asgardius/android_kernel_motorola_sm6225
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
android_kernel_motorola_sm6225/arch/powerpc/include/asm/tlbflush.h

170 lines
4.3 KiB
C
Raw Normal View History

powerpc: merge tlbflush.h Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
2005-11-04 06:58:59 +01:00
#ifndef _ASM_POWERPC_TLBFLUSH_H
#define _ASM_POWERPC_TLBFLUSH_H
[POWERPC] 4xx: Fix 4xx flush_tlb_page() On 4xx CPUs, the current implementation of flush_tlb_page() uses a low level _tlbie() assembly function that only works for the current PID. Thus, invalidations caused by, for example, a COW fault triggered by get_user_pages() from a different context will not work properly, causing among other things, gdb breakpoints to fail. This patch adds a "pid" argument to _tlbie() on 4xx processors, and uses it to flush entries in the right context. FSL BookE also gets the argument but it seems they don't need it (their tlbivax form ignores the PID when invalidating according to the document I have). Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Acked-by: Kumar Gala <galak@kernel.crashing.org> Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
2007-10-29 23:46:06 +01:00
powerpc: merge tlbflush.h Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
2005-11-04 06:58:59 +01:00
/*
* TLB flushing:
*
* - flush_tlb_mm(mm) flushes the specified mm context TLB's
* - flush_tlb_page(vma, vmaddr) flushes one page
* - flush_tlb_page_nohash(vma, vmaddr) flushes one page if SW loaded TLB
* - flush_tlb_range(vma, start, end) flushes a range of pages
* - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifdef __KERNEL__
[POWERPC] Cleanup and fix breakage in tlbflush.h BenH's commit a741e67969577163a4cfc78d7fd2753219087ef1 in powerpc.git, although (AFAICT) only intended to affect ppc64, also has side-effects which break 44x. I think 40x, 8xx and Freescale Book E are also affected, though I haven't tested them. The problem lies in unconditionally removing flush_tlb_pending() from the versions of flush_tlb_mm(), flush_tlb_range() and flush_tlb_kernel_range() used on ppc64 - which are also used the embedded platforms mentioned above. The patch below cleans up the convoluted #ifdef logic in tlbflush.h, in the process restoring the necessary flushes for the software TLB platforms. There are three sets of definitions for the flushing hooks: the software TLB versions (revised to avoid using names which appear to related to TLB batching), the 32-bit hash based versions (external functions) amd the 64-bit hash based versions (which implement batching). It also moves the declaration of update_mmu_cache() to always be in tlbflush.h (previously it was in tlbflush.h except for PPC64, where it was in pgtable.h). Booted on Ebony (440GP) and compiled for 64-bit and 32-bit multiplatform. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-24 05:09:12 +02:00
#if defined(CONFIG_4xx) || defined(CONFIG_8xx) || defined(CONFIG_FSL_BOOKE)
/*
* TLB flushing for software loaded TLB chips
*
* TODO: (CONFIG_FSL_BOOKE) determine if flush_tlb_range &
* flush_tlb_kernel_range are best implemented as tlbia vs
* specific tlbie's
*/
[POWERPC] 4xx: Fix 4xx flush_tlb_page() On 4xx CPUs, the current implementation of flush_tlb_page() uses a low level _tlbie() assembly function that only works for the current PID. Thus, invalidations caused by, for example, a COW fault triggered by get_user_pages() from a different context will not work properly, causing among other things, gdb breakpoints to fail. This patch adds a "pid" argument to _tlbie() on 4xx processors, and uses it to flush entries in the right context. FSL BookE also gets the argument but it seems they don't need it (their tlbivax form ignores the PID when invalidating according to the document I have). Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Acked-by: Kumar Gala <galak@kernel.crashing.org> Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
2007-10-29 23:46:06 +01:00
#include <linux/mm.h>
extern void _tlbie(unsigned long address, unsigned int pid);
powerpc: Introduce local (non-broadcast) forms of tlb invalidates Introduced a new set of low level tlb invalidate functions that do not broadcast invalidates on the bus: _tlbil_all - invalidate all _tlbil_pid - invalidate based on process id (or mm context) _tlbil_va - invalidate based on virtual address (ea + pid) On non-SMP configs _tlbil_all should be functionally equivalent to _tlbia and _tlbil_va should be functionally equivalent to _tlbie. The intent of this change is to handle SMP based invalidates via IPIs instead of broadcasts as the mechanism scales better for larger number of cores. On e500 (fsl-booke mmu) based cores move to using MMUCSR for invalidate alls and tlbsx/tlbwe for invalidate virtual address. Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
