03b8abedf4
The PSL and nMMU need to see all TLB invalidations for the memory
contexts used on the adapter. For the hash memory model, it is done by
making all TLBIs global as soon as the cxl driver is in use. For
radix, we need something similar, but we can refine and only convert
to global the invalidations for contexts actually used by the device.
The new mm_context_add_copro() API increments the 'active_cpus' count
for the contexts attached to the cxl adapter. As soon as there's more
than 1 active cpu, the TLBIs for the context become global. Active cpu
count must be decremented when detaching to restore locality if
possible and to avoid overflowing the counter.
The hash memory model support is somewhat limited, as we can't
decrement the active cpus count when mm_context_remove_copro() is
called, because we can't flush the TLB for a mm on hash. So TLBIs
remain global on hash.
Signed-off-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>
Fixes: f24be42aab ("cxl: Add psl9 specific code")
Tested-by: Alistair Popple <alistair@popple.id.au>
[mpe: Fold in updated comment on the barrier from Fred]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
192 lines
5.9 KiB
C
192 lines
5.9 KiB
C
#ifndef __ASM_POWERPC_MMU_CONTEXT_H
|
|
#define __ASM_POWERPC_MMU_CONTEXT_H
|
|
#ifdef __KERNEL__
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/spinlock.h>
|
|
#include <asm/mmu.h>
|
|
#include <asm/cputable.h>
|
|
#include <asm/cputhreads.h>
|
|
|
|
/*
|
|
* Most if the context management is out of line
|
|
*/
|
|
extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
|
|
extern void destroy_context(struct mm_struct *mm);
|
|
#ifdef CONFIG_SPAPR_TCE_IOMMU
|
|
struct mm_iommu_table_group_mem_t;
|
|
|
|
extern int isolate_lru_page(struct page *page); /* from internal.h */
|
|
extern bool mm_iommu_preregistered(struct mm_struct *mm);
|
|
extern long mm_iommu_get(struct mm_struct *mm,
|
|
unsigned long ua, unsigned long entries,
|
|
struct mm_iommu_table_group_mem_t **pmem);
|
|
extern long mm_iommu_put(struct mm_struct *mm,
|
|
struct mm_iommu_table_group_mem_t *mem);
|
|
extern void mm_iommu_init(struct mm_struct *mm);
|
|
extern void mm_iommu_cleanup(struct mm_struct *mm);
|
|
extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
|
|
unsigned long ua, unsigned long size);
|
|
extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
|
|
struct mm_struct *mm, unsigned long ua, unsigned long size);
|
|
extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
|
|
unsigned long ua, unsigned long entries);
|
|
extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
|
|
unsigned long ua, unsigned long *hpa);
|
|
extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
|
|
unsigned long ua, unsigned long *hpa);
|
|
extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
|
|
extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
|
|
#endif
|
|
extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm);
|
|
extern void set_context(unsigned long id, pgd_t *pgd);
|
|
|
|
#ifdef CONFIG_PPC_BOOK3S_64
|
|
extern void radix__switch_mmu_context(struct mm_struct *prev,
|
|
struct mm_struct *next);
|
|
static inline void switch_mmu_context(struct mm_struct *prev,
|
|
struct mm_struct *next,
|
|
struct task_struct *tsk)
|
|
{
|
|
if (radix_enabled())
|
|
return radix__switch_mmu_context(prev, next);
|
|
return switch_slb(tsk, next);
|
|
}
|
|
|
|
extern int hash__alloc_context_id(void);
|
|
extern void hash__reserve_context_id(int id);
|
|
extern void __destroy_context(int context_id);
|
|
static inline void mmu_context_init(void) { }
|
|
#else
|
|
extern void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next,
|
|
struct task_struct *tsk);
|
|
extern unsigned long __init_new_context(void);
|
|
extern void __destroy_context(unsigned long context_id);
|
|
extern void mmu_context_init(void);
|
|
#endif
|
|
|
|
#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)
|
|
extern void radix_kvm_prefetch_workaround(struct mm_struct *mm);
|
|
#else
|
|
static inline void radix_kvm_prefetch_workaround(struct mm_struct *mm) { }
|
|
#endif
|
|
|
|
extern void switch_cop(struct mm_struct *next);
|
|
extern int use_cop(unsigned long acop, struct mm_struct *mm);
|
|
extern void drop_cop(unsigned long acop, struct mm_struct *mm);
|
|
|
|
#ifdef CONFIG_PPC_BOOK3S_64
|
|
static inline void inc_mm_active_cpus(struct mm_struct *mm)
|
|
{
|
|
atomic_inc(&mm->context.active_cpus);
|
|
}
|
|
|
|
static inline void dec_mm_active_cpus(struct mm_struct *mm)
|
|
{
|
|
atomic_dec(&mm->context.active_cpus);
|
|
}
|
|
|
|
static inline void mm_context_add_copro(struct mm_struct *mm)
|
|
{
|
|
/*
|
|
* On hash, should only be called once over the lifetime of
|
|
* the context, as we can't decrement the active cpus count
|
|
* and flush properly for the time being.
