Menu
▾
▴
RE: [linuxsh-dev] cache-sh4.c
|
From: Dustin M. <du...@se...> - 2002-03-29 18:44:15
|
I've just tried Niibe-san's backport of the cache changes for the 2.4
kernel. I'm running on a SH7751 based system, and I've run into some
trouble. It seems I get a kernel oops (Segmentaton fault) in
__flush_cache_page when using the /bin/ps binary. The oops goes away if I
simply force the CONFIG_CPU_SUBTYPE_SH7750 defines to true and use the 7750
cache method. I'm still working to getting a better idea what is causing
the oops.
Dustin.
> -----Original Message-----
> From: lin...@li...
> [mailto:lin...@li...]On Behalf Of NIIBE
> Yutaka
> Sent: Wednesday, March 27, 2002 9:52 PM
> To: lin...@li...
> Subject: Re: [linuxsh-dev] cache-sh4.c
>
>
> NIIBE Yutaka wrote:
> > Yes. Besides this, we have important bug fixes (FPU thing, syscall
> > restart) and feature (kernel profiling support), which should be merged
> > into 2.4.
>
> The backport.
>
> Here it is.
>
> 2002-03-28 NIIBE Yutaka <gn...@m1...>
>
> * include/asm-sh/uaccess.h (strnlen_user, strlen_user): New inline
> implementation.
> (__clear_user): Make it external function.
>
> * arch/sh/mm/copy_page.S (__copy_user_page): Moved from
> __copy_user_page-sh4.S.
> * arch/sh/mm/__copy_user_page-sh4.S: Removed.
>
> * arch/sh/mm/clear_page.S (__clear_user, __flush_cache_4096): New
> function.
> (__clear_user_page): Moved from __clear_user_page-sh4.S.
> * arch/sh/mm/__clear_user_page-sh4.S: Removed.
>
> * arch/sh/mm/cache-sh4.c (flush_cache_4096): New function.
> (flush_dcache_page): Removed __flush_dcache_page and merged.
> (__flush_icache_page, flush_cache_mm, flush_cache_range): Revert the
> change of 2002-02-27.
> (__flush_cache_page): New function.
> (flush_cache_page): Use __flush_cache_page.
>
> * arch/sh/kernel/setup.c (setup_arch): Bug fix for FPU
> initialization.
>
> * include/asm-sh/mmu_context.h (switch_mm): Remove setting/resetting
> of mm->cpu_vm_mask. It's for SMP implementation.
> (get_new_mmu_context): Removed.
> (get_mmu_context): Merved with get_new_mmu_context.
>
> * include/asm-sh/hw_irq.h (sh_do_profile): Removed from here.
> * arch/sh/kernel/time.c (sh_do_profile): But implemented here.
>
> * include/asm-sh/ptrace.h (struct pt_regs): Renamed syscall_nr to
> tra.
>
> * arch/sh/kernel/process.c (dump_fpu, __switch_to, copy_thread):
> Don't need to protect from interrupt.
> (__switch_to, copy_thread): Don't check if it's init_task or not.
>
> * arch/sh/kernel/signal.c (do_signal): Don't set regs[0].
> Use tra (was: syscall_nr).
> (restore_sigcontext): Use tra.
> (handle_signal): Likewise.
> (save_sigcontext_fpu):
> (save_sigcontext_fpu): Use __put_user (was: __copy_to_user).
> Don't need to protect from interrupt.
>
> * arch/sh/kernel/entry.S (COMPAT_OLD_SYSCALL_ABI): Removed.
> (old_abi_system_call): Removed.
> (OFF_TRA): Renamed from SYSCALL_NR.
> (system_call): Use OFF_TRA and the value is now tra (was: encoded
> value).
>
> Index: arch/sh/kernel/entry.S
> ===================================================================
> RCS file: /cvsroot/linuxsh/linux/arch/sh/kernel/entry.S,v
> retrieving revision 1.1.1.1.2.2
> diff -u -3 -p -r1.1.1.1.2.2 entry.S
> --- arch/sh/kernel/entry.S 26 Feb 2002 11:42:29 -0000 1.1.1.1.2.2
> +++ arch/sh/kernel/entry.S 28 Mar 2002 05:49:28 -0000
> @@ -15,12 +15,6 @@
> #include <linux/config.h>
>
>
> -/*
> - * Define this to turn on compatibility with the previous
> - * system call ABI. This feature is not properly maintained.
> - */
> -#undef COMPAT_OLD_SYSCALL_ABI
> -
> ! NOTE:
> ! GNU as (as of 2.9.1) changes bf/s into bt/s and bra, when the address
> ! to be jumped is too far, but it causes illegal slot exception.
> @@ -97,7 +91,7 @@ OFF_R6 = 24 /* New ABI: ar
> OFF_R7 = 28 /* New ABI: arg3 */
> OFF_SP = (15*4)
> OFF_SR = (16*4+8)
> -SYSCALL_NR = (16*4+6*4)
> +OFF_TRA = (16*4+6*4)
>
>
> #define k0 r0
> @@ -345,29 +339,15 @@ system_call:
> mov.l @r9, r8
> !
> ! Is the trap argument >= 0x20? (TRA will be >= 0x80)
> - mov #0x20, r9
> - extu.b r9, r9
> - shll2 r9
> - cmp/hs r9, r8
> + mov #0x7f, r9
> + cmp/hi r9, r8
> bt debug_trap
> !
> - mov #SYSCALL_NR, r14
> + mov #OFF_TRA, r14
> add r15, r14
> !