2008-07-15 23:12:25 +02:00
extern void _tlbil_all(void);
extern void _tlbil_pid(unsigned int pid);
extern void _tlbil_va(unsigned long address, unsigned int pid);
[POWERPC] Cleanup and fix breakage in tlbflush.h BenH's commit a741e67969577163a4cfc78d7fd2753219087ef1 in powerpc.git, although (AFAICT) only intended to affect ppc64, also has side-effects which break 44x. I think 40x, 8xx and Freescale Book E are also affected, though I haven't tested them. The problem lies in unconditionally removing flush_tlb_pending() from the versions of flush_tlb_mm(), flush_tlb_range() and flush_tlb_kernel_range() used on ppc64 - which are also used the embedded platforms mentioned above. The patch below cleans up the convoluted #ifdef logic in tlbflush.h, in the process restoring the necessary flushes for the software TLB platforms. There are three sets of definitions for the flushing hooks: the software TLB versions (revised to avoid using names which appear to related to TLB batching), the 32-bit hash based versions (external functions) amd the 64-bit hash based versions (which implement batching). It also moves the declaration of update_mmu_cache() to always be in tlbflush.h (previously it was in tlbflush.h except for PPC64, where it was in pgtable.h). Booted on Ebony (440GP) and compiled for 64-bit and 32-bit multiplatform. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-24 05:09:12 +02:00
#if defined(CONFIG_40x) || defined(CONFIG_8xx)
#define _tlbia() asm volatile ("tlbia; sync" : : : "memory")
#else /* CONFIG_44x || CONFIG_FSL_BOOKE */
extern void _tlbia(void);
#endif
powerpc: merge tlbflush.h Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
2005-11-04 06:58:59 +01:00
[POWERPC] Cleanup and fix breakage in tlbflush.h BenH's commit a741e67969577163a4cfc78d7fd2753219087ef1 in powerpc.git, although (AFAICT) only intended to affect ppc64, also has side-effects which break 44x. I think 40x, 8xx and Freescale Book E are also affected, though I haven't tested them. The problem lies in unconditionally removing flush_tlb_pending() from the versions of flush_tlb_mm(), flush_tlb_range() and flush_tlb_kernel_range() used on ppc64 - which are also used the embedded platforms mentioned above. The patch below cleans up the convoluted #ifdef logic in tlbflush.h, in the process restoring the necessary flushes for the software TLB platforms. There are three sets of definitions for the flushing hooks: the software TLB versions (revised to avoid using names which appear to related to TLB batching), the 32-bit hash based versions (external functions) amd the 64-bit hash based versions (which implement batching). It also moves the declaration of update_mmu_cache() to always be in tlbflush.h (previously it was in tlbflush.h except for PPC64, where it was in pgtable.h). Booted on Ebony (440GP) and compiled for 64-bit and 32-bit multiplatform. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-24 05:09:12 +02:00
static inline void flush_tlb_mm(struct mm_struct *mm)
{
powerpc: Introduce local (non-broadcast) forms of tlb invalidates Introduced a new set of low level tlb invalidate functions that do not broadcast invalidates on the bus: _tlbil_all - invalidate all _tlbil_pid - invalidate based on process id (or mm context) _tlbil_va - invalidate based on virtual address (ea + pid) On non-SMP configs _tlbil_all should be functionally equivalent to _tlbia and _tlbil_va should be functionally equivalent to _tlbie. The intent of this change is to handle SMP based invalidates via IPIs instead of broadcasts as the mechanism scales better for larger number of cores. On e500 (fsl-booke mmu) based cores move to using MMUCSR for invalidate alls and tlbsx/tlbwe for invalidate virtual address. Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
2008-07-15 23:12:25 +02:00
_tlbil_pid(mm->context.id);
[POWERPC] Cleanup and fix breakage in tlbflush.h BenH's commit a741e67969577163a4cfc78d7fd2753219087ef1 in powerpc.git, although (AFAICT) only intended to affect ppc64, also has side-effects which break 44x. I think 40x, 8xx and Freescale Book E are also affected, though I haven't tested them. The problem lies in unconditionally removing flush_tlb_pending() from the versions of flush_tlb_mm(), flush_tlb_range() and flush_tlb_kernel_range() used on ppc64 - which are also used the embedded platforms mentioned above. The patch below cleans up the convoluted #ifdef logic in tlbflush.h, in the process restoring the necessary flushes for the software TLB platforms. There are three sets of definitions for the flushing hooks: the software TLB versions (revised to avoid using names which appear to related to TLB batching), the 32-bit hash based versions (external functions) amd the 64-bit hash based versions (which implement batching). It also moves the declaration of update_mmu_cache() to always be in tlbflush.h (previously it was in tlbflush.h except for PPC64, where it was in pgtable.h). Booted on Ebony (440GP) and compiled for 64-bit and 32-bit multiplatform. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-24 05:09:12 +02:00
