android_kernel_motorola_sm6225/include/asm-sparc64/mmu_context.h

157 lines
4.5 KiB
C
Raw Normal View History

/* $Id: mmu_context.h,v 1.54 2002/02/09 19:49:31 davem Exp $ */
#ifndef __SPARC64_MMU_CONTEXT_H
#define __SPARC64_MMU_CONTEXT_H
/* Derived heavily from Linus's Alpha/AXP ASN code... */
#ifndef __ASSEMBLY__
#include <linux/spinlock.h>
#include <asm/system.h>
#include <asm/spitfire.h>
#include <asm-generic/mm_hooks.h>
static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
}
extern spinlock_t ctx_alloc_lock;
extern unsigned long tlb_context_cache;
extern unsigned long mmu_context_bmap[];
extern void get_new_mmu_context(struct mm_struct *mm);
#ifdef CONFIG_SMP
extern void smp_new_mmu_context_version(void);
#else
#define smp_new_mmu_context_version() do { } while (0)
#endif
extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
extern void destroy_context(struct mm_struct *mm);
extern void __tsb_context_switch(unsigned long pgd_pa,
struct tsb_config *tsb_base,
struct tsb_config *tsb_huge,
unsigned long tsb_descr_pa);
static inline void tsb_context_switch(struct mm_struct *mm)
{
__tsb_context_switch(__pa(mm->pgd),
&mm->context.tsb_block[0],
#ifdef CONFIG_HUGETLB_PAGE
(mm->context.tsb_block[1].tsb ?
&mm->context.tsb_block[1] :
NULL)
#else
NULL
#endif
, __pa(&mm->context.tsb_descr[0]));
}
extern void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long mm_rss);
#ifdef CONFIG_SMP
extern void smp_tsb_sync(struct mm_struct *mm);
#else
#define smp_tsb_sync(__mm) do { } while (0)
#endif
/* Set MMU context in the actual hardware. */
#define load_secondary_context(__mm) \
__asm__ __volatile__( \
"\n661: stxa %0, [%1] %2\n" \
" .section .sun4v_1insn_patch, \"ax\"\n" \
" .word 661b\n" \
" stxa %0, [%1] %3\n" \
" .previous\n" \
" flush %%g6\n" \
: /* No outputs */ \
: "r" (CTX_HWBITS((__mm)->context)), \
"r" (SECONDARY_CONTEXT), "i" (ASI_DMMU), "i" (ASI_MMU))
extern void __flush_tlb_mm(unsigned long, unsigned long);
/* Switch the current MM context. Interrupts are disabled. */
static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk)
{
unsigned long ctx_valid, flags;
int cpu;
if (unlikely(mm == &init_mm))
return;
spin_lock_irqsave(&mm->context.lock, flags);
ctx_valid = CTX_VALID(mm->context);
if (!ctx_valid)
get_new_mmu_context(mm);
[SPARC64]: Fix and re-enable dynamic TSB sizing. This is good for up to %50 performance improvement of some test cases. The problem has been the race conditions, and hopefully I've plugged them all up here. 1) There was a serious race in switch_mm() wrt. lazy TLB switching to and from kernel threads. We could erroneously skip a tsb_context_switch() and thus use a stale TSB across a TSB grow event. There is a big comment now in that function describing exactly how it can happen. 2) All code paths that do something with the TSB need to be guarded with the mm->context.lock spinlock. This makes page table flushing paths properly synchronize with both TSB growing and TLB context changes. 3) TSB growing events are moved to the end of successful fault processing. Previously it was in update_mmu_cache() but that is deadlock prone. At the end of do_sparc64_fault() we hold no spinlocks that could deadlock the TSB grow sequence. We also have dropped the address space semaphore. While we're here, add prefetching to the copy_tsb() routine and put it in assembler into the tsb.S file. This piece of code is quite time critical. There are some small negative side effects to this code which can be improved upon. In particular we grab the mm->context.lock even for the tsb insert done by update_mmu_cache() now and that's a bit excessive. We can get rid of that locking, and the same lock taking in flush_tsb_user(), by disabling PSTATE_IE around the whole operation including the capturing of the tsb pointer and tsb_nentries value. That would work because anyone growing the TSB won't free up the old TSB until all cpus respond to the TSB change cross call. I'm not quite so confident in that optimization to put it in right now, but eventually we might be able to and the description is here for reference. This code seems very solid now. It passes several parallel GCC bootstrap builds, and our favorite "nut cruncher" stress test which is a full "make -j8192" build of a "make allmodconfig" kernel. That puts about 256 processes on each cpu's run queue, makes lots of process cpu migrations occur, causes lots of page table and TLB flushing activity, incurs many context version number changes, and it swaps the machine real far out to disk even though there is 16GB of ram on this test system. :-) Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-16 11:02:32 +01:00
/* We have to be extremely careful here or else we will miss
* a TSB grow if we switch back and forth between a kernel
* thread and an address space which has it's TSB size increased
* on another processor.
