MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
#include <linux/err.h>
|
|
|
|
|
#include <linux/slab.h>
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <asm/branch.h>
|
|
|
|
|
#include <asm/cacheflush.h>
|
|
|
|
|
#include <asm/fpu_emulator.h>
|
2014-04-16 08:09:53 +08:00
|
|
|
#include <asm/inst.h>
|
|
|
|
|
#include <asm/mipsregs.h>
|
|
|
|
|
#include <asm/uaccess.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
/**
|
|
|
|
|
* struct emuframe - The 'emulation' frame structure
|
|
|
|
|
* @emul: The instruction to 'emulate'.
|
|
|
|
|
* @badinst: A break instruction to cause a return to the kernel.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
* This structure defines the frames placed within the delay slot emulation
|
|
|
|
|
* page in response to a call to mips_dsemul(). Each thread may be allocated
|
|
|
|
|
* only one frame at any given time. The kernel stores within it the
|
|
|
|
|
* instruction to be 'emulated' followed by a break instruction, then
|
|
|
|
|
* executes the frame in user mode. The break causes a trap to the kernel
|
|
|
|
|
* which leads to do_dsemulret() being called unless the instruction in
|
|
|
|
|
* @emul causes a trap itself, is a branch, or a signal is delivered to
|
|
|
|
|
* the thread. In these cases the allocated frame will either be reused by
|
|
|
|
|
* a subsequent delay slot 'emulation', or be freed during signal delivery or
|
|
|
|
|
* upon thread exit.
|
|
|
|
|
*
|
|
|
|
|
* This approach is used because:
|
|
|
|
|
*
|
|
|
|
|
* - Actually emulating all instructions isn't feasible. We would need to
|
|
|
|
|
* be able to handle instructions from all revisions of the MIPS ISA,
|
|
|
|
|
* all ASEs & all vendor instruction set extensions. This would be a
|
|
|
|
|
* whole lot of work & continual maintenance burden as new instructions
|
|
|
|
|
* are introduced, and in the case of some vendor extensions may not
|
|
|
|
|
* even be possible. Thus we need to take the approach of actually
|
|
|
|
|
* executing the instruction.
|
|
|
|
|
*
|
|
|
|
|
* - We must execute the instruction within user context. If we were to
|
|
|
|
|
* execute the instruction in kernel mode then it would have access to
|
|
|
|
|
* kernel resources without very careful checks, leaving us with a
|
|
|
|
|
* high potential for security or stability issues to arise.
|
|
|
|
|
*
|
|
|
|
|
* - We used to place the frame on the users stack, but this requires
|
|
|
|
|
* that the stack be executable. This is bad for security so the
|
|
|
|
|
* per-process page is now used instead.
|
|
|
|
|
*
|
|
|
|
|
* - The instruction in @emul may be something entirely invalid for a
|
|
|
|
|
* delay slot. The user may (intentionally or otherwise) place a branch
|
|
|
|
|
* in a delay slot, or a kernel mode instruction, or something else
|
|
|
|
|
* which generates an exception. Thus we can't rely upon the break in
|
|
|
|
|
* @badinst always being hit. For this reason we track the index of the
|
|
|
|
|
* frame allocated to each thread, allowing us to clean it up at later
|
|
|
|
|
* points such as signal delivery or thread exit.