}
static inline void flush_tlb_page(struct vm_area_struct *vma,
unsigned long vmaddr)
{
powerpc: Introduce local (non-broadcast) forms of tlb invalidates Introduced a new set of low level tlb invalidate functions that do not broadcast invalidates on the bus: _tlbil_all - invalidate all _tlbil_pid - invalidate based on process id (or mm context) _tlbil_va - invalidate based on virtual address (ea + pid) On non-SMP configs _tlbil_all should be functionally equivalent to _tlbia and _tlbil_va should be functionally equivalent to _tlbie. The intent of this change is to handle SMP based invalidates via IPIs instead of broadcasts as the mechanism scales better for larger number of cores. On e500 (fsl-booke mmu) based cores move to using MMUCSR for invalidate alls and tlbsx/tlbwe for invalidate virtual address. Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
2008-07-15 23:12:25 +02:00
_tlbil_va(vmaddr, vma ? vma->vm_mm->context.id : 0);
[POWERPC] Cleanup and fix breakage in tlbflush.h BenH's commit a741e67969577163a4cfc78d7fd2753219087ef1 in powerpc.git, although (AFAICT) only intended to affect ppc64, also has side-effects which break 44x. I think 40x, 8xx and Freescale Book E are also affected, though I haven't tested them. The problem lies in unconditionally removing flush_tlb_pending() from the versions of flush_tlb_mm(), flush_tlb_range() and flush_tlb_kernel_range() used on ppc64 - which are also used the embedded platforms mentioned above. The patch below cleans up the convoluted #ifdef logic in tlbflush.h, in the process restoring the necessary flushes for the software TLB platforms. There are three sets of definitions for the flushing hooks: the software TLB versions (revised to avoid using names which appear to related to TLB batching), the 32-bit hash based versions (external functions) amd the 64-bit hash based versions (which implement batching). It also moves the declaration of update_mmu_cache() to always be in tlbflush.h (previously it was in tlbflush.h except for PPC64, where it was in pgtable.h). Booted on Ebony (440GP) and compiled for 64-bit and 32-bit multiplatform. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-24 05:09:12 +02:00
}
static inline void flush_tlb_page_nohash(struct vm_area_struct *vma,
unsigned long vmaddr)
{
powerpc: Introduce local (non-broadcast) forms of tlb invalidates Introduced a new set of low level tlb invalidate functions that do not broadcast invalidates on the bus: _tlbil_all - invalidate all _tlbil_pid - invalidate based on process id (or mm context) _tlbil_va - invalidate based on virtual address (ea + pid) On non-SMP configs _tlbil_all should be functionally equivalent to _tlbia and _tlbil_va should be functionally equivalent to _tlbie. The intent of this change is to handle SMP based invalidates via IPIs instead of broadcasts as the mechanism scales better for larger number of cores. On e500 (fsl-booke mmu) based cores move to using MMUCSR for invalidate alls and tlbsx/tlbwe for invalidate virtual address. Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
2008-07-15 23:12:25 +02:00
flush_tlb_page(vma, vmaddr);
[POWERPC] Cleanup and fix breakage in tlbflush.h BenH's commit a741e67969577163a4cfc78d7fd2753219087ef1 in powerpc.git, although (AFAICT) only intended to affect ppc64, also has side-effects which break 44x. I think 40x, 8xx and Freescale Book E are also affected, though I haven't tested them. The problem lies in unconditionally removing flush_tlb_pending() from the versions of flush_tlb_mm(), flush_tlb_range() and flush_tlb_kernel_range() used on ppc64 - which are also used the embedded platforms mentioned above. The patch below cleans up the convoluted #ifdef logic in tlbflush.h, in the process restoring the necessary flushes for the software TLB platforms. There are three sets of definitions for the flushing hooks: the software TLB versions (revised to avoid using names which appear to related to TLB batching), the 32-bit hash based versions (external functions) amd the 64-bit hash based versions (which implement batching). It also moves the declaration of update_mmu_cache() to always be in tlbflush.h (previously it was in tlbflush.h except for PPC64, where it was in pgtable.h). Booted on Ebony (440GP) and compiled for 64-bit and 32-bit multiplatform. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-24 05:09:12 +02:00
