Menu
▾
▴
Re: [linuxsh-dev] SH-4 cache problem?
|
From: NIIBE Y. <gn...@m1...> - 2001-08-07 14:17:50
|
SUGIOKA Toshinobu writes:
> Yes. This works good, nice performance.
Thanks for testing. I'll commit following. It does more clean-up.
* arch/sh/mm/cache-sh4.c (ptep_get_and_clear): Moved to ...
(check_cache_page): Removed.
(__flush_icache_page): Removed.
* include/asm-sh/pgtable.h (__flush_icache_page): Removed.
* include/asm-sh/pgalloc.h (ptep_get_and_clear): ... here.
(ptep_test_and_clear_young, ptep_test_and_clear_dirty,
ptep_set_wrprotect, ptep_mkdirty): Moved from pgtable.h.
(ptep_get_and_clear needs definition of mm.h).
* include/asm-sh/pgtable.h (PG_mapped): Renamed from
PG_mapped_with_alias.
(__flush_cache_page): Removed last argument, and add first arg.
* arch/sh/mm/cache-sh4.c (__flush_cache_page): Take u0 address
as first argument. Don't care about I-cache.
(flush_dcache_page): Follow the change.
* include/asm-sh/ide.h (ide_insw): Removed.
* drivers/cdrom/gdrom.c (gdrom_intr): Remove __flush_wback_region.
* arch/sh/mm/fault.c (update_mmu_cache): Flush the cache when first
mapped, even if it has no alias. (We needed this to for NFS).
Index: arch/sh/mm/cache-sh4.c
===================================================================
RCS file: /cvsroot/linuxsh/kernel/arch/sh/mm/cache-sh4.c,v
retrieving revision 1.11
diff -u -r1.11 cache-sh4.c
--- arch/sh/mm/cache-sh4.c 2001/08/07 05:20:02 1.11
+++ arch/sh/mm/cache-sh4.c 2001/08/07 14:09:50
@@ -196,9 +196,8 @@
/*
* Writeback&Invalidate the D-cache of the page
- * Invalidate the I-cache of the page, if needed
*/
-void __flush_cache_page(unsigned long phys, int exec)
+void __flush_cache_page(unsigned long u0, unsigned long phys)
{
unsigned long addr, data;
unsigned long flags;
@@ -207,74 +206,65 @@
save_and_cli(flags);
jump_to_P2();
- /* Loop all the D-cache */
- for (addr = CACHE_OC_ADDRESS_ARRAY;
- addr < (CACHE_OC_ADDRESS_ARRAY
- +(CACHE_OC_NUM_ENTRIES<< CACHE_OC_ENTRY_SHIFT));
- addr += (1<<CACHE_OC_ENTRY_SHIFT)) {
- data = ctrl_inl(addr)&(0x1ffff000|CACHE_VALID);
- if (data == phys)
- ctrl_outl(0, addr);
- }
-
- if (exec)
- /* Loop all the I-cache */
- for (addr = CACHE_IC_ADDRESS_ARRAY;
- addr < (CACHE_IC_ADDRESS_ARRAY
- +(CACHE_IC_NUM_ENTRIES<< CACHE_IC_ENTRY_SHIFT));
- addr += (1<<CACHE_IC_ENTRY_SHIFT)) {
- data = ctrl_inl(addr)&(0x1ffff000|CACHE_VALID);
- if (data == phys)
- ctrl_outl(0, addr);
- }
- back_to_P1();
- restore_flags(flags);
-}
-
-void __flush_icache_page(unsigned long u0, unsigned long phys)
-{
- unsigned long addr, data;
- unsigned long flags;
- phys|=CACHE_VALID;
-
- save_and_cli(flags);
if (u0) {
- jump_to_P2();
- /* Loop half of the I-cache */
- for (addr = CACHE_IC_ADDRESS_ARRAY|(u0&0x1000);
- addr < ((CACHE_IC_ADDRESS_ARRAY|(u0&0x1000))
- +(CACHE_IC_NUM_ENTRIES/2<<CACHE_IC_ENTRY_SHIFT));
- addr += (1<<CACHE_IC_ENTRY_SHIFT)) {
+ if ((u0^phys) & CACHE_ALIAS) {
+ /* Loop 4K of the D-cache */
+ for (addr = CACHE_OC_ADDRESS_ARRAY | (u0 & CACHE_ALIAS);
+ addr < (CACHE_OC_ADDRESS_ARRAY + (u0 & CACHE_ALIAS)
+ +(CACHE_OC_NUM_ENTRIES/4<<CACHE_OC_ENTRY_SHIFT));
+ addr += (1<<CACHE_OC_ENTRY_SHIFT)) {
+ data = ctrl_inl(addr)&(0x1ffff000|CACHE_VALID);
+ if (data == phys)
+ ctrl_outl(0, addr);
+ }
+ }
+ /* Loop another 4K of the D-cache */
+ for (addr = CACHE_OC_ADDRESS_ARRAY | (phys & CACHE_ALIAS);
