 0) {
struct _aarch64_ctx __user *end =
apply_user_offset(user, user->end_offset);
__put_user_error(0, &end->magic, err);
__put_user_error(0, &end->size, err);
}
return err;
}
static int get_sigframe(struct rt_sigframe_user_layout *user,
struct ksignal *ksig, struct pt_regs *regs)
{
unsigned long sp, sp_top;
int err;
init_user_layout(user);
arm64: signal: Report signal frame size to userspace via auxv Stateful CPU architecture extensions may require the signal frame to grow to a size that exceeds the arch's MINSIGSTKSZ #define. However, changing this #define is an ABI break. To allow userspace the option of determining the signal frame size in a more forwards-compatible way, this patch adds a new auxv entry tagged with AT_MINSIGSTKSZ, which provides the maximum signal frame size that the process can observe during its lifetime. If AT_MINSIGSTKSZ is absent from the aux vector, the caller can assume that the MINSIGSTKSZ #define is sufficient. This allows for a consistent interface with older kernels that do not provide AT_MINSIGSTKSZ. The idea is that libc could expose this via sysconf() or some similar mechanism. There is deliberately no AT_SIGSTKSZ. The kernel knows nothing about userspace's own stack overheads and should not pretend to know. For arm64: The primary motivation for this interface is the Scalable Vector Extension, which can require at least 4KB or so of extra space in the signal frame for the largest hardware implementations. To determine the correct value, a "Christmas tree" mode (via the add_all argument) is added to setup_sigframe_layout(), to simulate addition of all possible records to the signal frame at maximum possible size. If this procedure goes wrong somehow, resulting in a stupidly large frame layout and hence failure of sigframe_alloc() to allocate a record to the frame, then this is indicative of a kernel bug. In this case, we WARN() and no attempt is made to populate AT_MINSIGSTKSZ for userspace. For arm64 SVE: The SVE context block in the signal frame needs to be considered too when computing the maximum possible signal frame size. Because the size of this block depends on the vector length, this patch computes the size based not on the thread's current vector length but instead on the maximum possible vector length: this determines the maximum size of SVE context block that can be observed in any signal frame for the lifetime of the process. Signed-off-by: Dave Martin <Dave.Martin@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-06-01 18:10:14 +08:00
err = setup_sigframe_layout(user, false);
if (err)
return err;
sp = sp_top = sigsp(regs->sp, ksig);
sp = round_down(sp - sizeof(struct frame_record), 16);
user->next_frame = (struct frame_record __user *)sp;
sp = round_down(sp, 16) - sigframe_size(user);
user->sigframe = (struct rt_sigframe __user *)sp;
/*
* Check that we can actually write to the signal frame.
*/
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 10:57:57 +08:00
if (!access_ok(user->sigframe, sp_top - sp))
return -EFAULT;
return 0;
}
static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
struct rt_sigframe_user_layout *user, int usig)
{
__sigrestore_t sigtramp;
regs->regs[0] = usig;
regs->sp = (unsigned long)user->sigframe;
regs->regs[29] = (unsigned long)&user->next_frame->fp;
regs->pc = (unsigned long)ka->sa.sa_handler;
/*
* Signal delivery is a (wacky) indirect function call in
* userspace, so simulate the same setting of BTYPE as a BLR
* <register containing the signal handler entry point>.
* Signal delivery to a location in a PROT_BTI guarded page
* that is not a function entry point will now trigger a
* SIGILL in userspace.
*
* If the signal handler entry point is not in a PROT_BTI
* guarded page, this is harmless.