}
static inline void flush_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
powerpc: Introduce local (non-broadcast) forms of tlb invalidates Introduced a new set of low level tlb invalidate functions that do not broadcast invalidates on the bus: _tlbil_all - invalidate all _tlbil_pid - invalidate based on process id (or mm context) _tlbil_va - invalidate based on virtual address (ea + pid) On non-SMP configs _tlbil_all should be functionally equivalent to _tlbia and _tlbil_va should be functionally equivalent to _tlbie. The intent of this change is to handle SMP based invalidates via IPIs instead of broadcasts as the mechanism scales better for larger number of cores. On e500 (fsl-booke mmu) based cores move to using MMUCSR for invalidate alls and tlbsx/tlbwe for invalidate virtual address. Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
2008-07-15 23:12:25 +02:00
_tlbil_pid(vma->vm_mm->context.id);
[POWERPC] Cleanup and fix breakage in tlbflush.h BenH's commit a741e67969577163a4cfc78d7fd2753219087ef1 in powerpc.git, although (AFAICT) only intended to affect ppc64, also has side-effects which break 44x. I think 40x, 8xx and Freescale Book E are also affected, though I haven't tested them. The problem lies in unconditionally removing flush_tlb_pending() from the versions of flush_tlb_mm(), flush_tlb_range() and flush_tlb_kernel_range() used on ppc64 - which are also used the embedded platforms mentioned above. The patch below cleans up the convoluted #ifdef logic in tlbflush.h, in the process restoring the necessary flushes for the software TLB platforms. There are three sets of definitions for the flushing hooks: the software TLB versions (revised to avoid using names which appear to related to TLB batching), the 32-bit hash based versions (external functions) amd the 64-bit hash based versions (which implement batching). It also moves the declaration of update_mmu_cache() to always be in tlbflush.h (previously it was in tlbflush.h except for PPC64, where it was in pgtable.h). Booted on Ebony (440GP) and compiled for 64-bit and 32-bit multiplatform. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-24 05:09:12 +02:00
}
static inline void flush_tlb_kernel_range(unsigned long start,
unsigned long end)
{
powerpc: Introduce local (non-broadcast) forms of tlb invalidates Introduced a new set of low level tlb invalidate functions that do not broadcast invalidates on the bus: _tlbil_all - invalidate all _tlbil_pid - invalidate based on process id (or mm context) _tlbil_va - invalidate based on virtual address (ea + pid) On non-SMP configs _tlbil_all should be functionally equivalent to _tlbia and _tlbil_va should be functionally equivalent to _tlbie. The intent of this change is to handle SMP based invalidates via IPIs instead of broadcasts as the mechanism scales better for larger number of cores. On e500 (fsl-booke mmu) based cores move to using MMUCSR for invalidate alls and tlbsx/tlbwe for invalidate virtual address. Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
2008-07-15 23:12:25 +02:00
_tlbil_pid(0);
[POWERPC] Cleanup and fix breakage in tlbflush.h BenH's commit a741e67969577163a4cfc78d7fd2753219087ef1 in powerpc.git, although (AFAICT) only intended to affect ppc64, also has side-effects which break 44x. I think 40x, 8xx and Freescale Book E are also affected, though I haven't tested them. The problem lies in unconditionally removing flush_tlb_pending() from the versions of flush_tlb_mm(), flush_tlb_range() and flush_tlb_kernel_range() used on ppc64 - which are also used the embedded platforms mentioned above. The patch below cleans up the convoluted #ifdef logic in tlbflush.h, in the process restoring the necessary flushes for the software TLB platforms. There are three sets of definitions for the flushing hooks: the software TLB versions (revised to avoid using names which appear to related to TLB batching), the 32-bit hash based versions (external functions) amd the 64-bit hash based versions (which implement batching). It also moves the declaration of update_mmu_cache() to always be in tlbflush.h (previously it was in tlbflush.h except for PPC64, where it was in pgtable.h). Booted on Ebony (440GP) and compiled for 64-bit and 32-bit multiplatform. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-24 05:09:12 +02:00
}