*
* It is possible to play some games in order to optimize the
* switch, but the safest thing to do is to unconditionally
* perform the secondary context load and the TSB context switch.
*
* For reference the bad case is, for address space "A":
*
* CPU 0 CPU 1
* run address space A
* set cpu0's bits in cpu_vm_mask
* switch to kernel thread, borrow
* address space A via entry_lazy_tlb
* run address space A
* set cpu1's bit in cpu_vm_mask
* flush_tlb_pending()
* reset cpu_vm_mask to just cpu1
* TSB grow
* run address space A
* context was valid, so skip
* TSB context switch
*
* At that point cpu0 continues to use a stale TSB, the one from
* before the TSB grow performed on cpu1. cpu1 did not cross-call
* cpu0 to update it's TSB because at that point the cpu_vm_mask
* only had cpu1 set in it.
*/
load_secondary_context(mm);
tsb_context_switch(mm);
[SPARC64]: Fix and re-enable dynamic TSB sizing. This is good for up to %50 performance improvement of some test cases. The problem has been the race conditions, and hopefully I've plugged them all up here. 1) There was a serious race in switch_mm() wrt. lazy TLB switching to and from kernel threads. We could erroneously skip a tsb_context_switch() and thus use a stale TSB across a TSB grow event. There is a big comment now in that function describing exactly how it can happen. 2) All code paths that do something with the TSB need to be guarded with the mm->context.lock spinlock. This makes page table flushing paths properly synchronize with both TSB growing and TLB context changes. 3) TSB growing events are moved to the end of successful fault processing. Previously it was in update_mmu_cache() but that is deadlock prone. At the end of do_sparc64_fault() we hold no spinlocks that could deadlock the TSB grow sequence. We also have dropped the address space semaphore. While we're here, add prefetching to the copy_tsb() routine and put it in assembler into the tsb.S file. This piece of code is quite time critical. There are some small negative side effects to this code which can be improved upon. In particular we grab the mm->context.lock even for the tsb insert done by update_mmu_cache() now and that's a bit excessive. We can get rid of that locking, and the same lock taking in flush_tsb_user(), by disabling PSTATE_IE around the whole operation including the capturing of the tsb pointer and tsb_nentries value. That would work because anyone growing the TSB won't free up the old TSB until all cpus respond to the TSB change cross call. I'm not quite so confident in that optimization to put it in right now, but eventually we might be able to and the description is here for reference. This code seems very solid now. It passes several parallel GCC bootstrap builds, and our favorite "nut cruncher" stress test which is a full "make -j8192" build of a "make allmodconfig" kernel. That puts about 256 processes on each cpu's run queue, makes lots of process cpu migrations occur, causes lots of page table and TLB flushing activity, incurs many context version number changes, and it swaps the machine real far out to disk even though there is 16GB of ram on this test system. :-) Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-16 11:02:32 +01:00
/* Any time a processor runs a context on an address space
* for the first time, we must flush that context out of the
* local TLB.