|
|
|
|
|
*
|
|
|
|
|
* - The user may generate a fake struct emuframe if they wish, invoking
|
|
|
|
|
* the BRK_MEMU break instruction themselves. We must therefore not
|
|
|
|
|
* trust that BRK_MEMU means there's actually a valid frame allocated
|
|
|
|
|
* to the thread, and must not allow the user to do anything they
|
|
|
|
|
* couldn't already.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
struct emuframe {
|
|
|
|
|
mips_instruction emul;
|
|
|
|
|
mips_instruction badinst;
|
|
|
|
|
};
|
|
|
|
|
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
static const int emupage_frame_count = PAGE_SIZE / sizeof(struct emuframe);
|
|
|
|
|
|
|
|
|
|
static inline __user struct emuframe *dsemul_page(void)
|
|
|
|
|
{
|
|
|
|
|
return (__user struct emuframe *)STACK_TOP;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int alloc_emuframe(void)
|
|
|
|
|
{
|
|
|
|
|
mm_context_t *mm_ctx = ¤t->mm->context;
|
|
|
|
|
int idx;
|
|
|
|
|
|
|
|
|
|
retry:
|
|
|
|
|
spin_lock(&mm_ctx->bd_emupage_lock);
|
|
|
|
|
|
|
|
|
|
/* Ensure we have an allocation bitmap */
|
|
|
|
|
if (!mm_ctx->bd_emupage_allocmap) {
|
|
|
|
|
mm_ctx->bd_emupage_allocmap =
|
|
|
|
|
kcalloc(BITS_TO_LONGS(emupage_frame_count),
|
|
|
|
|
sizeof(unsigned long),
|
|
|
|
|
GFP_ATOMIC);
|
|
|
|
|
|
|
|
|
|
if (!mm_ctx->bd_emupage_allocmap) {
|
|
|
|
|
idx = BD_EMUFRAME_NONE;
|
|
|
|
|
goto out_unlock;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Attempt to allocate a single bit/frame */
|
|
|
|
|
idx = bitmap_find_free_region(mm_ctx->bd_emupage_allocmap,
|
|
|
|
|
emupage_frame_count, 0);
|
|
|
|
|
if (idx < 0) {
|
|
|
|
|
/*
|
|
|
|
|
* Failed to allocate a frame. We'll wait until one becomes
|
|
|
|
|
* available. We unlock the page so that other threads actually
|
|
|
|
|
* get the opportunity to free their frames, which means
|
|
|
|
|
* technically the result of bitmap_full may be incorrect.
|
|
|
|
|
* However the worst case is that we repeat all this and end up
|
|
|
|
|
* back here again.
|
|
|
|
|
*/
|
|
|
|
|
spin_unlock(&mm_ctx->bd_emupage_lock);
|
|
|
|
|
if (!wait_event_killable(mm_ctx->bd_emupage_queue,
|
|
|
|
|
!bitmap_full(mm_ctx->bd_emupage_allocmap,
|
|
|
|
|
emupage_frame_count)))
|
|
|
|
|
goto retry;
|
|
|
|
|
|
|
|
|
|
/* Received a fatal signal - just give in */
|
|
|
|
|
return BD_EMUFRAME_NONE;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Success! */
|
|
|
|
|
pr_debug("allocate emuframe %d to %d\n", idx, current->pid);
|
|
|
|
|
out_unlock:
|
|
|
|
|
spin_unlock(&mm_ctx->bd_emupage_lock);
|
|
|
|
|
return idx;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void free_emuframe(int idx, struct mm_struct *mm)
|
|
|
|
|
{
|
|
|
|
|
mm_context_t *mm_ctx = &mm->context;
|
|
|
|
|
|
|
|
|
|
spin_lock(&mm_ctx->bd_emupage_lock);
|
|
|
|
|
|
|
|
|
|
pr_debug("free emuframe %d from %d\n", idx, current->pid);
|
|
|
|
|
bitmap_clear(mm_ctx->bd_emupage_allocmap, idx, 1);
|
|
|
|
|
|
|
|
|
|
/* If some thread is waiting for a frame, now's its chance */
|
|
|
|
|
wake_up(&mm_ctx->bd_emupage_queue);
|
|
|
|
|
|
|
|
|
|
spin_unlock(&mm_ctx->bd_emupage_lock);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static bool within_emuframe(struct pt_regs *regs)
|
|
|
|
|
{
|
|
|
|
|
unsigned long base = (unsigned long)dsemul_page();
|
|
|
|
|
|
|
|
|
|
if (regs->cp0_epc < base)
|
|
|
|
|
return false;
|
|
|
|
|
if (regs->cp0_epc >= (base + PAGE_SIZE))
|
|
|
|
|
return false;
|
|
|
|
|
|
|
|
|
|
return true;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
bool dsemul_thread_cleanup(struct task_struct *tsk)
|
|
|
|
|
{
|
|
|
|
|
int fr_idx;
|
|
|
|
|
|
|
|
|
|
/* Clear any allocated frame, retrieving its index */
|
|
|
|
|
fr_idx = atomic_xchg(&tsk->thread.bd_emu_frame, BD_EMUFRAME_NONE);