*/
if (system_supports_bti()) {
regs->pstate &= ~PSR_BTYPE_MASK;
regs->pstate |= PSR_BTYPE_C;
}
/* TCO (Tag Check Override) always cleared for signal handlers */
regs->pstate &= ~PSR_TCO_BIT;
if (ka->sa.sa_flags & SA_RESTORER)
sigtramp = ka->sa.sa_restorer;
else
sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp);
regs->regs[30] = (unsigned long)sigtramp;
}
static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
struct pt_regs *regs)
{
struct rt_sigframe_user_layout user;
struct rt_sigframe __user *frame;
int err = 0;
arm64/sve: Signal handling support This patch implements support for saving and restoring the SVE registers around signals. A fixed-size header struct sve_context is always included in the signal frame encoding the thread's vector length at the time of signal delivery, optionally followed by a variable-layout structure encoding the SVE registers. Because of the need to preserve backwards compatibility, the FPSIMD view of the SVE registers is always dumped as a struct fpsimd_context in the usual way, in addition to any sve_context. The SVE vector registers are dumped in full, including bits 127:0 of each register which alias the corresponding FPSIMD vector registers in the hardware. To avoid any ambiguity about which alias to restore during sigreturn, the kernel always restores bits 127:0 of each SVE vector register from the fpsimd_context in the signal frame (which must be present): userspace needs to take this into account if it wants to modify the SVE vector register contents on return from a signal. FPSR and FPCR, which are used by both FPSIMD and SVE, are not included in sve_context because they are always present in fpsimd_context anyway. For signal delivery, a new helper fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Dave Martin <Dave.Martin@arm.com> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2017-10-31 23:51:07 +08:00
fpsimd_signal_preserve_current_state();
if (get_sigframe(&user, ksig, regs))
return 1;
frame = user.sigframe;
__put_user_error(0, &frame->uc.uc_flags, err);
__put_user_error(NULL, &frame->uc.uc_link, err);
err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
err |= setup_sigframe(&user, regs, set);
if (err == 0) {
setup_return(regs, &ksig->ka, &user, usig);
if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
err |= copy_siginfo_to_user(&frame->info, &ksig->info);
regs->regs[1] = (unsigned long)&frame->info;
regs->regs[2] = (unsigned long)&frame->uc;
}
}
return err;
}
static void setup_restart_syscall(struct pt_regs *regs)
{
if (is_compat_task())
compat_setup_restart_syscall(regs);
else
regs->regs[8] = __NR_restart_syscall;
}
/*
* OK, we're invoking a handler
*/
static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
{
sigset_t *oldset = sigmask_to_save();
int usig = ksig->sig;
int ret;
rseq_signal_deliver(ksig, regs);
/*
* Set up the stack frame
*/
if (is_compat_task()) {
if (ksig->ka.sa.sa_flags & SA_SIGINFO)
ret = compat_setup_rt_frame(usig, ksig, oldset, regs);
else
ret = compat_setup_frame(usig, ksig, oldset, regs);
} else {
ret = setup_rt_frame(usig, ksig, oldset, regs);
}
/*
* Check that the resulting registers are actually sane.
*/
ret |= !valid_user_regs(&regs->user_regs, current);
/* Step into the signal handler if we are stepping */
signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP));
}
/*
* Note that 'init' is a special process: it doesn't get signals it doesn't
* want to handle. Thus you cannot kill init even with a SIGKILL even by
* mistake.
*
* Note that we go through the signals twice: once to check the signals that
* the kernel can handle, and then we build all the user-level signal handling
* stack-frames in one go after that.
*/
static void do_signal(struct pt_regs *regs)
{
unsigned long continue_addr = 0, restart_addr = 0;
int retval = 0;
struct ksignal ksig;
arm64: Fix syscall restarting around signal suppressed by tracer Commit 17c2895 ("arm64: Abstract syscallno manipulation") abstracts out the pt_regs.syscallno value for a syscall cancelled by a tracer as NO_SYSCALL, and provides helpers to set and check for this condition. However, the way this was implemented has the unintended side-effect of disabling part of the syscall restart logic. This comes about because the second in_syscall() check in do_signal() re-evaluates the "in a syscall" condition based on the updated pt_regs instead of the original pt_regs. forget_syscall() is explicitly called prior to the second check in order to prevent restart logic in the ret_to_user path being spuriously triggered, which means that the second in_syscall() check always yields false. This triggers a failure in tools/testing/selftests/seccomp/seccomp_bpf.c, when using ptrace to suppress a signal that interrups a nanosleep() syscall. Misbehaviour of this type is only expected in the case where a tracer suppresses a signal and the target process is either being single-stepped or the interrupted syscall attempts to restart via -ERESTARTBLOCK. This patch restores the old behaviour by performing the in_syscall() check only once at the start of the function. Fixes: 17c289586009 ("arm64: Abstract syscallno manipulation") Signed-off-by: Dave Martin <Dave.Martin@arm.com> Reported-by: Sumit Semwal <sumit.semwal@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Cc: <stable@vger.kernel.org> # 4.14.x- Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-06-07 19:32:05 +08:00
bool syscall = in_syscall(regs);
/*
* If we were from a system call, check for system call restarting...