+ addr < (CACHE_OC_ADDRESS_ARRAY + (phys & CACHE_ALIAS)
+ +(CACHE_OC_NUM_ENTRIES/4<<CACHE_OC_ENTRY_SHIFT));
+ addr += (1<<CACHE_OC_ENTRY_SHIFT)) {
data = ctrl_inl(addr)&(0x1ffff000|CACHE_VALID);
if (data == phys)
ctrl_outl(0, addr);
}
- back_to_P1();
} else {
- jump_to_P2();
- /* Loop all the I-cache */
- for (addr = CACHE_IC_ADDRESS_ARRAY;
- addr < (CACHE_IC_ADDRESS_ARRAY
- +(CACHE_IC_NUM_ENTRIES << CACHE_IC_ENTRY_SHIFT));
- addr += (1<<CACHE_IC_ENTRY_SHIFT)) {
+ /* Loop all the D-cache */
+ for (addr = CACHE_OC_ADDRESS_ARRAY;
+ addr < (CACHE_OC_ADDRESS_ARRAY
+ +(CACHE_OC_NUM_ENTRIES<< CACHE_OC_ENTRY_SHIFT));
+ addr += (1<<CACHE_OC_ENTRY_SHIFT)) {
data = ctrl_inl(addr)&(0x1ffff000|CACHE_VALID);
if (data == phys)
ctrl_outl(0, addr);
}
- back_to_P1();
}
+
+#if 0 /* DEBUG DEBUG */
+ /* Loop all the I-cache */
+ for (addr = CACHE_IC_ADDRESS_ARRAY;
+ addr < (CACHE_IC_ADDRESS_ARRAY
+ +(CACHE_IC_NUM_ENTRIES<< CACHE_IC_ENTRY_SHIFT));
+ addr += (1<<CACHE_IC_ENTRY_SHIFT)) {
+ data = ctrl_inl(addr)&(0x1ffff000|CACHE_VALID);
+ if (data == phys) {
+ printk(KERN_INFO "__flush_cache_page: I-cache entry found\n");
+ ctrl_outl(0, addr);
+ }
+ }
+#endif
+ back_to_P1();
restore_flags(flags);
}
/*
- * Write back & invalidate the I/D-cache of the page.
+ * Write back & invalidate the D-cache of the page.
* (To avoid "alias" issues)
*/
void flush_dcache_page(struct page *page)
{
if (test_bit(PG_mapped_with_alias, &page->flags))
- __flush_cache_page(PHYSADDR(page_address(page)), 1);
+ __flush_cache_page(0, PHYSADDR(page_address(page)));
}
void flush_cache_all(void)
@@ -393,68 +383,6 @@
}
/*
- * Check entries of the I-cache & D-cache of the page.
- * (To see "alias" issues)
- */
-void check_cache_page(struct page *pg)
-{
- unsigned long phys, addr, data, i;
- unsigned long kaddr;
- unsigned long cache_line_index;
- int bingo = 0;
- unsigned long flags;
-
- /* Physical address of this page */
- phys = PHYSADDR(page_address(pg));
- kaddr = phys + PAGE_OFFSET;
- cache_line_index = (kaddr&CACHE_OC_ENTRY_MASK)>>CACHE_OC_ENTRY_SHIFT;
-
- save_and_cli(flags);
- jump_to_P2();
- /* Loop all the D-cache */
- for (i=0; i<CACHE_OC_NUM_ENTRIES; i++) {
- addr = CACHE_OC_ADDRESS_ARRAY| (i<<CACHE_OC_ENTRY_SHIFT);
- data = ctrl_inl(addr);
- if ((data & (CACHE_UPDATED|CACHE_VALID))
- == (CACHE_UPDATED|CACHE_VALID)
- && (data&PAGE_MASK) == phys) {
- data &= ~(CACHE_VALID|CACHE_UPDATED);
- ctrl_outl(data, addr);
- if ((i^cache_line_index)&0x180)
- bingo |= 1;
- }
- }
-
- cache_line_index &= 0xff;
- /* Loop all the I-cache */
- for (i=0; i<CACHE_IC_NUM_ENTRIES; i++) {
- addr = CACHE_IC_ADDRESS_ARRAY| (i<<CACHE_IC_ENTRY_SHIFT);
- data = ctrl_inl(addr);
- if ((data & CACHE_VALID) && (data&PAGE_MASK) == phys) {
- data &= ~CACHE_VALID;
- ctrl_outl(data, addr);
- if (((i^cache_line_index)&0x80))
- bingo |= 2;
- }
- }
- back_to_P1();
- restore_flags(flags);
-
- if (bingo) {
- extern void dump_stack(void);
-
- if (bingo&1)
- printk("BINGO!\n");
-#if 0
- if (bingo&2)
- printk("Bingo!\n");
-#endif
- dump_stack();
- printk("--------------------\n");
- }
-}
-
-/*
* clear_user_page
* @to: P1 address
* @address: U0 address to be mapped
@@ -523,18 +451,4 @@
pte_clear(pte);
up(&p3map_sem[(address & CACHE_ALIAS)>>12]);
}
-}
-
-pte_t ptep_get_and_clear(pte_t *ptep)
-{
- pte_t pte = *ptep;
-