|
|
|
|
|
|
|
|
|
|
/* If no frame was allocated, we're done */
|
|
|
|
|
if (fr_idx == BD_EMUFRAME_NONE)
|
|
|
|
|
return false;
|
|
|
|
|
|
|
|
|
|
task_lock(tsk);
|
|
|
|
|
|
|
|
|
|
/* Free the frame that this thread had allocated */
|
|
|
|
|
if (tsk->mm)
|
|
|
|
|
free_emuframe(fr_idx, tsk->mm);
|
|
|
|
|
|
|
|
|
|
task_unlock(tsk);
|
|
|
|
|
return true;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
bool dsemul_thread_rollback(struct pt_regs *regs)
|
|
|
|
|
{
|
|
|
|
|
struct emuframe __user *fr;
|
|
|
|
|
int fr_idx;
|
|
|
|
|
|
|
|
|
|
/* Do nothing if we're not executing from a frame */
|
|
|
|
|
if (!within_emuframe(regs))
|
|
|
|
|
return false;
|
|
|
|
|
|
|
|
|
|
/* Find the frame being executed */
|
|
|
|
|
fr_idx = atomic_read(¤t->thread.bd_emu_frame);
|
|
|
|
|
if (fr_idx == BD_EMUFRAME_NONE)
|
|
|
|
|
return false;
|
|
|
|
|
fr = &dsemul_page()[fr_idx];
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* If the PC is at the emul instruction, roll back to the branch. If
|
|
|
|
|
* PC is at the badinst (break) instruction, we've already emulated the
|
|
|
|
|
* instruction so progress to the continue PC. If it's anything else
|
|
|
|
|
* then something is amiss & the user has branched into some other area
|
|
|
|
|
* of the emupage - we'll free the allocated frame anyway.
|
|
|
|
|
*/
|
|
|
|
|
if (msk_isa16_mode(regs->cp0_epc) == (unsigned long)&fr->emul)
|
|
|
|
|
regs->cp0_epc = current->thread.bd_emu_branch_pc;
|
|
|
|
|
else if (msk_isa16_mode(regs->cp0_epc) == (unsigned long)&fr->badinst)
|
|
|
|
|
regs->cp0_epc = current->thread.bd_emu_cont_pc;
|
|
|
|
|
|
|
|
|
|
atomic_set(¤t->thread.bd_emu_frame, BD_EMUFRAME_NONE);
|
|
|
|
|
free_emuframe(fr_idx, current->mm);
|
|
|
|
|
return true;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void dsemul_mm_cleanup(struct mm_struct *mm)
|
|
|
|
|
{
|
|
|
|
|
mm_context_t *mm_ctx = &mm->context;
|
|
|
|
|
|
|
|
|
|
kfree(mm_ctx->bd_emupage_allocmap);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
int mips_dsemul(struct pt_regs *regs, mips_instruction ir,
|
|
|
|
|
unsigned long branch_pc, unsigned long cont_pc)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2016-01-22 13:21:47 +08:00
|
|
|
int isa16 = get_isa16_mode(regs->cp0_epc);
|
2016-01-22 13:20:46 +08:00
|
|
|
mips_instruction break_math;
|
2007-07-13 22:02:42 +08:00
|
|
|
struct emuframe __user *fr;
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
int err, fr_idx;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
MIPS: math-emu: Correctly handle NOP emulation
Fix an issue introduced with commit 9ab4471c9f1b ("MIPS: math-emu:
Correct delay-slot exception propagation") where the emulation of a NOP
instruction signals the need to terminate the emulation loop. This in
turn, if the PC has not changed from the entry to the loop, will cause
the kernel to terminate the program with SIGILL.
Consider this program:
static double div(double d)
{
do
d /= 2.0;
while (d > .5);
return d;
}
int main(int argc, char **argv)
{
return div(argc);
}
which gets compiled to the following binary code:
00400490 <main>:
400490: 44840000 mtc1 a0,$f0
400494: 3c020040 lui v0,0x40
400498: d44207f8 ldc1 $f2,2040(v0)
40049c: 46800021 cvt.d.w $f0,$f0
4004a0: 46220002 mul.d $f0,$f0,$f2
4004a4: 4620103c c.lt.d $f2,$f0
4004a8: 4501fffd bc1t 4004a0 <main+0x10>
4004ac: 00000000 nop
4004b0: 4620000d trunc.w.d $f0,$f0
4004b4: 03e00008 jr ra
4004b8: 44020000 mfc1 v0,$f0
4004bc: 00000000 nop
Where the FPU emulator is used, depending on the number of command-line
arguments this code will either run to completion or terminate with
SIGILL.
If no arguments are specified, then BC1T will not be taken, NOP will not
be emulated and code will complete successfully.