> -#ifdef COMPAT_OLD_SYSCALL_ABI
> - mov #0x40, r9
> - cmp/hs r9, r8
> - bf/s old_abi_system_call
> - nop
> -#endif
> ! New Syscall ABI
> - add #-0x40, r8
> - shlr2 r8
> - shll8 r8
> - shll8 r8 ! r8 = num_args<<16
> - mov r3, r10
> - or r8, r10 ! Encode syscall # and # of arguments
> - mov.l r10, @r14 ! set syscall_nr
> + mov.l r8, @r14 ! set tra
> STI()
> !
> stc k_current, r11
> @@ -426,74 +406,6 @@ syscall_ret_trace:
> jmp @r1 ! Call syscall_trace() which notifies superior
> lds r0, pr ! Then return to ret_from_syscall()
>
> -
> -
> -#ifdef COMPAT_OLD_SYSCALL_ABI
> -! Handle old ABI system call.
> -! Note that ptrace(SYSCALL) is not supported for the old ABI.
> -! At this point:
> -! r0, r4-7 as per ABI
> -! r8 = value of TRA register (= num_args<<2)
> -! r14 = points to SYSCALL_NR in stack frame
> -old_abi_system_call:
> - mov r0, r9 ! Save system call number in r9
> - ! ! arrange for return which
> pops stack
> - mov.l __old_abi_syscall_ret, r10
> - lds r10, pr
> - ! Build the stack frame if TRA > 0
> - mov r8, r10
> - cmp/pl r10
> - bf 0f
> - mov.l @(OFF_SP,r15), r0 ! get original user stack
> -7: add #-4, r10
> -4: mov.l @(r0,r10), r1 ! May cause address error exception..
> - mov.l r1, @-r15
> - cmp/pl r10
> - bt 7b
> -0:
> - mov.l r9, @r14 ! set syscall_nr
> - STI()
> - ! Call the system call handler through the table.
> - ! First check for bad syscall number
> - mov.l __n_sys, r10
> - cmp/hs r10, r9
> - bf 2f
> - ! Bad syscall number
> - rts ! return to old_abi_syscall_ret
> - mov #-ENOSYS, r0
> - ! Good syscall number
> -2: shll2 r9 ! x4
> - mov.l __sct, r11
> - add r11, r9
> - mov.l @r9, r11
> - jmp @r11 ! call specific syscall handler,
> - nop
> -
> - .align 2
> -__old_abi_syscall_ret:
> - .long old_abi_syscall_ret
> -
> - ! This code gets called on address error exception when copying
> - ! syscall arguments from user stack to kernel stack. It is
> - ! supposed to return -EINVAL through old_abi_syscall_ret, but it
> - ! appears to have been broken for a long time in that the r0
> - ! return value will be saved into the kernel stack relative to r15
> - ! but the value of r15 is not correct partway through the loop.
> - ! So the user prog is returned its old r0 value, not -EINVAL.
> - ! Greg Banks 28 Aug 2000.
> - .section .fixup,"ax"
> -fixup_syscall_argerr:
> - ! First get r15 back to
> - rts
> - mov #-EINVAL, r0
> - .previous
> -
> - .section __ex_table, "a"
> - .align 2
> - .long 4b,fixup_syscall_argerr
> - .previous
> -#endif
> -
> .align 2
> __TRA: .long TRA
> __syscall_trace:
> @@ -529,11 +441,6 @@ ret_from_exception:
> nop
>
> .align 2
> -#ifdef COMPAT_OLD_SYSCALL_ABI
> -old_abi_syscall_ret:
> - add r8, r15 ! pop off the arguments
> - /* fall through */
> -#endif
> syscall_ret:
> mov.l r0, @(OFF_R0,r15) ! save the return value
> /* fall through */
> @@ -685,7 +592,7 @@ handle_exception:
> 9: mov #-1, k4
> mov.l 3f, k1
> ! Save the user registers on the stack.
> - mov.l k4, @-r15 ! syscall_nr (default: -1)
> + mov.l k4, @-r15 ! Set tra (default: -1)
> !