*/
arm64: Fix syscall restarting around signal suppressed by tracer Commit 17c2895 ("arm64: Abstract syscallno manipulation") abstracts out the pt_regs.syscallno value for a syscall cancelled by a tracer as NO_SYSCALL, and provides helpers to set and check for this condition. However, the way this was implemented has the unintended side-effect of disabling part of the syscall restart logic. This comes about because the second in_syscall() check in do_signal() re-evaluates the "in a syscall" condition based on the updated pt_regs instead of the original pt_regs. forget_syscall() is explicitly called prior to the second check in order to prevent restart logic in the ret_to_user path being spuriously triggered, which means that the second in_syscall() check always yields false. This triggers a failure in tools/testing/selftests/seccomp/seccomp_bpf.c, when using ptrace to suppress a signal that interrups a nanosleep() syscall. Misbehaviour of this type is only expected in the case where a tracer suppresses a signal and the target process is either being single-stepped or the interrupted syscall attempts to restart via -ERESTARTBLOCK. This patch restores the old behaviour by performing the in_syscall() check only once at the start of the function. Fixes: 17c289586009 ("arm64: Abstract syscallno manipulation") Signed-off-by: Dave Martin <Dave.Martin@arm.com> Reported-by: Sumit Semwal <sumit.semwal@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Cc: <stable@vger.kernel.org> # 4.14.x- Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-06-07 19:32:05 +08:00
if (syscall) {
continue_addr = regs->pc;
restart_addr = continue_addr - (compat_thumb_mode(regs) ? 2 : 4);
retval = regs->regs[0];
/*
* Avoid additional syscall restarting via ret_to_user.
*/
forget_syscall(regs);
/*
* Prepare for system call restart. We do this here so that a
* debugger will see the already changed PC.
*/
switch (retval) {
case -ERESTARTNOHAND:
case -ERESTARTSYS:
case -ERESTARTNOINTR:
case -ERESTART_RESTARTBLOCK:
regs->regs[0] = regs->orig_x0;
regs->pc = restart_addr;
break;
}
}
/*
* Get the signal to deliver. When running under ptrace, at this point
* the debugger may change all of our registers.
*/
if (get_signal(&ksig)) {
/*
* Depending on the signal settings, we may need to revert the
* decision to restart the system call, but skip this if a
* debugger has chosen to restart at a different PC.
*/
if (regs->pc == restart_addr &&
(retval == -ERESTARTNOHAND ||
retval == -ERESTART_RESTARTBLOCK ||
(retval == -ERESTARTSYS &&
!(ksig.ka.sa.sa_flags & SA_RESTART)))) {
regs->regs[0] = -EINTR;
regs->pc = continue_addr;
}
handle_signal(&ksig, regs);
return;
}
/*
* Handle restarting a different system call. As above, if a debugger
* has chosen to restart at a different PC, ignore the restart.
*/
arm64: Fix syscall restarting around signal suppressed by tracer Commit 17c2895 ("arm64: Abstract syscallno manipulation") abstracts out the pt_regs.syscallno value for a syscall cancelled by a tracer as NO_SYSCALL, and provides helpers to set and check for this condition. However, the way this was implemented has the unintended side-effect of disabling part of the syscall restart logic. This comes about because the second in_syscall() check in do_signal() re-evaluates the "in a syscall" condition based on the updated pt_regs instead of the original pt_regs. forget_syscall() is explicitly called prior to the second check in order to prevent restart logic in the ret_to_user path being spuriously triggered, which means that the second in_syscall() check always yields false. This triggers a failure in tools/testing/selftests/seccomp/seccomp_bpf.c, when using ptrace to suppress a signal that interrups a nanosleep() syscall. Misbehaviour of this type is only expected in the case where a tracer suppresses a signal and the target process is either being single-stepped or the interrupted syscall attempts to restart via -ERESTARTBLOCK. This patch restores the old behaviour by performing the in_syscall() check only once at the start of the function. Fixes: 17c289586009 ("arm64: Abstract syscallno manipulation") Signed-off-by: Dave Martin <Dave.Martin@arm.com> Reported-by: Sumit Semwal <sumit.semwal@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Cc: <stable@vger.kernel.org> # 4.14.x- Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-06-07 19:32:05 +08:00
if (syscall && regs->pc == restart_addr) {
if (retval == -ERESTART_RESTARTBLOCK)
setup_restart_syscall(regs);
user_rewind_single_step(current);
}
restore_saved_sigmask();
}
asmlinkage void do_notify_resume(struct pt_regs *regs,
unsigned long thread_flags)
{
/*
* The assembly code enters us with IRQs off, but it hasn't
* informed the tracing code of that for efficiency reasons.
* Update the trace code with the current status.