If one argument is specified, then BC1T will be taken once and NOP will
be emulated. At this point the entry PC value will be 0x400498 and the
new PC value, set by `mips_dsemul' will be 0x4004a0, the target of BC1T.
The emulation loop will terminate, but SIGILL will not be issued,
because the PC has changed. The FPU emulator will be entered again and
on the second execution BC1T will not be taken, NOP will not be emulated
and code will complete successfully.
If two or more arguments are specified, then the first execution of BC1T
will proceed as above. Upon reentering the FPU emulator the emulation
loop will continue to BC1T, at which point the branch will be taken and
NOP emulated again. At this point however the entry PC value will be
0x4004a0, the same as the target of BC1T. This will make the emulator
conclude that execution has not advanced and therefore an unsupported
FPU instruction has been encountered, and SIGILL will be sent to the
process.
Fix the problem by extending the internal API of `mips_dsemul', making
it return -1 if no delay slot emulation frame has been made, the
instruction has been handled and execution of the emulation loop needs
to continue as if nothing happened. Remove code from `mips_dsemul' to
reproduce steps made by the emulation loop at the conclusion of each
iteration, as those will be reached normally now. Adjust call sites
accordingly. Document the API.
Signed-off-by: Maciej W. Rozycki <macro@imgtec.com>
Cc: Aurelien Jarno <aurelien@aurel32.net>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/12172/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-01-22 13:20:26 +08:00
|
|
|
/* NOP is easy */
|
2016-01-22 13:21:00 +08:00
|
|
|
if (ir == 0)
|
MIPS: math-emu: Correctly handle NOP emulation
Fix an issue introduced with commit 9ab4471c9f1b ("MIPS: math-emu:
Correct delay-slot exception propagation") where the emulation of a NOP
instruction signals the need to terminate the emulation loop. This in
turn, if the PC has not changed from the entry to the loop, will cause
the kernel to terminate the program with SIGILL.
Consider this program:
static double div(double d)
{
do
d /= 2.0;
while (d > .5);
return d;
}
int main(int argc, char **argv)
{
return div(argc);
}
which gets compiled to the following binary code:
00400490 <main>:
400490: 44840000 mtc1 a0,$f0
400494: 3c020040 lui v0,0x40
400498: d44207f8 ldc1 $f2,2040(v0)
40049c: 46800021 cvt.d.w $f0,$f0
4004a0: 46220002 mul.d $f0,$f0,$f2
4004a4: 4620103c c.lt.d $f2,$f0
4004a8: 4501fffd bc1t 4004a0 <main+0x10>
4004ac: 00000000 nop
4004b0: 4620000d trunc.w.d $f0,$f0
4004b4: 03e00008 jr ra
4004b8: 44020000 mfc1 v0,$f0
4004bc: 00000000 nop
Where the FPU emulator is used, depending on the number of command-line
arguments this code will either run to completion or terminate with
SIGILL.
If no arguments are specified, then BC1T will not be taken, NOP will not
be emulated and code will complete successfully.
If one argument is specified, then BC1T will be taken once and NOP will
be emulated. At this point the entry PC value will be 0x400498 and the
new PC value, set by `mips_dsemul' will be 0x4004a0, the target of BC1T.
The emulation loop will terminate, but SIGILL will not be issued,
because the PC has changed. The FPU emulator will be entered again and
on the second execution BC1T will not be taken, NOP will not be emulated
and code will complete successfully.
If two or more arguments are specified, then the first execution of BC1T
will proceed as above. Upon reentering the FPU emulator the emulation
loop will continue to BC1T, at which point the branch will be taken and
NOP emulated again. At this point however the entry PC value will be
0x4004a0, the same as the target of BC1T. This will make the emulator
conclude that execution has not advanced and therefore an unsupported
FPU instruction has been encountered, and SIGILL will be sent to the
process.
Fix the problem by extending the internal API of `mips_dsemul', making
it return -1 if no delay slot emulation frame has been made, the
instruction has been handled and execution of the emulation loop needs
to continue as if nothing happened. Remove code from `mips_dsemul' to
reproduce steps made by the emulation loop at the conclusion of each
iteration, as those will be reached normally now. Adjust call sites
accordingly. Document the API.