*/
cpu = smp_processor_id();
if (!ctx_valid || !cpu_isset(cpu, mm->cpu_vm_mask)) {
cpu_set(cpu, mm->cpu_vm_mask);
__flush_tlb_mm(CTX_HWBITS(mm->context),
SECONDARY_CONTEXT);
}
[SPARC64]: Fix and re-enable dynamic TSB sizing. This is good for up to %50 performance improvement of some test cases. The problem has been the race conditions, and hopefully I've plugged them all up here. 1) There was a serious race in switch_mm() wrt. lazy TLB switching to and from kernel threads. We could erroneously skip a tsb_context_switch() and thus use a stale TSB across a TSB grow event. There is a big comment now in that function describing exactly how it can happen. 2) All code paths that do something with the TSB need to be guarded with the mm->context.lock spinlock. This makes page table flushing paths properly synchronize with both TSB growing and TLB context changes. 3) TSB growing events are moved to the end of successful fault processing. Previously it was in update_mmu_cache() but that is deadlock prone. At the end of do_sparc64_fault() we hold no spinlocks that could deadlock the TSB grow sequence. We also have dropped the address space semaphore. While we're here, add prefetching to the copy_tsb() routine and put it in assembler into the tsb.S file. This piece of code is quite time critical. There are some small negative side effects to this code which can be improved upon. In particular we grab the mm->context.lock even for the tsb insert done by update_mmu_cache() now and that's a bit excessive. We can get rid of that locking, and the same lock taking in flush_tsb_user(), by disabling PSTATE_IE around the whole operation including the capturing of the tsb pointer and tsb_nentries value. That would work because anyone growing the TSB won't free up the old TSB until all cpus respond to the TSB change cross call. I'm not quite so confident in that optimization to put it in right now, but eventually we might be able to and the description is here for reference. This code seems very solid now. It passes several parallel GCC bootstrap builds, and our favorite "nut cruncher" stress test which is a full "make -j8192" build of a "make allmodconfig" kernel. That puts about 256 processes on each cpu's run queue, makes lots of process cpu migrations occur, causes lots of page table and TLB flushing activity, incurs many context version number changes, and it swaps the machine real far out to disk even though there is 16GB of ram on this test system. :-) Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-16 11:02:32 +01:00
spin_unlock_irqrestore(&mm->context.lock, flags);
}
#define deactivate_mm(tsk,mm) do { } while (0)
/* Activate a new MM instance for the current task. */
static inline void activate_mm(struct mm_struct *active_mm, struct mm_struct *mm)
{
unsigned long flags;
int cpu;
spin_lock_irqsave(&mm->context.lock, flags);
if (!CTX_VALID(mm->context))
get_new_mmu_context(mm);
cpu = smp_processor_id();
if (!cpu_isset(cpu, mm->cpu_vm_mask))
cpu_set(cpu, mm->cpu_vm_mask);
load_secondary_context(mm);
__flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT);
tsb_context_switch(mm);
[SPARC64]: Fix and re-enable dynamic TSB sizing. This is good for up to %50 performance improvement of some test cases. The problem has been the race conditions, and hopefully I've plugged them all up here. 1) There was a serious race in switch_mm() wrt. lazy TLB switching to and from kernel threads. We could erroneously skip a tsb_context_switch() and thus use a stale TSB across a TSB grow event. There is a big comment now in that function describing exactly how it can happen. 2) All code paths that do something with the TSB need to be guarded with the mm->context.lock spinlock. This makes page table flushing paths properly synchronize with both TSB growing and TLB context changes. 3) TSB growing events are moved to the end of successful fault processing. Previously it was in update_mmu_cache() but that is deadlock prone. At the end of do_sparc64_fault() we hold no spinlocks that could deadlock the TSB grow sequence. We also have dropped the address space semaphore. While we're here, add prefetching to the copy_tsb() routine and put it in assembler into the tsb.S file. This piece of code is quite time critical. There are some small negative side effects to this code which can be improved upon. In particular we grab the mm->context.lock even for the tsb insert done by update_mmu_cache() now and that's a bit excessive. We can get rid of that locking, and the same lock taking in flush_tsb_user(), by disabling PSTATE_IE around the whole operation including the capturing of the tsb pointer and tsb_nentries value. That would work because anyone growing the TSB won't free up the old TSB until all cpus respond to the TSB change cross call. I'm not quite so confident in that optimization to put it in right now, but eventually we might be able to and the description is here for reference. This code seems very solid now. It passes several parallel GCC bootstrap builds, and our favorite "nut cruncher" stress test which is a full "make -j8192" build of a "make allmodconfig" kernel. That puts about 256 processes on each cpu's run queue, makes lots of process cpu migrations occur, causes lots of page table and TLB flushing activity, incurs many context version number changes, and it swaps the machine real far out to disk even though there is 16GB of ram on this test system. :-) Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-16 11:02:32 +01:00
spin_unlock_irqrestore(&mm->context.lock, flags);
}
#endif /* !(__ASSEMBLY__) */
#endif /* !(__SPARC64_MMU_CONTEXT_H) */