- if (!pte_not_present(pte)) {
- struct page *page = pte_page(pte);
- if (VALID_PAGE(page)&&
- (!page->mapping || !(page->mapping->i_mmap_shared)))
- __clear_bit(PG_mapped_with_alias, &page->flags);
- }
- pte_clear(ptep);
- return pte;
}
Index: arch/sh/mm/fault.c
===================================================================
RCS file: /cvsroot/linuxsh/kernel/arch/sh/mm/fault.c,v
retrieving revision 1.45
diff -u -r1.45 fault.c
--- arch/sh/mm/fault.c 2001/08/07 05:20:02 1.45
+++ arch/sh/mm/fault.c 2001/08/07 14:09:50
@@ -290,14 +290,12 @@
return;
#if defined(__SH4__)
- if ((address ^ pte_val(pte)) & CACHE_ALIAS) {
- page = pte_page(pte);
- if (VALID_PAGE(page) &&
- !test_bit(PG_mapped_with_alias, &page->flags)) {
- unsigned long phys = pte_val(pte) & PTE_PHYS_MASK;
- __flush_cache_page(phys, 1);
- set_bit(PG_mapped_with_alias, &page->flags);
- }
+ page = pte_page(pte);
+ if (VALID_PAGE(page) &&
+ !test_bit(PG_mapped_with_alias, &page->flags)) {
+ unsigned long phys = pte_val(pte) & PTE_PHYS_MASK;
+ __flush_cache_page(address, phys);
+ set_bit(PG_mapped_with_alias, &page->flags);
}
#endif
Index: drivers/cdrom/gdrom.c
===================================================================
RCS file: /cvsroot/linuxsh/kernel/drivers/cdrom/gdrom.c,v
retrieving revision 1.4
diff -u -r1.4 gdrom.c
--- drivers/cdrom/gdrom.c 2001/08/03 23:50:59 1.4
+++ drivers/cdrom/gdrom.c 2001/08/07 14:09:50
@@ -144,7 +144,6 @@
}
insw(GDROM_DATA, ctrl->buf, count/2);
- __flush_wback_region(ctrl->buf, count);
ctrl->buf += count;
ctrl->size -= count;
}
Index: include/asm-sh/ide.h
===================================================================
RCS file: /cvsroot/linuxsh/kernel/include/asm-sh/ide.h,v
retrieving revision 1.16
diff -u -r1.16 ide.h
--- include/asm-sh/ide.h 2001/08/03 11:22:06 1.16
+++ include/asm-sh/ide.h 2001/08/07 14:09:52
@@ -17,21 +17,6 @@
#include <linux/config.h>
#include <asm/machvec.h>
-#if defined(__SH4__)
-#undef insw
-#define insw(port, buf, nr) ide_insw((port), (buf), (nr))
-
-static __inline__ void ide_insw(unsigned long port,
- void *dst,
- unsigned long count)
-{
- extern void _insw (unsigned long port, void *dst, unsigned long count);
-
- _insw(port, dst, count);
- __flush_wback_region(dst, (count << 1));
-}
-#endif
-
#ifndef MAX_HWIFS
/* Should never have less than 2, ide-pci.c(ide_match_hwif) requires it */
#define MAX_HWIFS 2
Index: include/asm-sh/pgalloc.h
===================================================================
RCS file: /cvsroot/linuxsh/kernel/include/asm-sh/pgalloc.h,v
retrieving revision 1.9
diff -u -r1.9 pgalloc.h
--- include/asm-sh/pgalloc.h 2001/07/18 04:24:43 1.9
+++ include/asm-sh/pgalloc.h 2001/08/07 14:09:53
@@ -95,4 +95,62 @@
{ /* Nothing to do */
}
+#if defined(__SH4__)
+/*
+ * For SH-4, we have our own implementation for ptep_get_and_clear
+ */
+static inline pte_t ptep_get_and_clear(pte_t *ptep)
+{
+ pte_t pte = *ptep;
+
+ pte_clear(ptep);
+ if (!pte_not_present(pte)) {
+ struct page *page = pte_page(pte);
+ if (VALID_PAGE(page)&&
+ (!page->mapping || !(page->mapping->i_mmap_shared)))
+ __clear_bit(PG_mapped_with_alias, &page->flags);
+ }
+ return pte;
+}
+#else
+static inline pte_t ptep_get_and_clear(pte_t *ptep)
+{
+ pte_t pte = *ptep;
+ pte_clear(ptep);
+ return pte;
+}
+#endif
+
+/*
+ * Following functions are same as generic ones.