> sts.l macl, @-r15
> sts.l mach, @-r15
> Index: arch/sh/kernel/process.c
> ===================================================================
> RCS file: /cvsroot/linuxsh/linux/arch/sh/kernel/process.c,v
> retrieving revision 1.1.1.1
> diff -u -3 -p -r1.1.1.1 process.c
> --- arch/sh/kernel/process.c 15 Oct 2001 20:44:51 -0000 1.1.1.1
> +++ arch/sh/kernel/process.c 28 Mar 2002 05:49:28 -0000
> @@ -179,11 +179,7 @@ int dump_fpu(struct pt_regs *regs, elf_f
>
> fpvalid = tsk->used_math;
> if (fpvalid) {
> - unsigned long flags;
> -
> - save_and_cli(flags);
> unlazy_fpu(tsk);
> - restore_flags(flags);
> memcpy(fpu, &tsk->thread.fpu.hard, sizeof(*fpu));
> }
>
> @@ -203,15 +199,9 @@ int copy_thread(int nr, unsigned long cl
> #if defined(__SH4__)
> struct task_struct *tsk = current;
>
> - if (tsk != &init_task) {
> - unsigned long flags;
> -
> - save_and_cli(flags);
> - unlazy_fpu(tsk);
> - restore_flags(flags);
> - p->thread.fpu = current->thread.fpu;
> - p->used_math = tsk->used_math;
> - }
> + unlazy_fpu(tsk);
> + p->thread.fpu = current->thread.fpu;
> + p->used_math = tsk->used_math;
> #endif
> childregs = ((struct pt_regs *)(THREAD_SIZE + (unsigned
> long) p)) - 1;
> *childregs = *regs;
> @@ -257,13 +247,7 @@ void dump_thread(struct pt_regs * regs,
> void __switch_to(struct task_struct *prev, struct task_struct *next)
> {
> #if defined(__SH4__)
> - if (prev != &init_task) {
> - unsigned long flags;
> -
> - save_and_cli(flags);
> - unlazy_fpu(prev);
> - restore_flags(flags);
> - }
> + unlazy_fpu(prev);
> #endif
> /*
> * Restore the kernel mode register
> Index: arch/sh/kernel/setup.c
> ===================================================================
> RCS file: /cvsroot/linuxsh/linux/arch/sh/kernel/setup.c,v
> retrieving revision 1.1.1.1.2.1
> diff -u -3 -p -r1.1.1.1.2.1 setup.c
> --- arch/sh/kernel/setup.c 30 Nov 2001 23:03:33 -0000 1.1.1.1.2.1
> +++ arch/sh/kernel/setup.c 28 Mar 2002 05:49:28 -0000
> @@ -485,9 +485,8 @@ void __init setup_arch(char **cmdline_p)
> }
>
> #if defined(__SH4__)
> - /* We already grab/initialized FPU in head.S. Make it
> consisitent. */
> - init_task.used_math = 1;
> - init_task.flags |= PF_USEDFPU;
> + init_task.used_math = 0;
> + init_task.flags &= ~PF_USEDFPU;
> #endif
> paging_init();
> }
> Index: arch/sh/kernel/signal.c
> ===================================================================
> RCS file: /cvsroot/linuxsh/linux/arch/sh/kernel/signal.c,v
> retrieving revision 1.1.1.1
> diff -u -3 -p -r1.1.1.1 signal.c
> --- arch/sh/kernel/signal.c 15 Oct 2001 20:44:52 -0000 1.1.1.1
> +++ arch/sh/kernel/signal.c 28 Mar 2002 05:49:28 -0000
> @@ -196,27 +196,20 @@ static inline int restore_sigcontext_fpu
> static inline int save_sigcontext_fpu(struct sigcontext *sc)
> {
> struct task_struct *tsk = current;
> - unsigned long flags;
> - int val;
>
> if (!tsk->used_math) {
> - val = 0;
> - __copy_to_user(&sc->sc_ownedfp, &val, sizeof(int));
> + __put_user(0, &sc->sc_ownedfp);
> return 0;
> }
>
> - val = 1;
> - __copy_to_user(&sc->sc_ownedfp, &val, sizeof(int));
> + __put_user(1, &sc->sc_ownedfp);
>
> /* This will cause a "finit" to be triggered by the next
> attempted FPU operation by the 'current' process.
> */
> tsk->used_math = 0;
>
> - save_and_cli(flags);
> unlazy_fpu(tsk);
> - restore_flags(flags);
> -
> return __copy_to_user(&sc->sc_fpregs[0], &tsk->thread.fpu.hard,
> sizeof(long)*(16*2+2));
> }
> @@ -255,7 +248,7 @@ restore_sigcontext(struct pt_regs *regs,
> }
> #endif
>
> - regs->syscall_nr = -1; /* disable syscall checks */
> + regs->tra = -1; /* disable syscall checks */
> err |= __get_user(*r0_p, &sc->sc_regs[0]);
> return err;
> }
> @@ -524,7 +517,7 @@ handle_signal(unsigned long sig, struct
> siginfo_t *info, sigset_t *oldset, struct pt_regs * regs)
> {
> /* Are we from a system call? */
> - if (regs->syscall_nr >= 0) {
> + if (regs->tra >= 0) {
> /* If so, check system call restarting.. */
> switch (regs->regs[0]) {
> case -ERESTARTNOHAND:
> @@ -538,7 +531,6 @@ handle_signal(unsigned long sig, struct
> }
> /* fallthrough */
> case -ERESTARTNOINTR:
> - regs->regs[0] = regs->syscall_nr;
> regs->pc -= 2;
> }
> }
> @@ -685,12 +677,11 @@ int do_signal(struct pt_regs *regs, sigs
> }
>
> /* Did we come from a system call? */
> - if (regs->syscall_nr >= 0) {
> + if (regs->tra >= 0) {
> /* Restart the system call - no handlers present */
> if (regs->regs[0] == -ERESTARTNOHAND ||
> regs->regs[0] == -ERESTARTSYS ||
> regs->regs[0] == -ERESTARTNOINTR) {
> - regs->regs[0] = regs->syscall_nr;
> regs->pc -= 2;
> }
> }
> Index: arch/sh/kernel/time.c
> ===================================================================
> RCS file: /cvsroot/linuxsh/linux/arch/sh/kernel/time.c,v
> retrieving revision 1.1.1.1
> diff -u -3 -p -r1.1.1.1 time.c
> --- arch/sh/kernel/time.c 15 Oct 2001 20:44:50 -0000 1.1.1.1
> +++ arch/sh/kernel/time.c 28 Mar 2002 05:49:28 -0000
> @@ -176,6 +176,25 @@ void do_settimeofday(struct timeval *tv)
> /* last time the RTC clock got updated */
> static long last_rtc_update;
>
> +static __inline__ void sh_do_profile (unsigned long pc)
> +{
> + extern int _stext;
> +
> + if (!prof_buffer)
> + return;
> +
> + pc -= (unsigned long) &_stext;
> + pc >>= prof_shift;
> + /*
> + * Don't ignore out-of-bounds PC values silently,
> + * put them into the last histogram slot, so if
> + * present, they will show up as a sharp peak.
