summaryrefslogtreecommitdiffstats
path: root/arch/x86/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/mm')
-rw-r--r--arch/x86/mm/Makefile2
-rw-r--r--arch/x86/mm/fault.c11
-rw-r--r--arch/x86/mm/gup.c2
-rw-r--r--arch/x86/mm/init_32.c35
-rw-r--r--arch/x86/mm/init_64.c77
-rw-r--r--arch/x86/mm/iomap_32.c59
-rw-r--r--arch/x86/mm/ioremap.c25
-rw-r--r--arch/x86/mm/numa_32.c35
-rw-r--r--arch/x86/mm/pageattr.c8
-rw-r--r--arch/x86/mm/pat.c240
10 files changed, 432 insertions, 62 deletions
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 59f89b434b4..fea4565ff57 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,7 +1,7 @@
obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
pat.o pgtable.o gup.o
-obj-$(CONFIG_X86_32) += pgtable_32.o
+obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_X86_PTDUMP) += dump_pagetables.o
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 31e8730fa24..20ef272c412 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -413,6 +413,7 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
unsigned long error_code)
{
unsigned long flags = oops_begin();
+ int sig = SIGKILL;
struct task_struct *tsk;
printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
@@ -423,8 +424,8 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
tsk->thread.trap_no = 14;
tsk->thread.error_code = error_code;
if (__die("Bad pagetable", regs, error_code))
- regs = NULL;
- oops_end(flags, regs, SIGKILL);
+ sig = 0;
+ oops_end(flags, regs, sig);
}
#endif
@@ -590,6 +591,7 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
int fault;
#ifdef CONFIG_X86_64
unsigned long flags;
+ int sig;
#endif
tsk = current;
@@ -849,11 +851,12 @@ no_context:
bust_spinlocks(0);
do_exit(SIGKILL);
#else
+ sig = SIGKILL;
if (__die("Oops", regs, error_code))
- regs = NULL;
+ sig = 0;
/* Executive summary in case the body of the oops scrolled away */
printk(KERN_EMERG "CR2: %016lx\n", address);
- oops_end(flags, regs, SIGKILL);
+ oops_end(flags, regs, sig);
#endif
/*
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 4ba373c5b8c..be54176e9eb 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -233,7 +233,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
len = (unsigned long) nr_pages << PAGE_SHIFT;
end = start + len;
if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
- start, len)))
+ (void __user *)start, len)))
goto slow_irqon;
/*
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8396868e82c..800e1d94c1b 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -67,7 +67,7 @@ static unsigned long __meminitdata table_top;
static int __initdata after_init_bootmem;
-static __init void *alloc_low_page(unsigned long *phys)
+static __init void *alloc_low_page(void)
{
unsigned long pfn = table_end++;
void *adr;
@@ -77,7 +77,6 @@ static __init void *alloc_low_page(unsigned long *phys)
adr = __va(pfn * PAGE_SIZE);
memset(adr, 0, PAGE_SIZE);
- *phys = pfn * PAGE_SIZE;
return adr;
}
@@ -92,16 +91,17 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
pmd_t *pmd_table;
#ifdef CONFIG_X86_PAE
- unsigned long phys;
if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
if (after_init_bootmem)
pmd_table = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
else
- pmd_table = (pmd_t *)alloc_low_page(&phys);
+ pmd_table = (pmd_t *)alloc_low_page();
paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
pud = pud_offset(pgd, 0);
BUG_ON(pmd_table != pmd_offset(pud, 0));
+
+ return pmd_table;
}
#endif
pud = pud_offset(pgd, 0);
