linux_dsm_epyc7002/arch/arm/mm/highmem.c

224 lines
5.7 KiB
C
Raw Normal View History

/*
* arch/arm/mm/highmem.c -- ARM highmem support
*
* Author: Nicolas Pitre
* Created: september 8, 2008
* Copyright: Marvell Semiconductors Inc.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/module.h>
#include <linux/highmem.h>
#include <linux/interrupt.h>
#include <asm/fixmap.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include "mm.h"
void *kmap(struct page *page)
{
might_sleep();
if (!PageHighMem(page))
return page_address(page);
return kmap_high(page);
}
EXPORT_SYMBOL(kmap);
void kunmap(struct page *page)
{
BUG_ON(in_interrupt());
if (!PageHighMem(page))
return;
kunmap_high(page);
}
EXPORT_SYMBOL(kunmap);
void *kmap_atomic(struct page *page, enum km_type type)
{
unsigned int idx;
unsigned long vaddr;
void *kmap;
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
debug_kmap_atomic(type);
#ifdef CONFIG_DEBUG_HIGHMEM
/*
* There is no cache coherency issue when non VIVT, so force the
* dedicated kmap usage for better debugging purposes in that case.
*/
if (!cache_is_vivt())
kmap = NULL;
else
#endif
kmap = kmap_high_get(page);
if (kmap)
return kmap;
idx = type + KM_TYPE_NR * smp_processor_id();
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
#ifdef CONFIG_DEBUG_HIGHMEM
/*
* With debugging enabled, kunmap_atomic forces that entry to 0.
* Make sure it was indeed properly unmapped.
*/
BUG_ON(!pte_none(*(TOP_PTE(vaddr))));
#endif
set_pte_ext(TOP_PTE(vaddr), mk_pte(page, kmap_prot), 0);
/*
* When debugging is off, kunmap_atomic leaves the previous mapping
* in place, so this TLB flush ensures the TLB is updated with the
* new mapping.
*/
local_flush_tlb_kernel_page(vaddr);
return (void *)vaddr;
}
EXPORT_SYMBOL(kmap_atomic);
kmap_atomic: make kunmap_atomic() harder to misuse kunmap_atomic() is currently at level -4 on Rusty's "Hard To Misuse" list[1] ("Follow common convention and you'll get it wrong"), except in some architectures when CONFIG_DEBUG_HIGHMEM is set[2][3]. kunmap() takes a pointer to a struct page; kunmap_atomic(), however, takes takes a pointer to within the page itself. This seems to once in a while trip people up (the convention they are following is the one from kunmap()). Make it much harder to misuse, by moving it to level 9 on Rusty's list[4] ("The compiler/linker won't let you get it wrong"). This is done by refusing to build if the type of its first argument is a pointer to a struct page. The real kunmap_atomic() is renamed to kunmap_atomic_notypecheck() (which is what you would call in case for some strange reason calling it with a pointer to a struct page is not incorrect in your code). The previous version of this patch was compile tested on x86-64. [1] http://ozlabs.org/~rusty/index.cgi/tech/2008-04-01.html [2] In these cases, it is at level 5, "Do it right or it will always break at runtime." [3] At least mips and powerpc look very similar, and sparc also seems to share a common ancestor with both; there seems to be quite some degree of copy-and-paste coding here. The include/asm/highmem.h file for these three archs mention x86 CPUs at its top. [4] http://ozlabs.org/~rusty/index.cgi/tech/2008-03-30.html [5] As an aside, could someone tell me why mn10300 uses unsigned long as the first parameter of kunmap_atomic() instead of void *? Signed-off-by: Cesar Eduardo Barros <cesarb@cesarb.net> Cc: Russell King <linux@arm.linux.org.uk> (arch/arm) Cc: Ralf Baechle <ralf@linux-mips.org> (arch/mips) Cc: David Howells <dhowells@redhat.com> (arch/frv, arch/mn10300) Cc: Koichi Yasutake <yasutake.koichi@jp.panasonic.com> (arch/mn10300) Cc: Kyle McMartin <kyle@mcmartin.ca> (arch/parisc) Cc: Helge Deller <deller@gmx.de> (arch/parisc) Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> (arch/parisc) Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> (arch/powerpc) Cc: Paul Mackerras <paulus@samba.org> (arch/powerpc) Cc: "David S. Miller" <davem@davemloft.net> (arch/sparc) Cc: Thomas Gleixner <tglx@linutronix.de> (arch/x86) Cc: Ingo Molnar <mingo@redhat.com> (arch/x86) Cc: "H. Peter Anvin" <hpa@zytor.com> (arch/x86) Cc: Arnd Bergmann <arnd@arndb.de> (include/asm-generic) Cc: Rusty Russell <rusty@rustcorp.com.au> ("Hard To Misuse" list) Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-08-10 07:18:32 +07:00
void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type)
{
unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
unsigned int idx = type + KM_TYPE_NR * smp_processor_id();
if (kvaddr >= (void *)FIXADDR_START) {
ARM: 6007/1: fix highmem with VIPT cache and DMA The VIVT cache of a highmem page is always flushed before the page is unmapped. This cache flush is explicit through flush_cache_kmaps() in flush_all_zero_pkmaps(), or through __cpuc_flush_dcache_area() in kunmap_atomic(). There is also an implicit flush of those highmem pages that were part of a process that just terminated making those pages free as the whole VIVT cache has to be flushed on every task switch. Hence unmapped highmem pages need no cache maintenance in that case. However unmapped pages may still be cached with a VIPT cache because the cache is tagged with physical addresses. There is no need for a whole cache flush during task switching for that reason, and despite the explicit cache flushes in flush_all_zero_pkmaps() and kunmap_atomic(), some highmem pages that were mapped in user space end up still cached even when they become unmapped. So, we do have to perform cache maintenance on those unmapped highmem pages in the context of DMA when using a VIPT cache. Unfortunately, it is not possible to perform that cache maintenance using physical addresses as all the L1 cache maintenance coprocessor functions accept virtual addresses only. Therefore we have no choice but to set up a temporary virtual mapping for that purpose. And of course the explicit cache flushing when unmapping a highmem page on a system with a VIPT cache now can go, which should increase performance. While at it, because the code in __flush_dcache_page() has to be modified anyway, let's also make sure the mapped highmem pages are pinned with kmap_high_get() for the duration of the cache maintenance operation. Because kunmap() does unmap highmem pages lazily, it was reported by Gary King <GKing@nvidia.com> that those pages ended up being unmapped during cache maintenance on SMP causing segmentation faults. Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2010-03-30 03:46:02 +07:00
if (cache_is_vivt())
__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
#ifdef CONFIG_DEBUG_HIGHMEM
BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
set_pte_ext(TOP_PTE(vaddr), __pte(0), 0);
local_flush_tlb_kernel_page(vaddr);
#else
(void) idx; /* to kill a warning */
#endif
} else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) {
/* this address was obtained through kmap_high_get() */
kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
}
pagefault_enable();
}
kmap_atomic: make kunmap_atomic() harder to misuse kunmap_atomic() is currently at level -4 on Rusty's "Hard To Misuse" list[1] ("Follow common convention and you'll get it wrong"), except in some architectures when CONFIG_DEBUG_HIGHMEM is set[2][3]. kunmap() takes a pointer to a struct page; kunmap_atomic(), however, takes takes a pointer to within the page itself. This seems to once in a while trip people up (the convention they are following is the one from kunmap()). Make it much harder to misuse, by moving it to level 9 on Rusty's list[4] ("The compiler/linker won't let you get it wrong"). This is done by refusing to build if the type of its first argument is a pointer to a struct page. The real kunmap_atomic() is renamed to kunmap_atomic_notypecheck() (which is what you would call in case for some strange reason calling it with a pointer to a struct page is not incorrect in your code). The previous version of this patch was compile tested on x86-64. [1] http://ozlabs.org/~rusty/index.cgi/tech/2008-04-01.html [2] In these cases, it is at level 5, "Do it right or it will always break at runtime." [3] At least mips and powerpc look very similar, and sparc also seems to share a common ancestor with both; there seems to be quite some degree of copy-and-paste coding here. The include/asm/highmem.h file for these three archs mention x86 CPUs at its top. [4] http://ozlabs.org/~rusty/index.cgi/tech/2008-03-30.html [5] As an aside, could someone tell me why mn10300 uses unsigned long as the first parameter of kunmap_atomic() instead of void *? Signed-off-by: Cesar Eduardo Barros <cesarb@cesarb.net> Cc: Russell King <linux@arm.linux.org.uk> (arch/arm) Cc: Ralf Baechle <ralf@linux-mips.org> (arch/mips) Cc: David Howells <dhowells@redhat.com> (arch/frv, arch/mn10300) Cc: Koichi Yasutake <yasutake.koichi@jp.panasonic.com> (arch/mn10300) Cc: Kyle McMartin <kyle@mcmartin.ca> (arch/parisc) Cc: Helge Deller <deller@gmx.de> (arch/parisc) Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> (arch/parisc) Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> (arch/powerpc) Cc: Paul Mackerras <paulus@samba.org> (arch/powerpc) Cc: "David S. Miller" <davem@davemloft.net> (arch/sparc) Cc: Thomas Gleixner <tglx@linutronix.de> (arch/x86) Cc: Ingo Molnar <mingo@redhat.com> (arch/x86) Cc: "H. Peter Anvin" <hpa@zytor.com> (arch/x86) Cc: Arnd Bergmann <arnd@arndb.de> (include/asm-generic) Cc: Rusty Russell <rusty@rustcorp.com.au> ("Hard To Misuse" list) Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-08-10 07:18:32 +07:00
EXPORT_SYMBOL(kunmap_atomic_notypecheck);
void *kmap_atomic_pfn(unsigned long pfn, enum km_type type)
{
unsigned int idx;
unsigned long vaddr;
pagefault_disable();
idx = type + KM_TYPE_NR * smp_processor_id();
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
#ifdef CONFIG_DEBUG_HIGHMEM
BUG_ON(!pte_none(*(TOP_PTE(vaddr))));
#endif
set_pte_ext(TOP_PTE(vaddr), pfn_pte(pfn, kmap_prot), 0);
local_flush_tlb_kernel_page(vaddr);
return (void *)vaddr;
}
struct page *kmap_atomic_to_page(const void *ptr)
{
unsigned long vaddr = (unsigned long)ptr;
pte_t *pte;
if (vaddr < FIXADDR_START)
return virt_to_page(ptr);
pte = TOP_PTE(vaddr);
return pte_page(*pte);
}
ARM: 6007/1: fix highmem with VIPT cache and DMA The VIVT cache of a highmem page is always flushed before the page is unmapped. This cache flush is explicit through flush_cache_kmaps() in flush_all_zero_pkmaps(), or through __cpuc_flush_dcache_area() in kunmap_atomic(). There is also an implicit flush of those highmem pages that were part of a process that just terminated making those pages free as the whole VIVT cache has to be flushed on every task switch. Hence unmapped highmem pages need no cache maintenance in that case. However unmapped pages may still be cached with a VIPT cache because the cache is tagged with physical addresses. There is no need for a whole cache flush during task switching for that reason, and despite the explicit cache flushes in flush_all_zero_pkmaps() and kunmap_atomic(), some highmem pages that were mapped in user space end up still cached even when they become unmapped. So, we do have to perform cache maintenance on those unmapped highmem pages in the context of DMA when using a VIPT cache. Unfortunately, it is not possible to perform that cache maintenance using physical addresses as all the L1 cache maintenance coprocessor functions accept virtual addresses only. Therefore we have no choice but to set up a temporary virtual mapping for that purpose. And of course the explicit cache flushing when unmapping a highmem page on a system with a VIPT cache now can go, which should increase performance. While at it, because the code in __flush_dcache_page() has to be modified anyway, let's also make sure the mapped highmem pages are pinned with kmap_high_get() for the duration of the cache maintenance operation. Because kunmap() does unmap highmem pages lazily, it was reported by Gary King <GKing@nvidia.com> that those pages ended up being unmapped during cache maintenance on SMP causing segmentation faults. Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2010-03-30 03:46:02 +07:00
#ifdef CONFIG_CPU_CACHE_VIPT
#include <linux/percpu.h>
/*
* The VIVT cache of a highmem page is always flushed before the page
* is unmapped. Hence unmapped highmem pages need no cache maintenance
* in that case.
*
* However unmapped pages may still be cached with a VIPT cache, and
* it is not possible to perform cache maintenance on them using physical
* addresses unfortunately. So we have no choice but to set up a temporary
* virtual mapping for that purpose.
*
* Yet this VIPT cache maintenance may be triggered from DMA support
* functions which are possibly called from interrupt context. As we don't
* want to keep interrupt disabled all the time when such maintenance is
* taking place, we therefore allow for some reentrancy by preserving and
* restoring the previous fixmap entry before the interrupted context is
* resumed. If the reentrancy depth is 0 then there is no need to restore
* the previous fixmap, and leaving the current one in place allow it to
* be reused the next time without a TLB flush (common with DMA).