> + */
> + if (pc > prof_len-1)
> + pc = prof_len-1;
> + prof_buffer[pc]++;
> +}
> +
> /*
> * timer_interrupt() needs to keep up the real-time clock,
> * as well as call the "do_timer()" routine every clocktick
> Index: arch/sh/mm/Makefile
> ===================================================================
> RCS file: /cvsroot/linuxsh/linux/arch/sh/mm/Makefile,v
> retrieving revision 1.1.1.1
> diff -u -3 -p -r1.1.1.1 Makefile
> --- arch/sh/mm/Makefile 15 Oct 2001 20:44:53 -0000 1.1.1.1
> +++ arch/sh/mm/Makefile 28 Mar 2002 05:49:28 -0000
> @@ -11,7 +11,7 @@ O_TARGET := mm.o
> obj-y := init.o fault.o extable.o clear_page.o copy_page.o
>
> obj-$(CONFIG_CPU_SH3) += cache-sh3.o
> -obj-$(CONFIG_CPU_SH4) += cache-sh4.o __clear_user_page-sh4.o
> __copy_user_page-sh4.o ioremap.o
> +obj-$(CONFIG_CPU_SH4) += cache-sh4.o ioremap.o
>
> USE_STANDARD_AS_RULE := true
>
> Index: arch/sh/mm/cache-sh4.c
> ===================================================================
> RCS file: /cvsroot/linuxsh/linux/arch/sh/mm/cache-sh4.c,v
> retrieving revision 1.1.1.1.2.3
> diff -u -3 -p -r1.1.1.1.2.3 cache-sh4.c
> --- arch/sh/mm/cache-sh4.c 22 Mar 2002 14:02:09 -0000 1.1.1.1.2.3
> +++ arch/sh/mm/cache-sh4.c 28 Mar 2002 05:49:28 -0000
> @@ -1,9 +1,8 @@
> /* $Id: cache-sh4.c,v 1.1.1.1.2.3 2002/03/22 14:02:09 gniibe Exp $
> *
> - * linux/arch/sh/mm/cache.c
> + * linux/arch/sh/mm/cache-sh4.c
> *
> - * Copyright (C) 1999, 2000 Niibe Yutaka
> - * Copyright (C) 2001, 2002 Paul Mundt
> + * Copyright (C) 1999, 2000, 2002 Niibe Yutaka
> */
>
> #include <linux/config.h>
> @@ -208,55 +207,34 @@ void flush_cache_sigtramp(unsigned long
> restore_flags(flags);
> }
>
> -/*
> - * Writeback&Invalidate the D-cache of the page
> - */
> -static void __flush_dcache_page(unsigned long phys)
> -{
> - unsigned long addr, data;
> - unsigned long flags;
> -
> - phys |= CACHE_VALID;
> -
> - 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);
> - }
> -
> - back_to_P1();
> - restore_flags(flags);
> -}
> -
> -static void __flush_icache_page(unsigned long phys)
> +static inline void flush_cache_4096(unsigned long start,
> + unsigned long phys)
> {
> +#if defined(CONFIG_CPU_SUBTYPE_SH7750)
> + register unsigned long addr __asm__ ("r4");
> + register unsigned long data __asm__ ("r0");
> + register unsigned long __r5 __asm__ ("r5") = phys;
> + register unsigned long __r6 __asm__ ("r6") =
> (0x1ffff000|CACHE_VALID);
> + register unsigned long __r7 __asm__ ("r7") = 0;
> + extern void __flush_cache_4096(unsigned long, unsigned long);
> +
> + asm volatile("jsr @%1; nop"
> + : "=r" (addr), "=r" (data)
> + : "0" (start), "1" (__flush_cache_4096 + 0x20000000),
> + "r" (__r5), "r" (__r6), "r" (__r7)
> + : "pr");
> +#else
> + /*
> + * SH7751 and ST40 have no restriction to handle cache.
> + * (While SH7750 must do that at P2 area.)
> + */
> unsigned long addr, data;
> - unsigned long flags;
> -
> - phys |= CACHE_VALID;
> -
> - save_and_cli(flags);
> - 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)) {
> + for (addr = start; addr < start + 4096; addr += 32) {
> data = ctrl_inl(addr)&(0x1ffff000|CACHE_VALID);
> if (data == phys)
> ctrl_outl(0, addr);
> }
> -
> - back_to_P1();
> - restore_flags(flags);
> +#endif
> }
>
> /*
> @@ -265,8 +243,22 @@ static void __flush_icache_page(unsigned
> */
> void flush_dcache_page(struct page *page)
> {
> - if (test_bit(PG_mapped, &page->flags))
> - __flush_dcache_page(PHYSADDR(page_address(page)));
> + if (test_bit(PG_mapped, &page->flags)) {
> + unsigned long phys = PHYSADDR(page_address(page));
> + unsigned long flags;
> +
> + phys |= CACHE_VALID;
> +
> + save_and_cli(flags);
> +
> + /* Loop all the D-cache */
> + flush_cache_4096(CACHE_OC_ADDRESS_ARRAY, phys);
> + flush_cache_4096(CACHE_OC_ADDRESS_ARRAY | 0x1000, phys);
> + flush_cache_4096(CACHE_OC_ADDRESS_ARRAY | 0x2000, phys);
> + flush_cache_4096(CACHE_OC_ADDRESS_ARRAY | 0x3000, phys);
> +
> + restore_flags(flags);
> + }
> }
>
> void flush_cache_all(void)
> @@ -298,15 +290,43 @@ void flush_cache_mm(struct mm_struct *mm
> * FIXME: Really, the optimal solution here would be able
> to flush out
> * individual lines created by the specified context, but this isn't
> * feasible for a number of architectures (such as MIPS, and some
> - * SPARC) .. is this possible for SuperH? (This is a
> non-issue if the
> - * SH4 cache is configured in write-through mode).