@@ -126,10 +126,8 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
if (!page_table)
page_table =
(pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
- } else {
- unsigned long phys;
- page_table = (pte_t *)alloc_low_page(&phys);
- }
+ } else
+ page_table = (pte_t *)alloc_low_page();
paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT);
set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
@@ -334,7 +332,6 @@ int devmem_is_allowed(unsigned long pagenr)
return 0;
}
-#ifdef CONFIG_HIGHMEM
pte_t *kmap_pte;
pgprot_t kmap_prot;
@@ -357,6 +354,7 @@ static void __init kmap_init(void)
kmap_prot = PAGE_KERNEL;
}
+#ifdef CONFIG_HIGHMEM
static void __init permanent_kmaps_init(pgd_t *pgd_base)
{
unsigned long vaddr;
@@ -436,7 +434,6 @@ static void __init set_highmem_pages_init(void)
#endif /* !CONFIG_NUMA */
#else
-# define kmap_init() do { } while (0)
# define permanent_kmaps_init(pgd_base) do { } while (0)
# define set_highmem_pages_init() do { } while (0)
#endif /* CONFIG_HIGHMEM */
@@ -970,8 +967,6 @@ void __init mem_init(void)
int codesize, reservedpages, datasize, initsize;
int tmp;
- start_periodic_check_for_corruption();
-
#ifdef CONFIG_FLATMEM
BUG_ON(!mem_map);
#endif
@@ -1041,11 +1036,25 @@ void __init mem_init(void)
(unsigned long)&_text, (unsigned long)&_etext,
((unsigned long)&_etext - (unsigned long)&_text) >> 10);
+ /*
+ * Check boundaries twice: Some fundamental inconsistencies can
+ * be detected at build time already.
+ */
+#define __FIXADDR_TOP (-PAGE_SIZE)
+#ifdef CONFIG_HIGHMEM
+ BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE > FIXADDR_START);
+ BUILD_BUG_ON(VMALLOC_END > PKMAP_BASE);
+#endif
+#define high_memory (-128UL << 20)
+ BUILD_BUG_ON(VMALLOC_START >= VMALLOC_END);
+#undef high_memory
+#undef __FIXADDR_TOP
+
#ifdef CONFIG_HIGHMEM
BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE > FIXADDR_START);
BUG_ON(VMALLOC_END > PKMAP_BASE);
#endif
- BUG_ON(VMALLOC_START > VMALLOC_END);
+ BUG_ON(VMALLOC_START >= VMALLOC_END);
BUG_ON((unsigned long)high_memory > VMALLOC_START);
if (boot_cpu_data.wp_works_ok < 0)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b8e461d4941..9f7a0d24d42 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -350,8 +350,10 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
* pagetable pages as RO. So assume someone who pre-setup
* these mappings are more intelligent.
*/
- if (pte_val(*pte))
+ if (pte_val(*pte)) {
+ pages++;
continue;
+ }
if (0)
printk(" pte=%p addr=%lx pte=%016lx\n",
@@ -418,8 +420,10 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
* not differ with respect to page frame and
* attributes.
*/
- if (page_size_mask & (1 << PG_LEVEL_2M))
+ if (page_size_mask & (1 << PG_LEVEL_2M)) {
+ pages++;
continue;
+ }
new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
}
@@ -499,8 +503,10 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
* not differ with respect to page frame and
* attributes.
*/
- if (page_size_mask & (1 << PG_LEVEL_1G))
+ if (page_size_mask & (1 << PG_LEVEL_1G)) {
+ pages++;
continue;
+ }
prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
}
@@ -665,12 +671,13 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
unsigned long last_map_addr = 0;
unsigned long page_size_mask = 0;
unsigned long start_pfn, end_pfn;
+ unsigned long pos;
struct map_range mr[NR_RANGE_MR];
int nr_range, i;
int use_pse, use_gbpages;
- printk(KERN_INFO "init_memory_mapping\n");
+ printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);
/*
* Find space for the kernel direct mapping tables.
