mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-20 15:26:52 +07:00
432c6bacbd
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binaries targeting older revisions of the architecture, which may include branch instructions whose encodings are no longer valid in MIPSr6.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>
226 lines
5.5 KiB
C
226 lines
5.5 KiB
C
/*
|
|
* Switch a MMU context.
|
|
*
|
|
* This file is subject to the terms and conditions of the GNU General Public
|
|
* License. See the file "COPYING" in the main directory of this archive
|
|
* for more details.
|
|
*
|
|
* Copyright (C) 1996, 1997, 1998, 1999 by Ralf Baechle
|
|
* Copyright (C) 1999 Silicon Graphics, Inc.
|
|
*/
|
|
#ifndef _ASM_MMU_CONTEXT_H
|
|
#define _ASM_MMU_CONTEXT_H
|
|
|
|
#include <linux/errno.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/slab.h>
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/dsemul.h>
|
|
#include <asm/hazards.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm-generic/mm_hooks.h>
|
|
|
|
#define htw_set_pwbase(pgd) \
|
|
do { \
|
|
if (cpu_has_htw) { \
|
|
write_c0_pwbase(pgd); \
|
|
back_to_back_c0_hazard(); \
|
|
} \
|
|
} while (0)
|
|
|
|
#define TLBMISS_HANDLER_SETUP_PGD(pgd) \
|
|
do { \
|
|
extern void tlbmiss_handler_setup_pgd(unsigned long); \
|
|
tlbmiss_handler_setup_pgd((unsigned long)(pgd)); \
|
|
htw_set_pwbase((unsigned long)pgd); \
|
|
} while (0)
|
|
|
|
#ifdef CONFIG_MIPS_PGD_C0_CONTEXT
|
|
|
|
#define TLBMISS_HANDLER_RESTORE() \
|
|
write_c0_xcontext((unsigned long) smp_processor_id() << \
|
|
SMP_CPUID_REGSHIFT)
|
|
|
|
#define TLBMISS_HANDLER_SETUP() \
|
|
do { \
|
|
TLBMISS_HANDLER_SETUP_PGD(swapper_pg_dir); \
|
|
TLBMISS_HANDLER_RESTORE(); \
|
|
} while (0)
|
|
|
|
#else /* !CONFIG_MIPS_PGD_C0_CONTEXT: using pgd_current*/
|
|
|
|
/*
|
|
* For the fast tlb miss handlers, we keep a per cpu array of pointers
|
|
* to the current pgd for each processor. Also, the proc. id is stuffed
|
|
* into the context register.
|
|
*/
|
|
extern unsigned long pgd_current[];
|
|
|
|
#define TLBMISS_HANDLER_RESTORE() \
|
|
write_c0_context((unsigned long) smp_processor_id() << \
|
|
SMP_CPUID_REGSHIFT)
|
|
|
|
#define TLBMISS_HANDLER_SETUP() \
|
|
TLBMISS_HANDLER_RESTORE(); \
|
|
back_to_back_c0_hazard(); \
|
|
TLBMISS_HANDLER_SETUP_PGD(swapper_pg_dir)
|
|
#endif /* CONFIG_MIPS_PGD_C0_CONTEXT*/
|
|
|
|
/*
|
|
* All unused by hardware upper bits will be considered
|
|
* as a software asid extension.
|
|
*/
|
|
static unsigned long asid_version_mask(unsigned int cpu)
|
|
{
|
|
unsigned long asid_mask = cpu_asid_mask(&cpu_data[cpu]);
|
|
|
|
return ~(asid_mask | (asid_mask - 1));
|
|
}
|
|
|
|
static unsigned long asid_first_version(unsigned int cpu)
|
|
{
|
|
return ~asid_version_mask(cpu) + 1;
|
|
}
|
|
|
|
#define cpu_context(cpu, mm) ((mm)->context.asid[cpu])
|
|
#define asid_cache(cpu) (cpu_data[cpu].asid_cache)
|
|
#define cpu_asid(cpu, mm) \
|
|
(cpu_context((cpu), (mm)) & cpu_asid_mask(&cpu_data[cpu]))
|
|
|
|
static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
|
|
{
|
|
}
|
|
|
|
|
|
/* Normal, classic MIPS get_new_mmu_context */
|
|
static inline void
|
|
get_new_mmu_context(struct mm_struct *mm, unsigned long cpu)
|
|
{
|
|
extern void kvm_local_flush_tlb_all(void);
|
|
unsigned long asid = asid_cache(cpu);
|
|
|
|
if (!((asid += cpu_asid_inc()) & cpu_asid_mask(&cpu_data[cpu]))) {
|
|
if (cpu_has_vtag_icache)
|
|
flush_icache_all();
|
|
#ifdef CONFIG_KVM
|
|
kvm_local_flush_tlb_all(); /* start new asid cycle */
|
|
#else
|
|
local_flush_tlb_all(); /* start new asid cycle */
|
|
#endif
|
|
if (!asid) /* fix version if needed */
|
|
asid = asid_first_version(cpu);
|
|
}
|
|
|
|
cpu_context(cpu, mm) = asid_cache(cpu) = asid;
|
|
}
|
|
|
|
/*
|
|
* Initialize the context related info for a new mm_struct
|
|
* instance.