Signed-off-by: Maciej W. Rozycki <macro@imgtec.com>
Cc: Aurelien Jarno <aurelien@aurel32.net>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/12172/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-01-22 13:20:26 +08:00
|
|
|
return -1;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2016-01-22 13:21:00 +08:00
|
|
|
/* microMIPS instructions */
|
2016-01-22 13:21:47 +08:00
|
|
|
if (isa16) {
|
2016-01-22 13:21:00 +08:00
|
|
|
union mips_instruction insn = { .word = ir };
|
|
|
|
|
|
|
|
|
|
/* NOP16 aka MOVE16 $0, $0 */
|
|
|
|
|
if ((ir >> 16) == MM_NOP16)
|
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
|
|
/* ADDIUPC */
|
|
|
|
|
if (insn.mm_a_format.opcode == mm_addiupc_op) {
|
|
|
|
|
unsigned int rs;
|
|
|
|
|
s32 v;
|
|
|
|
|
|
2016-01-30 17:09:43 +08:00
|
|
|
rs = (((insn.mm_a_format.rs + 0xe) & 0xf) + 2);
|
2016-01-22 13:21:00 +08:00
|
|
|
v = regs->cp0_epc & ~3;
|
|
|
|
|
v += insn.mm_a_format.simmediate << 2;
|
|
|
|
|
regs->regs[rs] = (long)v;
|
|
|
|
|
return -1;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
pr_debug("dsemul 0x%08lx cont at 0x%08lx\n", regs->cp0_epc, cont_pc);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
/* Allocate a frame if we don't already have one */
|
|
|
|
|
fr_idx = atomic_read(¤t->thread.bd_emu_frame);
|
|
|
|
|
if (fr_idx == BD_EMUFRAME_NONE)
|
|
|
|
|
fr_idx = alloc_emuframe();
|
|
|
|
|
if (fr_idx == BD_EMUFRAME_NONE)
|
2005-04-17 06:20:36 +08:00
|
|
|
return SIGBUS;
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
fr = &dsemul_page()[fr_idx];
|
|
|
|
|
|
|
|
|
|
/* Retrieve the appropriately encoded break instruction */
|
|
|
|
|
break_math = BREAK_MATH(isa16);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
/* Write the instructions to the frame */
|
2016-01-22 13:21:47 +08:00
|
|
|
if (isa16) {
|
2016-01-22 13:20:37 +08:00
|
|
|
err = __put_user(ir >> 16,
|
|
|
|
|
(u16 __user *)(&fr->emul));
|
|
|
|
|
err |= __put_user(ir & 0xffff,
|
|
|
|
|
(u16 __user *)((long)(&fr->emul) + 2));
|
2016-01-22 13:20:46 +08:00
|
|
|
err |= __put_user(break_math >> 16,
|
2016-01-22 13:20:37 +08:00
|
|
|
(u16 __user *)(&fr->badinst));
|
2016-01-22 13:20:46 +08:00
|
|
|
err |= __put_user(break_math & 0xffff,
|
2016-01-22 13:20:37 +08:00
|
|
|
(u16 __user *)((long)(&fr->badinst) + 2));
|
2013-03-26 01:09:02 +08:00
|
|
|
} else {
|
|
|
|
|
err = __put_user(ir, &fr->emul);
|
2016-01-22 13:20:46 +08:00
|
|
|
err |= __put_user(break_math, &fr->badinst);
|
2013-03-26 01:09:02 +08:00
|
|
|
}
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (unlikely(err)) {
|
2009-11-06 03:34:26 +08:00
|
|
|
MIPS_FPU_EMU_INC_STATS(errors);
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
free_emuframe(fr_idx, current->mm);
|
2005-04-17 06:20:36 +08:00
|
|
|
return SIGBUS;
|
|
|
|
|
}
|
|
|
|
|
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
/* Record the PC of the branch, PC to continue from & frame index */
|
|
|
|
|
current->thread.bd_emu_branch_pc = branch_pc;
|
|
|
|
|
current->thread.bd_emu_cont_pc = cont_pc;
|
|
|
|
|
atomic_set(¤t->thread.bd_emu_frame, fr_idx);
|
|
|
|
|
|
|
|
|
|
/* Change user register context to execute the frame */
|
2016-01-22 13:21:47 +08:00
|
|
|
regs->cp0_epc = (unsigned long)&fr->emul | isa16;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
/* Ensure the icache observes our newly written frame */
|
2015-04-04 06:26:37 +08:00
|
|
|
flush_cache_sigtramp((unsigned long)&fr->emul);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2015-04-04 06:26:56 +08:00
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
bool do_dsemulret(struct pt_regs *xcp)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
/* Cleanup the allocated frame, returning if there wasn't one */
|
|
|
|
|
if (!dsemul_thread_cleanup(current)) {
|
2009-11-06 03:34:26 +08:00
|
|
|
MIPS_FPU_EMU_INC_STATS(errors);
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
return false;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Set EPC to return to post-branch instruction */
|
MIPS: Use per-mm page to execute branch delay slot instructions
In some cases the kernel needs to execute an instruction from the delay
slot of an emulated branch instruction. These cases include:
- Emulated floating point branch instructions (bc1[ft]l?) for systems
which don't include an FPU, or upon which the kernel is run with the
"nofpu" parameter.