@@ -704,35 +711,50 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
/* head if not big page alignment ?*/
start_pfn = start >> PAGE_SHIFT;
- end_pfn = ((start + (PMD_SIZE - 1)) >> PMD_SHIFT)
+ pos = start_pfn << PAGE_SHIFT;
+ end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT)
<< (PMD_SHIFT - PAGE_SHIFT);
- nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+ if (start_pfn < end_pfn) {
+ nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+ pos = end_pfn << PAGE_SHIFT;
+ }
/* big page (2M) range*/
- start_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT)
+ start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
<< (PMD_SHIFT - PAGE_SHIFT);
- end_pfn = ((start + (PUD_SIZE - 1))>>PUD_SHIFT)
+ end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
<< (PUD_SHIFT - PAGE_SHIFT);
- if (end_pfn > ((end>>PUD_SHIFT)<<(PUD_SHIFT - PAGE_SHIFT)))
- end_pfn = ((end>>PUD_SHIFT)<<(PUD_SHIFT - PAGE_SHIFT));
- nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
- page_size_mask & (1<<PG_LEVEL_2M));
+ if (end_pfn > ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)))
+ end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT));
+ if (start_pfn < end_pfn) {
+ nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+ page_size_mask & (1<<PG_LEVEL_2M));
+ pos = end_pfn << PAGE_SHIFT;
+ }
/* big page (1G) range */
- start_pfn = end_pfn;
- end_pfn = (end>>PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT);
- nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+ start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
+ << (PUD_SHIFT - PAGE_SHIFT);
+ end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT);
+ if (start_pfn < end_pfn) {
+ nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
page_size_mask &
((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G)));
+ pos = end_pfn << PAGE_SHIFT;
+ }
/* tail is not big page (1G) alignment */
- start_pfn = end_pfn;
- end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
- nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
- page_size_mask & (1<<PG_LEVEL_2M));
+ start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
+ << (PMD_SHIFT - PAGE_SHIFT);
+ end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
+ if (start_pfn < end_pfn) {
+ nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+ page_size_mask & (1<<PG_LEVEL_2M));
+ pos = end_pfn << PAGE_SHIFT;
+ }
/* tail is not big page (2M) alignment */
- start_pfn = end_pfn;
+ start_pfn = pos>>PAGE_SHIFT;
end_pfn = end>>PAGE_SHIFT;
nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
@@ -831,12 +853,12 @@ int arch_add_memory(int nid, u64 start, u64 size)
unsigned long nr_pages = size >> PAGE_SHIFT;
int ret;
- last_mapped_pfn = init_memory_mapping(start, start + size-1);
+ last_mapped_pfn = init_memory_mapping(start, start + size);
if (last_mapped_pfn > max_pfn_mapped)
max_pfn_mapped = last_mapped_pfn;
ret = __add_pages(zone, start_pfn, nr_pages);
- WARN_ON(1);
+ WARN_ON_ONCE(ret);
return ret;
}
@@ -878,8 +900,7 @@ static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel,
void __init mem_init(void)
{
long codesize, reservedpages, datasize, initsize;
-
- start_periodic_check_for_corruption();
+ unsigned long absent_pages;
pci_iommu_alloc();
@@ -893,8 +914,9 @@ void __init mem_init(void)
#else
totalram_pages = free_all_bootmem();
#endif
- reservedpages = max_pfn - totalram_pages -
- absent_pages_in_range(0, max_pfn);
+
+ absent_pages = absent_pages_in_range(0, max_pfn);
+ reservedpages = max_pfn - totalram_pages - absent_pages;
after_bootmem = 1;
codesize = (unsigned long) &_etext - (unsigned long) &_text;
@@ -911,10 +933,11 @@ void __init mem_init(void)
VSYSCALL_END - VSYSCALL_START);
printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, "
- "%ldk reserved, %ldk data, %ldk init)\n",