> + * SPARC) .. is this possible for SuperH?
> *
> - * In the meantime, we'll just flush all of the caches if we have a
> - * valid mm context.. this seems to be the simplest way to avoid at
> - * least a few wasted cache flushes. -Lethal
> + * In the meantime, we'll just flush all of the caches.. this
> + * seems to be the simplest way to avoid at least a few wasted
> + * cache flushes. -Lethal
> */
> - if (mm->context != 0)
> - flush_cache_all();
> + flush_cache_all();
> +}
> +
> +static void __flush_cache_page(struct vm_area_struct *vma,
> + unsigned long address,
> + unsigned long phys)
> +{
> + unsigned long flags;
> +
> + phys |= CACHE_VALID;
> + save_and_cli(flags);
> +
> + /* We only need to flush D-cache when we have alias */
> + if ((address^phys) & CACHE_ALIAS) {
> + /* Loop 4K of the D-cache */
> + flush_cache_4096(
> + CACHE_OC_ADDRESS_ARRAY | (address & CACHE_ALIAS),
> + phys);
> + /* Loop another 4K of the D-cache */
> + flush_cache_4096(
> + CACHE_OC_ADDRESS_ARRAY | (phys & CACHE_ALIAS),
> + phys);
> + }
> +
> + if (vma->vm_flags & VM_EXEC)
> + /* Loop 4K (half) of the I-cache */
> + flush_cache_4096(
> + CACHE_IC_ADDRESS_ARRAY | (address & 0x1000),
> + phys);
> +
> + restore_flags(flags);
> }
>
> /*
> @@ -321,39 +341,15 @@ void flush_cache_mm(struct mm_struct *mm
> void flush_cache_range(struct mm_struct *mm, unsigned long start,
> unsigned long end)
> {
> - unsigned long flags;
> -
> - if (mm->context == 0)
> - return;
> -
> - start &= PAGE_MASK;
> -
> - if (!find_vma(mm, start))
> - return;
> - if (mm->context != current->active_mm->context) {
> - flush_cache_all();
> - } else {
> - pgd_t *pgd;
> - pmd_t *pmd;
> - pte_t *pte;
> -
> - save_and_cli(flags);
> - jump_to_P2();
> -
> - for (start; start < end; start += PAGE_SIZE) {
> - pgd = pgd_offset(mm, start);
> - pmd = pmd_offset(pgd, start);
> - pte = pte_offset(pmd, start);
> -
> - if (pte_val(*pte) & _PAGE_PRESENT) {
> - __flush_icache_page(start);
> - __flush_dcache_page(start);
> - }
> - }
> -
> - back_to_P1();
> - restore_flags(flags);
> - }
> + /*
> + * We could call flush_cache_page for the pages of these
> + * range, but it's really time consuming (we have to scan the
> + * caches all the time...).
> + *
> + * We can't use A-bit magic, as there's the case we don't have
> + * valid entry on TLB.
> + */
> + flush_cache_all();
> }
>
> /*
> @@ -367,8 +363,7 @@ void flush_cache_page(struct vm_area_str
> pmd_t *pmd;
> pte_t *pte;
> pte_t entry;
> - unsigned long phys, addr, data;
> - unsigned long flags;
> + unsigned long phys;
>
> dir = pgd_offset(vma->vm_mm, address);
> pmd = pmd_offset(dir, address);
> @@ -376,49 +371,11 @@ void flush_cache_page(struct vm_area_str
> return;
> pte = pte_offset(pmd, address);
> entry = *pte;
> - if (pte_none(entry) || !pte_present(entry))
> + if (!(pte_val(entry) & _PAGE_PRESENT))
> return;
>
> phys = pte_val(entry)&PTE_PHYS_MASK;
> -
> - phys |= CACHE_VALID;
> - save_and_cli(flags);
> - jump_to_P2();
> -
> - /* We only need to flush D-cache when we have alias */
> - if ((address^phys) & CACHE_ALIAS) {
> - /* Loop 4K of the D-cache */
> - for (addr = CACHE_OC_ADDRESS_ARRAY | (address &
> CACHE_ALIAS);
> - addr < (CACHE_OC_ADDRESS_ARRAY + (address &
> 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);
> - }
> - }
> -
> - if (vma->vm_flags & VM_EXEC)
> - /* Loop 4K of the I-cache */
> - for (addr = CACHE_IC_ADDRESS_ARRAY|(address&0x1000);
> - addr < ((CACHE_IC_ADDRESS_ARRAY|(address&0x1000))
> -
> +(CACHE_IC_NUM_ENTRIES/2<<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);
> + __flush_cache_page(vma, address, phys);
> }
>
> /*
> Index: arch/sh/mm/clear_page.S
> ===================================================================
> RCS file: /cvsroot/linuxsh/linux/arch/sh/mm/clear_page.S,v
> retrieving revision 1.1.1.1
> diff -u -3 -p -r1.1.1.1 clear_page.S
> --- arch/sh/mm/clear_page.S 15 Oct 2001 20:44:53 -0000 1.1.1.1
> +++ arch/sh/mm/clear_page.S 28 Mar 2002 05:49:28 -0000
> @@ -1,10 +1,13 @@
> /* $Id: clear_page.S,v 1.1.1.1 2001/10/15 20:44:53 mrbrown Exp $
> *
> - * clear_page implementation of SuperH
> + * __clear_user_page, __clear_user, clear_page implementation of SuperH
> *
> - * Copyright (C) 2001 Niibe Yutaka & Kaz Kojima
> + * Copyright (C) 2001 Kaz Kojima
> + * Copyright (C) 2001, 2002 Niibe Yutaka
> *
> */
> +#include <linux/config.h>
> +#include <linux/linkage.h>
>
> /*
> * clear_page
> @@ -18,7 +21,6 @@
> * r4 --- to
> * r5 --- to + 4096
> */
> -#include <linux/linkage.h>
> ENTRY(clear_page)
> mov r4,r5
> mov.w .Llimit,r0
> @@ -50,3 +52,154 @@ ENTRY(clear_page)
> rts
> nop
> .Llimit: .word (4096-28)
> +
> +ENTRY(__clear_user)
> + !