- MIPSr6 systems running binaries targeting older revisions of the
architecture, which may include branch instructions whose encodings
are no longer valid in MIPSr6.
Executing instructions from such delay slots is done by writing the
instruction to memory followed by a trap, as part of an "emuframe", and
executing it. This avoids the requirement of an emulator for the entire
MIPS instruction set. Prior to this patch such emuframes are written to
the user stack and executed from there.
This patch moves FP branch delay emuframes off of the user stack and
into a per-mm page. Allocating a page per-mm leaves userland with access
to only what it had access to previously, and compared to other
solutions is relatively simple.
When a thread requires a delay slot emulation, it is allocated a frame.
A thread may only have one frame allocated at any one time, since it may
only ever be executing one instruction at any one time. In order to
ensure that we can free up allocated frame later, its index is recorded
in struct thread_struct. In the typical case, after executing the delay
slot instruction we'll execute a break instruction with the BRK_MEMU
code. This traps back to the kernel & leads to a call to do_dsemulret
which frees the allocated frame & moves the user PC back to the
instruction that would have executed following the emulated branch.
In some cases the delay slot instruction may be invalid, such as a
branch, or may trigger an exception. In these cases the BRK_MEMU break
instruction will not be hit. In order to ensure that frames are freed
this patch introduces dsemul_thread_cleanup() and calls it to free any
allocated frame upon thread exit. If the instruction generated an
exception & leads to a signal being delivered to the thread, or indeed
if a signal simply happens to be delivered to the thread whilst it is
executing from the struct emuframe, then we need to take care to exit
the frame appropriately. This is done by either rolling back the user PC
to the branch or advancing it to the continuation PC prior to signal
delivery, using dsemul_thread_rollback(). If this were not done then a
sigreturn would return to the struct emuframe, and if that frame had
meanwhile been used in response to an emulated branch instruction within
the signal handler then we would execute the wrong user code.
Whilst a user could theoretically place something like a compact branch
to self in a delay slot and cause their thread to become stuck in an
infinite loop with the frame never being deallocated, this would:
- Only affect the users single process.
- Be architecturally invalid since there would be a branch in the
delay slot, which is forbidden.
- Be extremely unlikely to happen by mistake, and provide a program
with no more ability to harm the system than a simple infinite loop
would.
If a thread requires a delay slot emulation & no frame is available to
it (ie. the process has enough other threads that all frames are
currently in use) then the thread joins a waitqueue. It will sleep until
a frame is freed by another thread in the process.
Since we now know whether a thread has an allocated frame due to our
tracking of its index, the cookie field of struct emuframe is removed as
we can be more certain whether we have a valid frame. Since a thread may
only ever have a single frame at any given time, the epc field of struct
emuframe is also removed & the PC to continue from is instead stored in
struct thread_struct. Together these changes simplify & shrink struct
emuframe somewhat, allowing twice as many frames to fit into the page
allocated for them.
The primary benefit of this patch is that we are now free to mark the
user stack non-executable where that is possible.
Signed-off-by: Paul Burton <paul.burton@imgtec.com>
Cc: Leonid Yegoshin <leonid.yegoshin@imgtec.com>
Cc: Maciej Rozycki <maciej.rozycki@imgtec.com>
Cc: Faraz Shahbazker <faraz.shahbazker@imgtec.com>
Cc: Raghu Gandham <raghu.gandham@imgtec.com>
Cc: Matthew Fortune <matthew.fortune@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/13764/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2016-07-08 18:06:19 +08:00
|
|
|
xcp->cp0_epc = current->thread.bd_emu_cont_pc;
|
|
|
|
|
pr_debug("dsemulret to 0x%08lx\n", xcp->cp0_epc);
|
|
|
|
|
return true;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|