#elif defined(CONFIG_PPC32)
/*
* TLB flushing for "classic" hash-MMMU 32-bit CPUs, 6xx, 7xx, 7xxx
*/
extern void _tlbie(unsigned long address);
extern void _tlbia(void);
extern void flush_tlb_mm(struct mm_struct *mm);
extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
extern void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr);
extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end);
extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
#else
/*
* TLB flushing for 64-bit has-MMU CPUs
*/
powerpc: merge tlbflush.h Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
2005-11-04 06:58:59 +01:00
#include <linux/percpu.h>
#include <asm/page.h>
#define PPC64_TLB_BATCH_NR 192
struct ppc64_tlb_batch {
[POWERPC] Make tlb flush batch use lazy MMU mode The current tlb flush code on powerpc 64 bits has a subtle race since we lost the page table lock due to the possible faulting in of new PTEs after a previous one has been removed but before the corresponding hash entry has been evicted, which can leads to all sort of fatal problems. This patch reworks the batch code completely. It doesn't use the mmu_gather stuff anymore. Instead, we use the lazy mmu hooks that were added by the paravirt code. They have the nice property that the enter/leave lazy mmu mode pair is always fully contained by the PTE lock for a given range of PTEs. Thus we can guarantee that all batches are flushed on a given CPU before it drops that lock. We also generalize batching for any PTE update that require a flush. Batching is now enabled on a CPU by arch_enter_lazy_mmu_mode() and disabled by arch_leave_lazy_mmu_mode(). The code epects that this is always contained within a PTE lock section so no preemption can happen and no PTE insertion in that range from another CPU. When batching is enabled on a CPU, every PTE updates that need a hash flush will use the batch for that flush. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-10 09:09:37 +02:00
int active;
unsigned long index;
struct mm_struct *mm;
real_pte_t pte[PPC64_TLB_BATCH_NR];
unsigned long vaddr[PPC64_TLB_BATCH_NR];
unsigned int psize;
[POWERPC] Use 1TB segments This makes the kernel use 1TB segments for all kernel mappings and for user addresses of 1TB and above, on machines which support them (currently POWER5+, POWER6 and PA6T). We detect that the machine supports 1TB segments by looking at the ibm,processor-segment-sizes property in the device tree. We don't currently use 1TB segments for user addresses < 1T, since that would effectively prevent 32-bit processes from using huge pages unless we also had a way to revert to using 256MB segments. That would be possible but would involve extra complications (such as keeping track of which segment size was used when HPTEs were inserted) and is not addressed here. Parts of this patch were originally written by Ben Herrenschmidt. Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-10-11 12:37:10 +02:00
int ssize;
powerpc: merge tlbflush.h Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
2005-11-04 06:58:59 +01:00
};
DECLARE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch);
extern void __flush_tlb_pending(struct ppc64_tlb_batch *batch);
[POWERPC] Make tlb flush batch use lazy MMU mode The current tlb flush code on powerpc 64 bits has a subtle race since we lost the page table lock due to the possible faulting in of new PTEs after a previous one has been removed but before the corresponding hash entry has been evicted, which can leads to all sort of fatal problems. This patch reworks the batch code completely. It doesn't use the mmu_gather stuff anymore. Instead, we use the lazy mmu hooks that were added by the paravirt code. They have the nice property that the enter/leave lazy mmu mode pair is always fully contained by the PTE lock for a given range of PTEs. Thus we can guarantee that all batches are flushed on a given CPU before it drops that lock. We also generalize batching for any PTE update that require a flush. Batching is now enabled on a CPU by arch_enter_lazy_mmu_mode() and disabled by arch_leave_lazy_mmu_mode(). The code epects that this is always contained within a PTE lock section so no preemption can happen and no PTE insertion in that range from another CPU. When batching is enabled on a CPU, every PTE updates that need a hash flush will use the batch for that flush. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-10 09:09:37 +02:00
extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long pte, int huge);
#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
static inline void arch_enter_lazy_mmu_mode(void)
{
struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