> + mov #0, r0
> + mov #0xe0, r1 ! 0xffffffe0
> + !
> + ! r4..r4&~32 -------- not aligned [ Area 0 ]
> + ! r4&~32..(r4+r5)&~32 -------- aligned [ Area 1 ]
> + ! (r4+r5)&~32..r4+r5 -------- not aligned [ Area 2 ]
> + !
> + ! Clear area 0
> + mov r4, r2
> + and r1, r2
> + cmp/eq r4, r2
> + bt/s area1
> + mov r4, r3
> + sub r2, r3
> + mov r4, r2
> + !
> +l0: dt r3
> +0: mov.b r0, @r2
> + bf/s l0
> + add #1, r2
> + !
> + mov r4, r3
> + add r5, r3
> + and r1, r3
> + !
> + ! Clear area 1
> +area1:
> +#if defined(__SH4__)
> +1: movca.l r0, @r2
> +#else
> +1: mov.l r0, @r2
> +#endif
> + add #4, r2
> +2: mov.l r0, @r2
> + add #4, r2
> +3: mov.l r0, @r2
> + add #4, r2
> +4: mov.l r0, @r2
> + add #4, r2
> +5: mov.l r0, @r2
> + add #4, r2
> +6: mov.l r0, @r2
> + add #4, r2
> +7: mov.l r0, @r2
> + add #4, r2
> +8: mov.l r0, @r2
> + add #4, r2
> + cmp/hi r2, r3
> + bt/s 1b
> + nop
> + !
> + ! Clear area 2
> + add r5, r4
> + cmp/eq r4, r2
> + bt/s done
> + sub r2, r4
> +l2: dt r4
> +9: mov.b r0, @r2
> + bf/s l2
> + add #1, r2
> + !
> +done: rts
> + nop ! return 0 as normal return
> +
> + ! return the number of bytes remained
> +bad_clear_user:
> + mov r4, r0
> + mov r5, r0
> + rts
> + sub r2, r0
> +
> +.section __ex_table,"a"
> + .align 2
> + .long 0b, bad_clear_user
> + .long 1b, bad_clear_user
> + .long 2b, bad_clear_user
> + .long 3b, bad_clear_user
> + .long 4b, bad_clear_user
> + .long 5b, bad_clear_user
> + .long 6b, bad_clear_user
> + .long 7b, bad_clear_user
> + .long 8b, bad_clear_user
> + .long 9b, bad_clear_user
> +.previous
> +
> +#if defined(__SH4__)
> +/*
> + * __clear_user_page
> + * @to: P1 address (with same color)
> + * @orig_to: P1 address
> + *
> + * void __clear_user_page(void *to, void *orig_to)
> + */
> +
> +/*
> + * r0 --- scratch
> + * r4 --- to
> + * r5 --- orig_to
> + * r6 --- to + 4096
> + */
> +ENTRY(__clear_user_page)
> + mov.w .L4096,r0
> + mov r4,r6
> + add r0,r6
> + mov #0,r0
> + !
> +1: ocbi @r5
> + add #32,r5
> + movca.l r0,@r4
> + mov r4,r1
> + add #32,r4
> + mov.l r0,@-r4
> + mov.l r0,@-r4
> + mov.l r0,@-r4
> + mov.l r0,@-r4
> + mov.l r0,@-r4
> + mov.l r0,@-r4
> + mov.l r0,@-r4
> + add #28,r4
> + cmp/eq r6,r4
> + bf/s 1b
> + ocbwb @r1
> + !