+ "%ldk absent, %ldk reserved, %ldk data, %ldk init)\n",
(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
max_pfn << (PAGE_SHIFT-10),
codesize >> 10,
+ absent_pages << (PAGE_SHIFT-10),
reservedpages << (PAGE_SHIFT-10),
datasize >> 10,
initsize >> 10);
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
new file mode 100644
index 00000000000..d0151d8ce45
--- /dev/null
+++ b/arch/x86/mm/iomap_32.c
@@ -0,0 +1,59 @@
+/*
+ * Copyright © 2008 Ingo Molnar
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ */
+
+#include <asm/iomap.h>
+#include <linux/module.h>
+
+/* Map 'pfn' using fixed map 'type' and protections 'prot'
+ */
+void *
+iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
+{
+ enum fixed_addresses idx;
+ unsigned long vaddr;
+
+ pagefault_disable();
+
+ idx = type + KM_TYPE_NR*smp_processor_id();
+ vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+ set_pte(kmap_pte-idx, pfn_pte(pfn, prot));
+ arch_flush_lazy_mmu_mode();
+
+ return (void*) vaddr;
+}
+EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn);
+
+void
+iounmap_atomic(void *kvaddr, enum km_type type)
+{
+ unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
+ enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
+
+ /*
+ * Force other mappings to Oops if they'll try to access this pte
+ * without first remap it. Keeping stale mappings around is a bad idea
+ * also, in case the page changes cacheability attributes or becomes
+ * a protected page in a hypervisor.
+ */
+ if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
+ kpte_clear_flush(kmap_pte-idx, vaddr);
+
+ arch_flush_lazy_mmu_mode();
+ pagefault_enable();
+}
+EXPORT_SYMBOL_GPL(iounmap_atomic);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index ae71e11eb3e..bd85d42819e 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -223,7 +223,8 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
* Check if the request spans more than any BAR in the iomem resource
* tree.
*/
- WARN_ON(iomem_map_sanity_check(phys_addr, size));
+ WARN_ONCE(iomem_map_sanity_check(phys_addr, size),
+ KERN_INFO "Info: mapping multiple BARs. Your kernel is fine.");
/*
* Don't allow anybody to remap normal RAM that we're using..
@@ -387,7 +388,7 @@ static void __iomem *ioremap_default(resource_size_t phys_addr,
unsigned long size)
{
unsigned long flags;
- void *ret;
+ void __iomem *ret;
int err;
/*
@@ -399,11 +400,11 @@ static void __iomem *ioremap_default(resource_size_t phys_addr,
if (err < 0)
return NULL;
- ret = (void *) __ioremap_caller(phys_addr, size, flags,
- __builtin_return_address(0));
+ ret = __ioremap_caller(phys_addr, size, flags,
+ __builtin_return_address(0));
free_memtype(phys_addr, phys_addr + size);
- return (void __iomem *)ret;
+ return ret;
}
void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
@@ -622,7 +623,7 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx)
__early_set_fixmap(idx, 0, __pgprot(0));
}
-static void *prev_map[FIX_BTMAPS_SLOTS] __initdata;
+static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
static int __init check_early_ioremap_leak(void)
{
@@ -645,7 +646,7 @@ static int __init check_early_ioremap_leak(void)
}
late_initcall(check_early_ioremap_leak);
-static void __init *__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot)
+static void __init __iomem *__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot)
{
unsigned long offset, last_addr;
unsigned int nrpages;
@@ -713,23 +714,23 @@ static void __init *__early_ioremap(unsigned long phys_addr, unsigned long size,
if (early_ioremap_debug)
printk(KERN_CONT "%08lx + %08lx\n", offset, fix_to_virt(idx0));
- prev_map[slot] = (void *) (offset + fix_to_virt(idx0));
+ prev_map[slot] = (void __iomem *)(offset + fix_to_virt(idx0));
return prev_map[slot];
}
/* Remap an IO device */