|
|
*/
|
|
inc_mm_active_cpus(mm);
|
|
}
|
|
|
|
static inline void mm_context_remove_copro(struct mm_struct *mm)
|
|
{
|
|
/*
|
|
* Need to broadcast a global flush of the full mm before
|
|
* decrementing active_cpus count, as the next TLBI may be
|
|
* local and the nMMU and/or PSL need to be cleaned up.
|
|
* Should be rare enough so that it's acceptable.
|
|
*
|
|
* Skip on hash, as we don't know how to do the proper flush
|
|
* for the time being. Invalidations will remain global if
|
|
* used on hash.
|
|
*/
|
|
if (radix_enabled()) {
|
|
flush_all_mm(mm);
|
|
dec_mm_active_cpus(mm);
|
|
}
|
|
}
|
|
#else
|
|
static inline void inc_mm_active_cpus(struct mm_struct *mm) { }
|
|
static inline void dec_mm_active_cpus(struct mm_struct *mm) { }
|
|
static inline void mm_context_add_copro(struct mm_struct *mm) { }
|
|
static inline void mm_context_remove_copro(struct mm_struct *mm) { }
|
|
#endif
|
|
|
|
|
|
extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
|
|
struct task_struct *tsk);
|
|
|
|
static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
|
|
struct task_struct *tsk)
|
|
{
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
|
switch_mm_irqs_off(prev, next, tsk);
|
|
local_irq_restore(flags);
|
|
}
|
|
#define switch_mm_irqs_off switch_mm_irqs_off
|
|
|
|
|
|
#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)
|
|
{
|
|
switch_mm(prev, next, current);
|
|
}
|
|
|
|
/* We don't currently use enter_lazy_tlb() for anything */
|
|
static inline void enter_lazy_tlb(struct mm_struct *mm,
|
|
struct task_struct *tsk)
|
|
{
|
|
/* 64-bit Book3E keeps track of current PGD in the PACA */
|
|
#ifdef CONFIG_PPC_BOOK3E_64
|
|
get_paca()->pgd = NULL;
|
|
#endif
|
|
}
|
|
|
|
static inline void arch_dup_mmap(struct mm_struct *oldmm,
|
|
struct mm_struct *mm)
|
|
{
|
|
}
|
|
|
|
static inline void arch_exit_mmap(struct mm_struct *mm)
|
|
{
|
|
}
|
|
|
|
static inline void arch_unmap(struct mm_struct *mm,
|
|
struct vm_area_struct *vma,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
if (start <= mm->context.vdso_base && mm->context.vdso_base < end)
|
|
mm->context.vdso_base = 0;
|
|
}
|
|
|
|
static inline void arch_bprm_mm_init(struct mm_struct *mm,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
}
|
|
|
|
static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
|
|
bool write, bool execute, bool foreign)
|
|
{
|
|
/* by default, allow everything */
|
|
return true;
|
|
}
|
|
#endif /* __KERNEL__ */
|
|
#endif /* __ASM_POWERPC_MMU_CONTEXT_H */
|