> + rts
> + nop
> +.L4096: .word 4096
> +
> +#if defined(CONFIG_CPU_SUBTYPE_SH7750)
> +ENTRY(__flush_cache_4096)
> + .rept 128
> + mov.l @r4,r0
> + and r6,r0
> + cmp/eq r5,r0
> + bf 1f
> + mov.l r7,@r4
> +1: add #32,r4
> + .endr
> + nop
> + nop
> + nop
> + nop
> + nop
> + nop
> + nop
> + rts
> + nop
> +#endif
> +#endif
> Index: arch/sh/mm/copy_page.S
> ===================================================================
> RCS file: /cvsroot/linuxsh/linux/arch/sh/mm/copy_page.S,v
> retrieving revision 1.1.1.1
> diff -u -3 -p -r1.1.1.1 copy_page.S
> --- arch/sh/mm/copy_page.S 15 Oct 2001 20:44:53 -0000 1.1.1.1
> +++ arch/sh/mm/copy_page.S 28 Mar 2002 05:49:28 -0000
> @@ -1,10 +1,11 @@
> /* $Id: copy_page.S,v 1.1.1.1 2001/10/15 20:44:53 mrbrown Exp $
> *
> - * copy_page implementation of SuperH
> + * copy_page, __copy_user_page implementation of SuperH
> *
> * Copyright (C) 2001 Niibe Yutaka & Kaz Kojima
> *
> */
> +#include <linux/linkage.h>
>
> /*
> * copy_page
> @@ -21,7 +22,6 @@
> * r10 --- to
> * r11 --- from
> */
> -#include <linux/linkage.h>
> ENTRY(copy_page)
> mov.l r8,@-r15
> mov.l r10,@-r15
> @@ -66,4 +66,67 @@ ENTRY(copy_page)
> mov.l @r15+,r8
> rts
> nop
> +
> +#if defined(__SH4__)
> +/*
> + * __copy_user_page
> + * @to: P1 address (with same color)
> + * @from: P1 address
> + * @orig_to: P1 address
> + *
> + * void __copy_user_page(void *to, void *from, void *orig_to)
> + */
> +
> +/*
> + * r0, r1, r2, r3, r4, r5, r6, r7 --- scratch
> + * r8 --- from + 4096
> + * r9 --- orig_to
> + * r10 --- to
> + * r11 --- from
> + */
> +#include <linux/linkage.h>
> +ENTRY(__copy_user_page)
> + mov.l r8,@-r15
> + mov.l r9,@-r15
> + mov.l r10,@-r15
> + mov.l r11,@-r15
> + mov r4,r10
> + mov r5,r11
> + mov r6,r9
> + mov r5,r8
> + mov.w .L4096,r0
> + add r0,r8
> + !
> +1: ocbi @r9
> + add #32,r9
> + mov.l @r11+,r0
> + mov.l @r11+,r1
> + mov.l @r11+,r2
> + mov.l @r11+,r3
> + mov.l @r11+,r4
> + mov.l @r11+,r5
> + mov.l @r11+,r6
> + mov.l @r11+,r7
> + movca.l r0,@r10
> + mov r10,r0
> + add #32,r10
> + mov.l r7,@-r10
> + mov.l r6,@-r10
> + mov.l r5,@-r10
> + mov.l r4,@-r10
> + mov.l r3,@-r10
> + mov.l r2,@-r10
> + mov.l r1,@-r10
> + ocbwb @r0
> + cmp/eq r11,r8
> + bf/s 1b
> + add #28,r10
> + !
> + mov.l @r15+,r11
> + mov.l @r15+,r10
> + mov.l @r15+,r9
> + mov.l @r15+,r8
> + rts
> + nop
> +#endif
> .L4096: .word 4096
> Index: include/asm-sh/hw_irq.h
> ===================================================================
> RCS file: /cvsroot/linuxsh/linux/include/asm-sh/hw_irq.h,v
> retrieving revision 1.1.1.1
> diff -u -3 -p -r1.1.1.1 hw_irq.h
> --- include/asm-sh/hw_irq.h 15 Oct 2001 20:45:08 -0000 1.1.1.1
> +++ include/asm-sh/hw_irq.h 28 Mar 2002 05:49:28 -0000
> @@ -1,6 +1,4 @@
> #ifndef __ASM_SH_HW_IRQ_H
> #define __ASM_SH_HW_IRQ_H
> -static __inline__ void sh_do_profile (unsigned long pc) {/*Not
> implemented yet*/}
> -
> static __inline__ void hw_resend_irq(struct hw_interrupt_type
> *h, unsigned int i) { /* Nothing to do */ }
> #endif /* __ASM_SH_HW_IRQ_H */
> Index: include/asm-sh/mmu_context.h
> ===================================================================
> RCS file: /cvsroot/linuxsh/linux/include/asm-sh/mmu_context.h,v
> retrieving revision 1.1.1.1
> diff -u -3 -p -r1.1.1.1 mmu_context.h
> --- include/asm-sh/mmu_context.h 15 Oct 2001 20:45:10 -0000
> 1.1.1.1
> +++ include/asm-sh/mmu_context.h 28 Mar 2002 05:49:28 -0000
> @@ -29,19 +29,32 @@ extern unsigned long mmu_context_cache;
> */
> #define MMU_VPN_MASK 0xfffff000
>
> +/*
> + * Get MMU context if needed.
> + */
> static __inline__ void
> -get_new_mmu_context(struct mm_struct *mm)
> +get_mmu_context(struct mm_struct *mm)
> {
> extern void flush_tlb_all(void);
> + unsigned long mc = mmu_context_cache;
>
> - unsigned long mc = ++mmu_context_cache;
> + /* Check if we have old version of context. */
> + if (((mm->context ^ mc) & MMU_CONTEXT_VERSION_MASK) == 0)
> + /* It's up to date, do nothing */
> + return;
>
> + /* It's old, we need to get new context with new version. */
> + mc = ++mmu_context_cache;
> if (!(mc & MMU_CONTEXT_ASID_MASK)) {
> - /* We exhaust ASID of this version.
> - Flush all TLB and start new cycle. */
> + /*
> + * We exhaust ASID of this version.
> + * Flush all TLB and start new cycle.
> + */
> flush_tlb_all();
> - /* Fix version if needed.