*/
static DEFINE_PER_CPU(int, kmap_high_l1_vipt_depth);
void *kmap_high_l1_vipt(struct page *page, pte_t *saved_pte)
{
unsigned int idx, cpu;
int *depth;
ARM: 6007/1: fix highmem with VIPT cache and DMA The VIVT cache of a highmem page is always flushed before the page is unmapped. This cache flush is explicit through flush_cache_kmaps() in flush_all_zero_pkmaps(), or through __cpuc_flush_dcache_area() in kunmap_atomic(). There is also an implicit flush of those highmem pages that were part of a process that just terminated making those pages free as the whole VIVT cache has to be flushed on every task switch. Hence unmapped highmem pages need no cache maintenance in that case. However unmapped pages may still be cached with a VIPT cache because the cache is tagged with physical addresses. There is no need for a whole cache flush during task switching for that reason, and despite the explicit cache flushes in flush_all_zero_pkmaps() and kunmap_atomic(), some highmem pages that were mapped in user space end up still cached even when they become unmapped. So, we do have to perform cache maintenance on those unmapped highmem pages in the context of DMA when using a VIPT cache. Unfortunately, it is not possible to perform that cache maintenance using physical addresses as all the L1 cache maintenance coprocessor functions accept virtual addresses only. Therefore we have no choice but to set up a temporary virtual mapping for that purpose. And of course the explicit cache flushing when unmapping a highmem page on a system with a VIPT cache now can go, which should increase performance. While at it, because the code in __flush_dcache_page() has to be modified anyway, let's also make sure the mapped highmem pages are pinned with kmap_high_get() for the duration of the cache maintenance operation. Because kunmap() does unmap highmem pages lazily, it was reported by Gary King <GKing@nvidia.com> that those pages ended up being unmapped during cache maintenance on SMP causing segmentation faults. Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2010-03-30 03:46:02 +07:00
unsigned long vaddr, flags;
pte_t pte, *ptep;
if (!in_interrupt())
preempt_disable();
cpu = smp_processor_id();
depth = &per_cpu(kmap_high_l1_vipt_depth, cpu);
ARM: 6007/1: fix highmem with VIPT cache and DMA The VIVT cache of a highmem page is always flushed before the page is unmapped. This cache flush is explicit through flush_cache_kmaps() in flush_all_zero_pkmaps(), or through __cpuc_flush_dcache_area() in kunmap_atomic(). There is also an implicit flush of those highmem pages that were part of a process that just terminated making those pages free as the whole VIVT cache has to be flushed on every task switch. Hence unmapped highmem pages need no cache maintenance in that case. However unmapped pages may still be cached with a VIPT cache because the cache is tagged with physical addresses. There is no need for a whole cache flush during task switching for that reason, and despite the explicit cache flushes in flush_all_zero_pkmaps() and kunmap_atomic(), some highmem pages that were mapped in user space end up still cached even when they become unmapped. So, we do have to perform cache maintenance on those unmapped highmem pages in the context of DMA when using a VIPT cache. Unfortunately, it is not possible to perform that cache maintenance using physical addresses as all the L1 cache maintenance coprocessor functions accept virtual addresses only. Therefore we have no choice but to set up a temporary virtual mapping for that purpose. And of course the explicit cache flushing when unmapping a highmem page on a system with a VIPT cache now can go, which should increase performance. While at it, because the code in __flush_dcache_page() has to be modified anyway, let's also make sure the mapped highmem pages are pinned with kmap_high_get() for the duration of the cache maintenance operation. Because kunmap() does unmap highmem pages lazily, it was reported by Gary King <GKing@nvidia.com> that those pages ended up being unmapped during cache maintenance on SMP causing segmentation faults. Signed-off-by: Nicolas Pitre <nico@marvell.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2010-03-30 03:46:02 +07:00
idx = KM_L1_CACHE + KM_TYPE_NR * cpu;
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
ptep = TOP_PTE(vaddr);
pte = mk_pte(page, kmap_prot);
raw_local_irq_save(flags);
(*depth)++;
if (pte_val(*ptep) == pte_val(pte)) {
*saved_pte = pte;
} else {
*saved_pte = *ptep;
set_pte_ext(ptep, pte, 0);
local_flush_tlb_kernel_page(vaddr);
}
raw_local_irq_restore(flags);
return (void *)vaddr;
}
void kunmap_high_l1_vipt(struct page *page, pte_t saved_pte)
{
unsigned int idx, cpu = smp_processor_id();
int *depth = &per_cpu(kmap_high_l1_vipt_depth, cpu);
unsigned long vaddr, flags;
pte_t pte, *ptep;
idx = KM_L1_CACHE + KM_TYPE_NR * cpu;
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
ptep = TOP_PTE(vaddr);
pte = mk_pte(page, kmap_prot);
BUG_ON(pte_val(*ptep) != pte_val(pte));
BUG_ON(*depth <= 0);
raw_local_irq_save(flags);
(*depth)--;
if (*depth != 0 && pte_val(pte) != pte_val(saved_pte)) {
set_pte_ext(ptep, saved_pte, 0);
local_flush_tlb_kernel_page(vaddr);
}
raw_local_irq_restore(flags);
if (!in_interrupt())
preempt_enable();
}
#endif /* CONFIG_CPU_CACHE_VIPT */