-void __init *early_ioremap(unsigned long phys_addr, unsigned long size)
+void __init __iomem *early_ioremap(unsigned long phys_addr, unsigned long size)
{
return __early_ioremap(phys_addr, size, PAGE_KERNEL_IO);
}
/* Remap memory */
-void __init *early_memremap(unsigned long phys_addr, unsigned long size)
+void __init __iomem *early_memremap(unsigned long phys_addr, unsigned long size)
{
return __early_ioremap(phys_addr, size, PAGE_KERNEL);
}
-void __init early_iounmap(void *addr, unsigned long size)
+void __init early_iounmap(void __iomem *addr, unsigned long size)
{
unsigned long virt_addr;
unsigned long offset;
@@ -779,7 +780,7 @@ void __init early_iounmap(void *addr, unsigned long size)
--idx;
--nrpages;
}
- prev_map[slot] = 0;
+ prev_map[slot] = NULL;
}
void __this_fixmap_does_not_exist(void)
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 847c164725f..8518c678d83 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -222,6 +222,41 @@ static void __init remap_numa_kva(void)
}
}
+#ifdef CONFIG_HIBERNATION
+/**
+ * resume_map_numa_kva - add KVA mapping to the temporary page tables created
+ * during resume from hibernation
+ * @pgd_base - temporary resume page directory
+ */
+void resume_map_numa_kva(pgd_t *pgd_base)
+{
+ int node;
+
+ for_each_online_node(node) {
+ unsigned long start_va, start_pfn, size, pfn;
+
+ start_va = (unsigned long)node_remap_start_vaddr[node];
+ start_pfn = node_remap_start_pfn[node];
+ size = node_remap_size[node];
+
+ printk(KERN_DEBUG "%s: node %d\n", __FUNCTION__, node);
+
+ for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) {
+ unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
+ pgd_t *pgd = pgd_base + pgd_index(vaddr);
+ pud_t *pud = pud_offset(pgd, vaddr);
+ pmd_t *pmd = pmd_offset(pud, vaddr);
+
+ set_pmd(pmd, pfn_pmd(start_pfn + pfn,
+ PAGE_KERNEL_LARGE_EXEC));
+
+ printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n",
+ __FUNCTION__, vaddr, start_pfn + pfn);
+ }
+ }
+}
+#endif
+
static unsigned long calculate_numa_remap_pages(void)
{
int nid;
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index f1dc1b75d16..e89d24815f2 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -67,18 +67,18 @@ static void split_page_count(int level)
void arch_report_meminfo(struct seq_file *m)
{
- seq_printf(m, "DirectMap4k: %8lu kB\n",
+ seq_printf(m, "DirectMap4k: %8lu kB\n",
direct_pages_count[PG_LEVEL_4K] << 2);
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
- seq_printf(m, "DirectMap2M: %8lu kB\n",
+ seq_printf(m, "DirectMap2M: %8lu kB\n",
direct_pages_count[PG_LEVEL_2M] << 11);
#else
- seq_printf(m, "DirectMap4M: %8lu kB\n",
+ seq_printf(m, "DirectMap4M: %8lu kB\n",
direct_pages_count[PG_LEVEL_2M] << 12);
#endif
#ifdef CONFIG_X86_64
if (direct_gbpages)
- seq_printf(m, "DirectMap1G: %8lu kB\n",
+ seq_printf(m, "DirectMap1G: %8lu kB\n",
direct_pages_count[PG_LEVEL_1G] << 20);
#endif
}
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 738fd0f2495..541bcc944a5 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -481,12 +481,16 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
return 1;
}
#else
+/* This check is needed to avoid cache aliasing when PAT is enabled */
static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
u64 from = ((u64)pfn) << PAGE_SHIFT;
u64 to = from + size;
u64 cursor = from;
+ if (!pat_enabled)
+ return 1;
+
while (cursor < to) {
if (!devmem_is_allowed(pfn)) {
printk(KERN_INFO
@@ -592,6 +596,242 @@ void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
free_memtype(addr, addr + size);
}
+/*
+ * Internal interface to reserve a range of physical memory with prot.
+ * Reserved non RAM regions only and after successful reserve_memtype,
+ * this func also keeps identity mapping (if any) in sync with this new prot.