> - Note that we avoid version #0 to distingush
> NO_CONTEXT. */
> + /*
> + * Fix version; Note that we avoid version #0
> + * to distingush NO_CONTEXT.
> + */
> if (!mc)
> mmu_context_cache = mc = MMU_CONTEXT_FIRST_VERSION;
> }
> @@ -49,21 +62,6 @@ get_new_mmu_context(struct mm_struct *mm
> }
>
> /*
> - * Get MMU context if needed.
> - */
> -static __inline__ void
> -get_mmu_context(struct mm_struct *mm)
> -{
> - if (mm) {
> - unsigned long mc = mmu_context_cache;
> - /* Check if we have old version of context.
> - If it's old, we need to get new context with new
> version. */
> - if ((mm->context ^ mc) & MMU_CONTEXT_VERSION_MASK)
> - get_new_mmu_context(mm);
> - }
> -}
> -
> -/*
> * Initialize the context related info for a new mm_struct
> * instance.
> */
> @@ -169,8 +167,6 @@ static __inline__ void switch_mm(struct
> if (prev != next) {
> unsigned long __pgdir = (unsigned long)next->pgd;
>
> - clear_bit(cpu, &prev->cpu_vm_mask);
> - set_bit(cpu, &next->cpu_vm_mask);
> __asm__ __volatile__("mov.l %0, %1"
> : /* no output */
> : "r" (__pgdir), "m" (__m(MMU_TTB)));
> @@ -185,4 +181,5 @@ static __inline__ void
> enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk,
> unsigned cpu)
> {
> }
> +
> #endif /* __ASM_SH_MMU_CONTEXT_H */
> Index: include/asm-sh/ptrace.h
> ===================================================================
> RCS file: /cvsroot/linuxsh/linux/include/asm-sh/ptrace.h,v
> retrieving revision 1.1.1.1
> diff -u -3 -p -r1.1.1.1 ptrace.h
> --- include/asm-sh/ptrace.h 15 Oct 2001 20:45:11 -0000 1.1.1.1
> +++ include/asm-sh/ptrace.h 28 Mar 2002 05:49:28 -0000
> @@ -61,7 +61,7 @@ struct pt_regs {
> unsigned long gbr;
> unsigned long mach;
> unsigned long macl;
> - long syscall_nr;
> + long tra;
> };
>
> #ifdef __KERNEL__
> Index: include/asm-sh/uaccess.h
> ===================================================================
> RCS file: /cvsroot/linuxsh/linux/include/asm-sh/uaccess.h,v
> retrieving revision 1.1.1.1.2.1
> diff -u -3 -p -r1.1.1.1.2.1 uaccess.h
> --- include/asm-sh/uaccess.h 3 Nov 2001 00:52:47 -0000 1.1.1.1.2.1
> +++ include/asm-sh/uaccess.h 28 Mar 2002 05:49:28 -0000
> @@ -308,39 +308,11 @@ __copy_res; })
> __copy_user((void *)(to), \
> (void *)(from), n)
>
> -/* XXX: Not sure it works well..
> - should be such that: 4byte clear and the rest. */
> -static __inline__ __kernel_size_t
> -__clear_user(void *addr, __kernel_size_t size)
> -{
> - unsigned long __a;
> -
> - __asm__ __volatile__(
> - "9:\n\t"
> - "dt %0\n"
> - "1:\n\t"
> - "mov.b %4, @%1\n\t"
> - "bf/s 9b\n\t"
> - " add #1, %1\n"
> - "2:\n"
> - ".section .fixup,\"ax\"\n"
> - "3:\n\t"
> - "mov.l 4f, %1\n\t"
> - "jmp @%1\n\t"
> - " nop\n"
> - ".balign 4\n"
> - "4: .long 2b\n"
> - ".previous\n"
> - ".section __ex_table,\"a\"\n"
> - " .balign 4\n"
> - " .long 1b,3b\n"
> - ".previous"
> - : "=r" (size), "=r" (__a)
> - : "0" (size), "1" (addr), "r" (0)
> - : "memory", "t");
> -
> - return size;
> -}
> +/*
> + * Clear the area and return remaining number of bytes
> + * (on failure. Usually it's 0.)
> + */
> +extern __kernel_size_t __clear_user(void *addr, __kernel_size_t size);
>
> #define clear_user(addr,n) ({ \
> void * __cl_addr = (addr); \
> @@ -396,8 +368,6 @@ if(__access_ok(__sfu_src, __sfu_count))
> __sfu_res = __strncpy_from_user((unsigned long) (dest),
> __sfu_src, __sfu_count); \
> } __sfu_res; })
>
> -#define strlen_user(str) strnlen_user(str, ~0UL >> 1)
> -
> /*
> * Return the size of a string (including the ending 0!)
> */
> @@ -436,10 +406,18 @@ static __inline__ long __strnlen_user(co
>
> static __inline__ long strnlen_user(const char *s, long n)
> {
> - if (!__addr_ok(s))
> + if (!access_ok(VERIFY_READ, s, n))
> return 0;
> else
> return __strnlen_user(s, n);
> +}
> +
> +static __inline__ long strlen_user(const char *s)
> +{
> + if (!access_ok(VERIFY_READ, s, 0))
> + return 0;
> + else
> + return __strnlen_user(s, ~0UL >> 1);
> }
>
> struct exception_table_entry
>
> _______________________________________________
> linuxsh-dev mailing list
> lin...@li...
> https://lists.sourceforge.net/lists/listinfo/linuxsh-dev
>
>
|