|
|
*/
|
|
static inline int
|
|
init_new_context(struct task_struct *tsk, struct mm_struct *mm)
|
|
{
|
|
int i;
|
|
|
|
for_each_possible_cpu(i)
|
|
cpu_context(i, mm) = 0;
|
|
|
|
atomic_set(&mm->context.fp_mode_switching, 0);
|
|
|
|
mm->context.bd_emupage_allocmap = NULL;
|
|
spin_lock_init(&mm->context.bd_emupage_lock);
|
|
init_waitqueue_head(&mm->context.bd_emupage_queue);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
|
|
struct task_struct *tsk)
|
|
{
|
|
unsigned int cpu = smp_processor_id();
|
|
unsigned long flags;
|
|
local_irq_save(flags);
|
|
|
|
htw_stop();
|
|
/* Check if our ASID is of an older version and thus invalid */
|
|
if ((cpu_context(cpu, next) ^ asid_cache(cpu)) & asid_version_mask(cpu))
|
|
get_new_mmu_context(next, cpu);
|
|
write_c0_entryhi(cpu_asid(cpu, next));
|
|
TLBMISS_HANDLER_SETUP_PGD(next->pgd);
|
|
|
|
/*
|
|
* Mark current->active_mm as not "active" anymore.
|
|
* We don't want to mislead possible IPI tlb flush routines.
|
|
*/
|
|
cpumask_clear_cpu(cpu, mm_cpumask(prev));
|
|
cpumask_set_cpu(cpu, mm_cpumask(next));
|
|
htw_start();
|
|
|
|
local_irq_restore(flags);
|
|
}
|
|
|
|
/*
|
|
* Destroy context related info for an mm_struct that is about
|
|
* to be put to rest.
|
|
*/
|
|
static inline void destroy_context(struct mm_struct *mm)
|
|
{
|
|
dsemul_mm_cleanup(mm);
|
|
}
|
|
|
|
#define deactivate_mm(tsk, mm) do { } while (0)
|
|
|
|
/*
|
|
* After we have set current->mm to a new value, this activates
|
|
* the context for the new mm so we see the new mappings.
|
|
*/
|
|
static inline void
|
|
activate_mm(struct mm_struct *prev, struct mm_struct *next)
|
|
{
|
|
unsigned long flags;
|
|
unsigned int cpu = smp_processor_id();
|
|
|
|
local_irq_save(flags);
|
|
|
|
htw_stop();
|
|
/* Unconditionally get a new ASID. */
|
|
get_new_mmu_context(next, cpu);
|
|
|
|
write_c0_entryhi(cpu_asid(cpu, next));
|
|
TLBMISS_HANDLER_SETUP_PGD(next->pgd);
|
|
|
|
/* mark mmu ownership change */
|
|
cpumask_clear_cpu(cpu, mm_cpumask(prev));
|
|
cpumask_set_cpu(cpu, mm_cpumask(next));
|
|
htw_start();
|
|
|
|
local_irq_restore(flags);
|
|
}
|
|
|
|
/*
|
|
* If mm is currently active_mm, we can't really drop it. Instead,
|
|
* we will get a new one for it.
|
|
*/
|
|
static inline void
|
|
drop_mmu_context(struct mm_struct *mm, unsigned cpu)
|
|
{
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
|
htw_stop();
|
|
|
|
if (cpumask_test_cpu(cpu, mm_cpumask(mm))) {
|
|
get_new_mmu_context(mm, cpu);
|
|
write_c0_entryhi(cpu_asid(cpu, mm));
|
|
} else {
|
|
/* will get a new context next time */
|
|
cpu_context(cpu, mm) = 0;
|
|
}
|
|
htw_start();
|
|
local_irq_restore(flags);
|
|
}
|
|
|
|
#endif /* _ASM_MMU_CONTEXT_H */
|