+ */
+static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t vma_prot)
+{
+ int is_ram = 0;
+ int id_sz, ret;
+ unsigned long flags;
+ unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK);
+
+ is_ram = pagerange_is_ram(paddr, paddr + size);
+
+ if (is_ram != 0) {
+ /*
+ * For mapping RAM pages, drivers need to call
+ * set_memory_[uc|wc|wb] directly, for reserve and free, before
+ * setting up the PTE.
+ */
+ WARN_ON_ONCE(1);
+ return 0;
+ }
+
+ ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
+ if (ret)
+ return ret;
+
+ if (flags != want_flags) {
+ free_memtype(paddr, paddr + size);
+ printk(KERN_ERR
+ "%s:%d map pfn expected mapping type %s for %Lx-%Lx, got %s\n",
+ current->comm, current->pid,
+ cattr_name(want_flags),
+ (unsigned long long)paddr,
+ (unsigned long long)(paddr + size),
+ cattr_name(flags));
+ return -EINVAL;
+ }
+
+ /* Need to keep identity mapping in sync */
+ if (paddr >= __pa(high_memory))
+ return 0;
+
+ id_sz = (__pa(high_memory) < paddr + size) ?
+ __pa(high_memory) - paddr :
+ size;
+
+ if (ioremap_change_attr((unsigned long)__va(paddr), id_sz, flags) < 0) {
+ free_memtype(paddr, paddr + size);
+ printk(KERN_ERR
+ "%s:%d reserve_pfn_range ioremap_change_attr failed %s "
+ "for %Lx-%Lx\n",
+ current->comm, current->pid,
+ cattr_name(flags),
+ (unsigned long long)paddr,
+ (unsigned long long)(paddr + size));
+ return -EINVAL;
+ }
+ return 0;
+}
+
+/*
+ * Internal interface to free a range of physical memory.
+ * Frees non RAM regions only.
+ */
+static void free_pfn_range(u64 paddr, unsigned long size)
+{
+ int is_ram;
+
+ is_ram = pagerange_is_ram(paddr, paddr + size);
+ if (is_ram == 0)
+ free_memtype(paddr, paddr + size);
+}
+
+/*
+ * track_pfn_vma_copy is called when vma that is covering the pfnmap gets
+ * copied through copy_page_range().
+ *
+ * If the vma has a linear pfn mapping for the entire range, we get the prot
+ * from pte and reserve the entire vma range with single reserve_pfn_range call.
+ * Otherwise, we reserve the entire vma range, my ging through the PTEs page
+ * by page to get physical address and protection.
+ */
+int track_pfn_vma_copy(struct vm_area_struct *vma)
+{
+ int retval = 0;
+ unsigned long i, j;
+ u64 paddr;
+ unsigned long prot;
+ unsigned long vma_start = vma->vm_start;
+ unsigned long vma_end = vma->vm_end;
+ unsigned long vma_size = vma_end - vma_start;
+
+ if (!pat_enabled)
+ return 0;
+
+ if (is_linear_pfn_mapping(vma)) {
+ /*
+ * reserve the whole chunk covered by vma. We need the
+ * starting address and protection from pte.
+ */
+ if (follow_phys(vma, vma_start, 0, &prot, &paddr)) {
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+ }
+ return reserve_pfn_range(paddr, vma_size, __pgprot(prot));
+ }
+
+ /* reserve entire vma page by page, using pfn and prot from pte */
+ for (i = 0; i < vma_size; i += PAGE_SIZE) {
+ if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
+ continue;
+
+ retval = reserve_pfn_range(paddr, PAGE_SIZE, __pgprot(prot));
+ if (retval)
+ goto cleanup_ret;
+ }
+ return 0;
+
+cleanup_ret:
+ /* Reserve error: Cleanup partial reservation and return error */
+ for (j = 0; j < i; j += PAGE_SIZE) {
+ if (follow_phys(vma, vma_start + j, 0, &prot, &paddr))
+ continue;
+
+ free_pfn_range(paddr, PAGE_SIZE);
+ }
+
+ return retval;
+}
+
+/*
+ * track_pfn_vma_new is called when a _new_ pfn mapping is being established
+ * for physical range indicated by pfn and size.