*/
trace_hardirqs_off();
arm64/syscalls: Check address limit on user-mode return Ensure the address limit is a user-mode segment before returning to user-mode. Otherwise a process can corrupt kernel-mode memory and elevate privileges [1]. The set_fs function sets the TIF_SETFS flag to force a slow path on return. In the slow path, the address limit is checked to be USER_DS if needed. [1] https://bugs.chromium.org/p/project-zero/issues/detail?id=990 Signed-off-by: Thomas Garnier <thgarnie@google.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Mark Rutland <mark.rutland@arm.com> Cc: kernel-hardening@lists.openwall.com Cc: Will Deacon <will.deacon@arm.com> Cc: David Howells <dhowells@redhat.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Miroslav Benes <mbenes@suse.cz> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Pratyush Anand <panand@redhat.com> Cc: Russell King <linux@armlinux.org.uk> Cc: Petr Mladek <pmladek@suse.com> Cc: Rik van Riel <riel@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andy Lutomirski <luto@kernel.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: linux-arm-kernel@lists.infradead.org Cc: Will Drewry <wad@chromium.org> Cc: linux-api@vger.kernel.org Cc: Oleg Nesterov <oleg@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Paolo Bonzini <pbonzini@redhat.com> Link: http://lkml.kernel.org/r/20170615011203.144108-3-thgarnie@google.com
2017-06-15 09:12:03 +08:00
do {
/* Check valid user FS if needed */
addr_limit_user_check();
if (thread_flags & _TIF_NEED_RESCHED) {
/* Unmask Debug and SError for the next task */
local_daif_restore(DAIF_PROCCTX_NOIRQ);
schedule();
} else {
local_daif_restore(DAIF_PROCCTX);
if (thread_flags & _TIF_UPROBE)
uprobe_notify_resume(regs);
if (thread_flags & _TIF_MTE_ASYNC_FAULT) {
clear_thread_flag(TIF_MTE_ASYNC_FAULT);
send_sig_fault(SIGSEGV, SEGV_MTEAERR,
(void __user *)NULL, current);
}
if (thread_flags & _TIF_SIGPENDING)
do_signal(regs);
if (thread_flags & _TIF_NOTIFY_RESUME) {
tracehook_notify_resume(regs);
rseq_handle_notify_resume(NULL, regs);
}
if (thread_flags & _TIF_FOREIGN_FPSTATE)
fpsimd_restore_current_state();
}
local_daif_mask();
thread_flags = READ_ONCE(current_thread_info()->flags);
} while (thread_flags & _TIF_WORK_MASK);
}
arm64: signal: Report signal frame size to userspace via auxv Stateful CPU architecture extensions may require the signal frame to grow to a size that exceeds the arch's MINSIGSTKSZ #define. However, changing this #define is an ABI break. To allow userspace the option of determining the signal frame size in a more forwards-compatible way, this patch adds a new auxv entry tagged with AT_MINSIGSTKSZ, which provides the maximum signal frame size that the process can observe during its lifetime. If AT_MINSIGSTKSZ is absent from the aux vector, the caller can assume that the MINSIGSTKSZ #define is sufficient. This allows for a consistent interface with older kernels that do not provide AT_MINSIGSTKSZ. The idea is that libc could expose this via sysconf() or some similar mechanism. There is deliberately no AT_SIGSTKSZ. The kernel knows nothing about userspace's own stack overheads and should not pretend to know. For arm64: The primary motivation for this interface is the Scalable Vector Extension, which can require at least 4KB or so of extra space in the signal frame for the largest hardware implementations. To determine the correct value, a "Christmas tree" mode (via the add_all argument) is added to setup_sigframe_layout(), to simulate addition of all possible records to the signal frame at maximum possible size. If this procedure goes wrong somehow, resulting in a stupidly large frame layout and hence failure of sigframe_alloc() to allocate a record to the frame, then this is indicative of a kernel bug. In this case, we WARN() and no attempt is made to populate AT_MINSIGSTKSZ for userspace. For arm64 SVE: The SVE context block in the signal frame needs to be considered too when computing the maximum possible signal frame size. Because the size of this block depends on the vector length, this patch computes the size based not on the thread's current vector length but instead on the maximum possible vector length: this determines the maximum size of SVE context block that can be observed in any signal frame for the lifetime of the process. Signed-off-by: Dave Martin <Dave.Martin@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-06-01 18:10:14 +08:00
unsigned long __ro_after_init signal_minsigstksz;
/*
* Determine the stack space required for guaranteed signal devliery.
* This function is used to populate AT_MINSIGSTKSZ at process startup.
* cpufeatures setup is assumed to be complete.
*/
void __init minsigstksz_setup(void)
{
struct rt_sigframe_user_layout user;
init_user_layout(&user);
/*
* If this fails, SIGFRAME_MAXSZ needs to be enlarged. It won't
* be big enough, but it's our best guess:
*/
if (WARN_ON(setup_sigframe_layout(&user, true)))
return;
signal_minsigstksz = sigframe_size(&user) +
round_up(sizeof(struct frame_record), 16) +
16; /* max alignment padding */
}