batch->active = 1;
}
static inline void arch_leave_lazy_mmu_mode(void)
powerpc: merge tlbflush.h Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
2005-11-04 06:58:59 +01:00
{
[POWERPC] Make tlb flush batch use lazy MMU mode The current tlb flush code on powerpc 64 bits has a subtle race since we lost the page table lock due to the possible faulting in of new PTEs after a previous one has been removed but before the corresponding hash entry has been evicted, which can leads to all sort of fatal problems. This patch reworks the batch code completely. It doesn't use the mmu_gather stuff anymore. Instead, we use the lazy mmu hooks that were added by the paravirt code. They have the nice property that the enter/leave lazy mmu mode pair is always fully contained by the PTE lock for a given range of PTEs. Thus we can guarantee that all batches are flushed on a given CPU before it drops that lock. We also generalize batching for any PTE update that require a flush. Batching is now enabled on a CPU by arch_enter_lazy_mmu_mode() and disabled by arch_leave_lazy_mmu_mode(). The code epects that this is always contained within a PTE lock section so no preemption can happen and no PTE insertion in that range from another CPU. When batching is enabled on a CPU, every PTE updates that need a hash flush will use the batch for that flush. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-10 09:09:37 +02:00
struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
powerpc: merge tlbflush.h Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
2005-11-04 06:58:59 +01:00
if (batch->index)
__flush_tlb_pending(batch);
[POWERPC] Make tlb flush batch use lazy MMU mode The current tlb flush code on powerpc 64 bits has a subtle race since we lost the page table lock due to the possible faulting in of new PTEs after a previous one has been removed but before the corresponding hash entry has been evicted, which can leads to all sort of fatal problems. This patch reworks the batch code completely. It doesn't use the mmu_gather stuff anymore. Instead, we use the lazy mmu hooks that were added by the paravirt code. They have the nice property that the enter/leave lazy mmu mode pair is always fully contained by the PTE lock for a given range of PTEs. Thus we can guarantee that all batches are flushed on a given CPU before it drops that lock. We also generalize batching for any PTE update that require a flush. Batching is now enabled on a CPU by arch_enter_lazy_mmu_mode() and disabled by arch_leave_lazy_mmu_mode(). The code epects that this is always contained within a PTE lock section so no preemption can happen and no PTE insertion in that range from another CPU. When batching is enabled on a CPU, every PTE updates that need a hash flush will use the batch for that flush. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-10 09:09:37 +02:00
batch->active = 0;
powerpc: merge tlbflush.h Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
2005-11-04 06:58:59 +01:00
}
[POWERPC] Make tlb flush batch use lazy MMU mode The current tlb flush code on powerpc 64 bits has a subtle race since we lost the page table lock due to the possible faulting in of new PTEs after a previous one has been removed but before the corresponding hash entry has been evicted, which can leads to all sort of fatal problems. This patch reworks the batch code completely. It doesn't use the mmu_gather stuff anymore. Instead, we use the lazy mmu hooks that were added by the paravirt code. They have the nice property that the enter/leave lazy mmu mode pair is always fully contained by the PTE lock for a given range of PTEs. Thus we can guarantee that all batches are flushed on a given CPU before it drops that lock. We also generalize batching for any PTE update that require a flush. Batching is now enabled on a CPU by arch_enter_lazy_mmu_mode() and disabled by arch_leave_lazy_mmu_mode(). The code epects that this is always contained within a PTE lock section so no preemption can happen and no PTE insertion in that range from another CPU. When batching is enabled on a CPU, every PTE updates that need a hash flush will use the batch for that flush. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-10 09:09:37 +02:00
#define arch_flush_lazy_mmu_mode() do {} while (0)
[PATCH] ppc64: support 64k pages Adds a new CONFIG_PPC_64K_PAGES which, when enabled, changes the kernel base page size to 64K. The resulting kernel still boots on any hardware. On current machines with 4K pages support only, the kernel will maintain 16 "subpages" for each 64K page transparently. Note that while real 64K capable HW has been tested, the current patch will not enable it yet as such hardware is not released yet, and I'm still verifying with the firmware architects the proper to get the information from the newer hypervisors. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-07 01:06:55 +01:00
