mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-21 08:19:28 +00:00
![Benjamin Herrenschmidt](/assets/img/avatar_default.png)
The basic issue is to be able to do what hugetlbfs does but with different page sizes for some other special filesystems; more specifically, my need is: - Huge pages - SPE local store mappings using 64K pages on a 4K base page size kernel on Cell - Some special 4K segments in 64K-page kernels for mapping a dodgy type of powerpc-specific infiniband hardware that requires 4K MMU mappings for various reasons I won't explain here. The main issues are: - To maintain/keep track of the page size per "segment" (as we can only have one page size per segment on powerpc, which are 256MB divisions of the address space). - To make sure special mappings stay within their allotted "segments" (including MAP_FIXED crap) - To make sure everybody else doesn't mmap/brk/grow_stack into a "segment" that is used for a special mapping Some of the necessary mechanisms to handle that were present in the hugetlbfs code, but mostly in ways not suitable for anything else. The patch relies on some changes to the generic get_unmapped_area() that just got merged. It still hijacks hugetlb callbacks here or there as the generic code hasn't been entirely cleaned up yet but that shouldn't be a problem. So what is a slice ? Well, I re-used the mechanism used formerly by our hugetlbfs implementation which divides the address space in "meta-segments" which I called "slices". The division is done using 256MB slices below 4G, and 1T slices above. Thus the address space is divided currently into 16 "low" slices and 16 "high" slices. (Special case: high slice 0 is the area between 4G and 1T). Doing so simplifies significantly the tracking of segments and avoids having to keep track of all the 256MB segments in the address space. While I used the "concepts" of hugetlbfs, I mostly re-implemented everything in a more generic way and "ported" hugetlbfs to it. Slices can have an associated page size, which is encoded in the mmu context and used by the SLB miss handler to set the segment sizes. The hash code currently doesn't care, it has a specific check for hugepages, though I might add a mechanism to provide per-slice hash mapping functions in the future. The slice code provide a pair of "generic" get_unmapped_area() (bottomup and topdown) functions that should work with any slice size. There is some trickiness here so I would appreciate people to have a look at the implementation of these and let me know if I got something wrong. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
113 lines
3.6 KiB
C
113 lines
3.6 KiB
C
/*
|
|
* include/asm-powerpc/paca.h
|
|
*
|
|
* This control block defines the PACA which defines the processor
|
|
* specific data for each logical processor on the system.
|
|
* There are some pointers defined that are utilized by PLIC.
|
|
*
|
|
* C 2001 PPC 64 Team, IBM Corp
|
|
*
|
|
* 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.
|
|
*/
|
|
#ifndef _ASM_POWERPC_PACA_H
|
|
#define _ASM_POWERPC_PACA_H
|
|
#ifdef __KERNEL__
|
|
|
|
#include <asm/types.h>
|
|
#include <asm/lppaca.h>
|
|
#include <asm/mmu.h>
|
|
|
|
register struct paca_struct *local_paca asm("r13");
|
|
#define get_paca() local_paca
|
|
#define get_lppaca() (get_paca()->lppaca_ptr)
|
|
#define get_slb_shadow() (get_paca()->slb_shadow_ptr)
|
|
|
|
struct task_struct;
|
|
|
|
/*
|
|
* Defines the layout of the paca.
|
|
*
|
|
* This structure is not directly accessed by firmware or the service
|
|
* processor except for the first two pointers that point to the
|
|
* lppaca area and the ItLpRegSave area for this CPU. The lppaca
|
|
* object is currently contained within the PACA but it doesn't need
|
|
* to be.
|
|
*/
|
|
struct paca_struct {
|
|
/*
|
|
* Because hw_cpu_id, unlike other paca fields, is accessed
|
|
* routinely from other CPUs (from the IRQ code), we stick to
|
|
* read-only (after boot) fields in the first cacheline to
|
|
* avoid cacheline bouncing.
|
|
*/
|
|
|
|
/*
|
|
* MAGIC: These first two pointers can't be moved - they're
|
|
* accessed by the firmware
|
|
*/
|
|
struct lppaca *lppaca_ptr; /* Pointer to LpPaca for PLIC */
|
|
#ifdef CONFIG_PPC_ISERIES
|
|
void *reg_save_ptr; /* Pointer to LpRegSave for PLIC */
|
|
#endif /* CONFIG_PPC_ISERIES */
|
|
|
|
/*
|
|
* MAGIC: the spinlock functions in arch/powerpc/lib/locks.c
|
|
* load lock_token and paca_index with a single lwz
|
|
* instruction. They must travel together and be properly
|
|
* aligned.
|
|
*/
|
|
u16 lock_token; /* Constant 0x8000, used in locks */
|
|
u16 paca_index; /* Logical processor number */
|
|
|
|
u64 kernel_toc; /* Kernel TOC address */
|
|
u64 stab_real; /* Absolute address of segment table */
|
|
u64 stab_addr; /* Virtual address of segment table */
|
|
void *emergency_sp; /* pointer to emergency stack */
|
|
u64 data_offset; /* per cpu data offset */
|
|
s16 hw_cpu_id; /* Physical processor number */
|
|
u8 cpu_start; /* At startup, processor spins until */
|
|
/* this becomes non-zero. */
|
|
struct slb_shadow *slb_shadow_ptr;
|
|
|
|
/*
|
|
* Now, starting in cacheline 2, the exception save areas
|
|
*/
|
|
/* used for most interrupts/exceptions */
|
|
u64 exgen[10] __attribute__((aligned(0x80)));
|
|
u64 exmc[10]; /* used for machine checks */
|
|
u64 exslb[10]; /* used for SLB/segment table misses
|
|
* on the linear mapping */
|
|
|
|
mm_context_t context;
|
|
u16 vmalloc_sllp;
|
|
u16 slb_cache_ptr;
|
|
u16 slb_cache[SLB_CACHE_ENTRIES];
|
|
|
|
/*
|
|
* then miscellaneous read-write fields
|
|
*/
|
|
struct task_struct *__current; /* Pointer to current */
|
|
u64 kstack; /* Saved Kernel stack addr */
|
|
u64 stab_rr; /* stab/slb round-robin counter */
|
|
u64 saved_r1; /* r1 save for RTAS calls */
|
|
u64 saved_msr; /* MSR saved here by enter_rtas */
|
|
u16 trap_save; /* Used when bad stack is encountered */
|
|
u8 soft_enabled; /* irq soft-enable flag */
|
|
u8 hard_enabled; /* set if irqs are enabled in MSR */
|
|
u8 io_sync; /* writel() needs spin_unlock sync */
|
|
|
|
/* Stuff for accurate time accounting */
|
|
u64 user_time; /* accumulated usermode TB ticks */
|
|
u64 system_time; /* accumulated system TB ticks */
|
|
u64 startpurr; /* PURR/TB value snapshot */
|
|
};
|
|
|
|
extern struct paca_struct paca[];
|
|
|
|
void setup_boot_paca(void);
|
|
|
|
#endif /* __KERNEL__ */
|
|
#endif /* _ASM_POWERPC_PACA_H */
|