+ *
+ * prot is passed in as a parameter for the new mapping. If the vma has a
+ * linear pfn mapping for the entire range reserve the entire vma range with
+ * single reserve_pfn_range call.
+ * Otherwise, we look t the pfn and size and reserve only the specified range
+ * page by page.
+ *
+ * Note that this function can be called with caller trying to map only a
+ * subrange/page inside the vma.
+ */
+int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
+ unsigned long pfn, unsigned long size)
+{
+ int retval = 0;
+ unsigned long i, j;
+ u64 base_paddr;
+ u64 paddr;
+ unsigned long vma_start = vma->vm_start;
+ unsigned long vma_end = vma->vm_end;
+ unsigned long vma_size = vma_end - vma_start;
+
+ if (!pat_enabled)
+ return 0;
+
+ if (is_linear_pfn_mapping(vma)) {
+ /* reserve the whole chunk starting from vm_pgoff */
+ paddr = (u64)vma->vm_pgoff << PAGE_SHIFT;
+ return reserve_pfn_range(paddr, vma_size, prot);
+ }
+
+ /* reserve page by page using pfn and size */
+ base_paddr = (u64)pfn << PAGE_SHIFT;
+ for (i = 0; i < size; i += PAGE_SIZE) {
+ paddr = base_paddr + i;
+ retval = reserve_pfn_range(paddr, PAGE_SIZE, prot);
+ if (retval)
+ goto cleanup_ret;
+ }
+ return 0;
+
+cleanup_ret:
+ /* Reserve error: Cleanup partial reservation and return error */
+ for (j = 0; j < i; j += PAGE_SIZE) {
+ paddr = base_paddr + j;
+ free_pfn_range(paddr, PAGE_SIZE);
+ }
+
+ return retval;
+}
+
+/*
+ * untrack_pfn_vma is called while unmapping a pfnmap for a region.
+ * untrack can be called for a specific region indicated by pfn and size or
+ * can be for the entire vma (in which case size can be zero).
+ */
+void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
+ unsigned long size)
+{
+ unsigned long i;
+ u64 paddr;
+ unsigned long prot;
+ unsigned long vma_start = vma->vm_start;
+ unsigned long vma_end = vma->vm_end;
+ unsigned long vma_size = vma_end - vma_start;
+
+ if (!pat_enabled)
+ return;
+
+ if (is_linear_pfn_mapping(vma)) {
+ /* free the whole chunk starting from vm_pgoff */
+ paddr = (u64)vma->vm_pgoff << PAGE_SHIFT;
+ free_pfn_range(paddr, vma_size);
+ return;
+ }
+
+ if (size != 0 && size != vma_size) {
+ /* free page by page, using pfn and size */
+ paddr = (u64)pfn << PAGE_SHIFT;
+ for (i = 0; i < size; i += PAGE_SIZE) {
+ paddr = paddr + i;
+ free_pfn_range(paddr, PAGE_SIZE);
+ }
+ } else {
+ /* free entire vma, page by page, using the pfn from pte */
+ for (i = 0; i < vma_size; i += PAGE_SIZE) {
+ if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
+ continue;
+
+ free_pfn_range(paddr, PAGE_SIZE);
+ }
+ }
+}
+
+pgprot_t pgprot_writecombine(pgprot_t prot)
+{
+ if (pat_enabled)
+ return __pgprot(pgprot_val(prot) | _PAGE_CACHE_WC);
+ else
+ return pgprot_noncached(prot);
+}
+
#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
/* get Nth element of the linked list */
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-09-24 09:10:08 +0000