+ */
+static inline int ptep_test_and_clear_young(pte_t *ptep)
+{
+ pte_t pte = *ptep;
+ if (!pte_young(pte))
+ return 0;
+ set_pte(ptep, pte_mkold(pte));
+ return 1;
+}
+
+static inline int ptep_test_and_clear_dirty(pte_t *ptep)
+{
+ pte_t pte = *ptep;
+ if (!pte_dirty(pte))
+ return 0;
+ set_pte(ptep, pte_mkclean(pte));
+ return 1;
+}
+
+static inline void ptep_set_wrprotect(pte_t *ptep)
+{
+ pte_t old_pte = *ptep;
+ set_pte(ptep, pte_wrprotect(old_pte));
+}
+
+static inline void ptep_mkdirty(pte_t *ptep)
+{
+ pte_t old_pte = *ptep;
+ set_pte(ptep, pte_mkdirty(old_pte));
+}
#endif /* __ASM_SH_PGALLOC_H */
Index: include/asm-sh/pgtable.h
===================================================================
RCS file: /cvsroot/linuxsh/kernel/include/asm-sh/pgtable.h,v
retrieving revision 1.41
diff -u -r1.41 pgtable.h
--- include/asm-sh/pgtable.h 2001/08/07 05:20:03 1.41
+++ include/asm-sh/pgtable.h 2001/08/07 14:09:53
@@ -52,6 +52,10 @@
/*
* Caches are broken on SH-4, so we need them.
*/
+
+/* Page is 4K, OC size is 16K, there are four lines. */
+#define CACHE_ALIAS 0x00003000
+
extern void flush_cache_all(void);
extern void flush_cache_mm(struct mm_struct *mm);
extern void flush_cache_range(struct mm_struct *mm, unsigned long start,
@@ -70,8 +74,7 @@
extern void __flush_purge_region(void *start, int size);
/* Flush a page */
-extern void __flush_cache_page(unsigned long phys, int exec);
-extern void __flush_icache_page(unsigned long u0, unsigned long phys);
+extern void __flush_cache_page(unsigned long u0, unsigned long phys);
/* Initialization of P3 area for copy_user_page */
extern void p3_cache_init(void);
@@ -297,55 +300,6 @@
* (We needed atomic implementation for SMP)
*
*/
-
-#if defined(__SH4__)
-/* Page is 4K, OC size is 16K, there are four lines. */
-#define CACHE_ALIAS 0x00003000
-/*
- * For SH-4, we have our own implementation for ptep_get_and_clear
- */
-extern pte_t ptep_get_and_clear(pte_t *ptep);
-#else
-static inline pte_t ptep_get_and_clear(pte_t *ptep)
-{
- pte_t pte = *ptep;
- pte_clear(ptep);
- return pte;
-}
-#endif
-
-/*
- * Following functions are same as generic ones.
- */
-static inline int ptep_test_and_clear_young(pte_t *ptep)
-{
- pte_t pte = *ptep;
- if (!pte_young(pte))
- return 0;
- set_pte(ptep, pte_mkold(pte));
- return 1;
-}
-
-static inline int ptep_test_and_clear_dirty(pte_t *ptep)
-{
- pte_t pte = *ptep;
- if (!pte_dirty(pte))
- return 0;
- set_pte(ptep, pte_mkclean(pte));
- return 1;
-}
-
-static inline void ptep_set_wrprotect(pte_t *ptep)
-{
- pte_t old_pte = *ptep;
- set_pte(ptep, pte_wrprotect(old_pte));
-}
-
-static inline void ptep_mkdirty(pte_t *ptep)
-{
- pte_t old_pte = *ptep;
- set_pte(ptep, pte_mkdirty(old_pte));
-}
#define pte_same(A,B) (pte_val(A) == pte_val(B))
--
|