extern void flush_hash_page(unsigned long va, real_pte_t pte, int psize,
[POWERPC] Use 1TB segments This makes the kernel use 1TB segments for all kernel mappings and for user addresses of 1TB and above, on machines which support them (currently POWER5+, POWER6 and PA6T). We detect that the machine supports 1TB segments by looking at the ibm,processor-segment-sizes property in the device tree. We don't currently use 1TB segments for user addresses < 1T, since that would effectively prevent 32-bit processes from using huge pages unless we also had a way to revert to using 256MB segments. That would be possible but would involve extra complications (such as keeping track of which segment size was used when HPTEs were inserted) and is not addressed here. Parts of this patch were originally written by Ben Herrenschmidt. Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-10-11 12:37:10 +02:00
int ssize, int local);
[PATCH] ppc64: support 64k pages Adds a new CONFIG_PPC_64K_PAGES which, when enabled, changes the kernel base page size to 64K. The resulting kernel still boots on any hardware. On current machines with 4K pages support only, the kernel will maintain 16 "subpages" for each 64K page transparently. Note that while real 64K capable HW has been tested, the current patch will not enable it yet as such hardware is not released yet, and I'm still verifying with the firmware architects the proper to get the information from the newer hypervisors. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-07 01:06:55 +01:00
extern void flush_hash_range(unsigned long number, int local);
powerpc: merge tlbflush.h Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
2005-11-04 06:58:59 +01:00
static inline void flush_tlb_mm(struct mm_struct *mm)
{
}
static inline void flush_tlb_page(struct vm_area_struct *vma,
[POWERPC] Cleanup and fix breakage in tlbflush.h BenH's commit a741e67969577163a4cfc78d7fd2753219087ef1 in powerpc.git, although (AFAICT) only intended to affect ppc64, also has side-effects which break 44x. I think 40x, 8xx and Freescale Book E are also affected, though I haven't tested them. The problem lies in unconditionally removing flush_tlb_pending() from the versions of flush_tlb_mm(), flush_tlb_range() and flush_tlb_kernel_range() used on ppc64 - which are also used the embedded platforms mentioned above. The patch below cleans up the convoluted #ifdef logic in tlbflush.h, in the process restoring the necessary flushes for the software TLB platforms. There are three sets of definitions for the flushing hooks: the software TLB versions (revised to avoid using names which appear to related to TLB batching), the 32-bit hash based versions (external functions) amd the 64-bit hash based versions (which implement batching). It also moves the declaration of update_mmu_cache() to always be in tlbflush.h (previously it was in tlbflush.h except for PPC64, where it was in pgtable.h). Booted on Ebony (440GP) and compiled for 64-bit and 32-bit multiplatform. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-24 05:09:12 +02:00
unsigned long vmaddr)
powerpc: merge tlbflush.h Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
2005-11-04 06:58:59 +01:00
{
}
static inline void flush_tlb_page_nohash(struct vm_area_struct *vma,
unsigned long vmaddr)
{
}
static inline void flush_tlb_range(struct vm_area_struct *vma,
[POWERPC] Cleanup and fix breakage in tlbflush.h BenH's commit a741e67969577163a4cfc78d7fd2753219087ef1 in powerpc.git, although (AFAICT) only intended to affect ppc64, also has side-effects which break 44x. I think 40x, 8xx and Freescale Book E are also affected, though I haven't tested them. The problem lies in unconditionally removing flush_tlb_pending() from the versions of flush_tlb_mm(), flush_tlb_range() and flush_tlb_kernel_range() used on ppc64 - which are also used the embedded platforms mentioned above. The patch below cleans up the convoluted #ifdef logic in tlbflush.h, in the process restoring the necessary flushes for the software TLB platforms. There are three sets of definitions for the flushing hooks: the software TLB versions (revised to avoid using names which appear to related to TLB batching), the 32-bit hash based versions (external functions) amd the 64-bit hash based versions (which implement batching). It also moves the declaration of update_mmu_cache() to always be in tlbflush.h (previously it was in tlbflush.h except for PPC64, where it was in pgtable.h). Booted on Ebony (440GP) and compiled for 64-bit and 32-bit multiplatform. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-24 05:09:12 +02:00
