You've already forked linux-apfs
mirror of
https://github.com/linux-apfs/linux-apfs.git
synced 2026-05-01 15:00:59 -07:00
Nagarathnam Muthusamy
9a08862a5d
Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.
vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.
*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
before the vdso code page, the pointer to data page is got by subracting offset
from an address in the vdso code page. The return address stored in
%i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
converted into raw bytes by vdso2c program to be ready for mapping into the
process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
generates two files vdso-image-64.c and vdso-image-32.c which contains the
respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
arch_setup_additional_pages and the location of mapping is passed on to the
process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
cpu_relax is added for the use of vDSO.
This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.
Testing:
========
[root@localhost ~]# cat vdso_test.c
int main() {
struct timespec tv_start, tv_end;
struct timeval tv_tmp;
int i;
int count = 1 * 1000 * 10000;
long long diff;
clock_gettime(0, &tv_start);
for (i = 0; i < count; i++)
gettimeofday(&tv_tmp, NULL);
clock_gettime(0, &tv_end);
diff = (long long)(tv_end.tv_sec -
tv_start.tv_sec)*(1*1000*1000*1000);
diff += (tv_end.tv_nsec - tv_start.tv_nsec);
printf("Start sec: %d\n", tv_start.tv_sec);
printf("End sec : %d\n", tv_end.tv_sec);
printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
(double)diff / (double)count);
return 0;
}
[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle
V1 to V2 Changes:
=================
Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.
V2 to V3 Changes:
=================
Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.
V3 to V4 Changes:
=================
Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.
Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
112 lines
3.1 KiB
C
112 lines
3.1 KiB
C
#ifndef __MMU_H
|
|
#define __MMU_H
|
|
|
|
#include <linux/const.h>
|
|
#include <asm/page.h>
|
|
#include <asm/hypervisor.h>
|
|
|
|
#define CTX_NR_BITS 13
|
|
|
|
#define TAG_CONTEXT_BITS ((_AC(1,UL) << CTX_NR_BITS) - _AC(1,UL))
|
|
|
|
/* UltraSPARC-III+ and later have a feature whereby you can
|
|
* select what page size the various Data-TLB instances in the
|
|
* chip. In order to gracefully support this, we put the version
|
|
* field in a spot outside of the areas of the context register
|
|
* where this parameter is specified.
|
|
*/
|
|
#define CTX_VERSION_SHIFT 22
|
|
#define CTX_VERSION_MASK ((~0UL) << CTX_VERSION_SHIFT)
|
|
|
|
#define CTX_PGSZ_8KB _AC(0x0,UL)
|
|
#define CTX_PGSZ_64KB _AC(0x1,UL)
|
|
#define CTX_PGSZ_512KB _AC(0x2,UL)
|
|
#define CTX_PGSZ_4MB _AC(0x3,UL)
|
|
#define CTX_PGSZ_BITS _AC(0x7,UL)
|
|
#define CTX_PGSZ0_NUC_SHIFT 61
|
|
#define CTX_PGSZ1_NUC_SHIFT 58
|
|
#define CTX_PGSZ0_SHIFT 16
|
|
#define CTX_PGSZ1_SHIFT 19
|
|
#define CTX_PGSZ_MASK ((CTX_PGSZ_BITS << CTX_PGSZ0_SHIFT) | \
|
|
(CTX_PGSZ_BITS << CTX_PGSZ1_SHIFT))
|
|
|
|
#define CTX_PGSZ_BASE CTX_PGSZ_8KB
|
|
#define CTX_PGSZ_HUGE CTX_PGSZ_4MB
|
|
#define CTX_PGSZ_KERN CTX_PGSZ_4MB
|
|
|
|
/* Thus, when running on UltraSPARC-III+ and later, we use the following
|
|
* PRIMARY_CONTEXT register values for the kernel context.
|
|
*/
|
|
#define CTX_CHEETAH_PLUS_NUC \
|
|
((CTX_PGSZ_KERN << CTX_PGSZ0_NUC_SHIFT) | \
|
|
(CTX_PGSZ_BASE << CTX_PGSZ1_NUC_SHIFT))
|
|
|
|
#define CTX_CHEETAH_PLUS_CTX0 \
|
|
((CTX_PGSZ_KERN << CTX_PGSZ0_SHIFT) | \
|
|
(CTX_PGSZ_BASE << CTX_PGSZ1_SHIFT))
|
|
|
|
/* If you want "the TLB context number" use CTX_NR_MASK. If you
|
|
* want "the bits I program into the context registers" use
|
|
* CTX_HW_MASK.
|
|
*/
|
|
#define CTX_NR_MASK TAG_CONTEXT_BITS
|
|
#define CTX_HW_MASK (CTX_NR_MASK | CTX_PGSZ_MASK)
|
|
|
|
#define CTX_FIRST_VERSION BIT(CTX_VERSION_SHIFT)
|
|
#define CTX_VALID(__ctx) \
|
|
(!(((__ctx.sparc64_ctx_val) ^ tlb_context_cache) & CTX_VERSION_MASK))
|
|
#define CTX_HWBITS(__ctx) ((__ctx.sparc64_ctx_val) & CTX_HW_MASK)
|
|
#define CTX_NRBITS(__ctx) ((__ctx.sparc64_ctx_val) & CTX_NR_MASK)
|
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
#define TSB_ENTRY_ALIGNMENT 16
|
|
|
|
struct tsb {
|
|
unsigned long tag;
|
|
unsigned long pte;
|
|
} __attribute__((aligned(TSB_ENTRY_ALIGNMENT)));
|
|
|
|
void __tsb_insert(unsigned long ent, unsigned long tag, unsigned long pte);
|
|
void tsb_flush(unsigned long ent, unsigned long tag);
|
|
void tsb_init(struct tsb *tsb, unsigned long size);
|
|
|
|
struct tsb_config {
|
|
struct tsb *tsb;
|
|
unsigned long tsb_rss_limit;
|
|
unsigned long tsb_nentries;
|
|
unsigned long tsb_reg_val;
|
|
unsigned long tsb_map_vaddr;
|
|
unsigned long tsb_map_pte;
|
|
};
|
|
|
|
#define MM_TSB_BASE 0
|
|
|
|
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
|
|
#define MM_TSB_HUGE 1
|
|
#define MM_NUM_TSBS 2
|
|
#else
|
|
#define MM_NUM_TSBS 1
|
|
#endif
|
|
|
|
typedef struct {
|
|
spinlock_t lock;
|
|
unsigned long sparc64_ctx_val;
|
|
unsigned long hugetlb_pte_count;
|
|
unsigned long thp_pte_count;
|
|
struct tsb_config tsb_block[MM_NUM_TSBS];
|
|
struct hv_tsb_descr tsb_descr[MM_NUM_TSBS];
|
|
void *vdso;
|
|
} mm_context_t;
|
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
#define TSB_CONFIG_TSB 0x00
|
|
#define TSB_CONFIG_RSS_LIMIT 0x08
|
|
#define TSB_CONFIG_NENTRIES 0x10
|
|
#define TSB_CONFIG_REG_VAL 0x18
|
|
#define TSB_CONFIG_MAP_VADDR 0x20
|
|
#define TSB_CONFIG_MAP_PTE 0x28
|
|
|
|
#endif /* __MMU_H */
|