unsigned long start, unsigned long end)
powerpc: merge tlbflush.h Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
2005-11-04 06:58:59 +01:00
{
}
static inline void flush_tlb_kernel_range(unsigned long start,
[POWERPC] Cleanup and fix breakage in tlbflush.h BenH's commit a741e67969577163a4cfc78d7fd2753219087ef1 in powerpc.git, although (AFAICT) only intended to affect ppc64, also has side-effects which break 44x. I think 40x, 8xx and Freescale Book E are also affected, though I haven't tested them. The problem lies in unconditionally removing flush_tlb_pending() from the versions of flush_tlb_mm(), flush_tlb_range() and flush_tlb_kernel_range() used on ppc64 - which are also used the embedded platforms mentioned above. The patch below cleans up the convoluted #ifdef logic in tlbflush.h, in the process restoring the necessary flushes for the software TLB platforms. There are three sets of definitions for the flushing hooks: the software TLB versions (revised to avoid using names which appear to related to TLB batching), the 32-bit hash based versions (external functions) amd the 64-bit hash based versions (which implement batching). It also moves the declaration of update_mmu_cache() to always be in tlbflush.h (previously it was in tlbflush.h except for PPC64, where it was in pgtable.h). Booted on Ebony (440GP) and compiled for 64-bit and 32-bit multiplatform. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-04-24 05:09:12 +02:00
unsigned long end)
powerpc: merge tlbflush.h Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
2005-11-04 06:58:59 +01:00
{
}
[POWERPC] Rewrite IO allocation & mapping on powerpc64 This rewrites pretty much from scratch the handling of MMIO and PIO space allocations on powerpc64. The main goals are: - Get rid of imalloc and use more common code where possible - Simplify the current mess so that PIO space is allocated and mapped in a single place for PCI bridges - Handle allocation constraints of PIO for all bridges including hot plugged ones within the 2GB space reserved for IO ports, so that devices on hotplugged busses will now work with drivers that assume IO ports fit in an int. - Cleanup and separate tracking of the ISA space in the reserved low 64K of IO space. No ISA -> Nothing mapped there. I booted a cell blade with IDE on PIO and MMIO and a dual G5 so far, that's it :-) With this patch, all allocations are done using the code in mm/vmalloc.c, though we use the low level __get_vm_area with explicit start/stop constraints in order to manage separate areas for vmalloc/vmap, ioremap, and PCI IOs. This greatly simplifies a lot of things, as you can see in the diffstat of that patch :-) A new pair of functions pcibios_map/unmap_io_space() now replace all of the previous code that used to manipulate PCI IOs space. The allocation is done at mapping time, which is now called from scan_phb's, just before the devices are probed (instead of after, which is by itself a bug fix). The only other caller is the PCI hotplug code for hot adding PCI-PCI bridges (slots). imalloc is gone, as is the "sub-allocation" thing, but I do beleive that hotplug should still work in the sense that the space allocation is always done by the PHB, but if you unmap a child bus of this PHB (which seems to be possible), then the code should properly tear down all the HPTE mappings for that area of the PHB allocated IO space. I now always reserve the first 64K of IO space for the bridge with the ISA bus on it. I have moved the code for tracking ISA in a separate file which should also make it smarter if we ever are capable of hot unplugging or re-plugging an ISA bridge. This should have a side effect on platforms like powermac where VGA IOs will no longer work. This is done on purpose though as they would have worked semi-randomly before. The idea at this point is to isolate drivers that might need to access those and fix them by providing a proper function to obtain an offset to the legacy IOs of a given bus. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-06-04 07:15:36 +02:00
/* Private function for use by PCI IO mapping code */
extern void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
unsigned long end);
powerpc: merge tlbflush.h Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
2005-11-04 06:58:59 +01:00
#endif
#endif /*__KERNEL__ */
#endif /* _ASM_POWERPC_TLBFLUSH_H */
Reference in a new issue Copy permalink