aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/mm')
-rw-r--r--arch/x86/mm/extable.c142
-rw-r--r--arch/x86/mm/init.c21
-rw-r--r--arch/x86/mm/init_64.c23
-rw-r--r--arch/x86/mm/numa_emulation.c8
-rw-r--r--arch/x86/mm/tlb.c16
5 files changed, 177 insertions, 33 deletions
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 1fb85dbe390a..903ec1e9c326 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -1,11 +1,23 @@
#include <linux/module.h>
#include <linux/spinlock.h>
+#include <linux/sort.h>
#include <asm/uaccess.h>
+static inline unsigned long
+ex_insn_addr(const struct exception_table_entry *x)
+{
+ return (unsigned long)&x->insn + x->insn;
+}
+static inline unsigned long
+ex_fixup_addr(const struct exception_table_entry *x)
+{
+ return (unsigned long)&x->fixup + x->fixup;
+}
int fixup_exception(struct pt_regs *regs)
{
const struct exception_table_entry *fixup;
+ unsigned long new_ip;
#ifdef CONFIG_PNPBIOS
if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) {
@@ -23,15 +35,135 @@ int fixup_exception(struct pt_regs *regs)
fixup = search_exception_tables(regs->ip);
if (fixup) {
- /* If fixup is less than 16, it means uaccess error */
- if (fixup->fixup < 16) {
+ new_ip = ex_fixup_addr(fixup);
+
+ if (fixup->fixup - fixup->insn >= 0x7ffffff0 - 4) {
+ /* Special hack for uaccess_err */
current_thread_info()->uaccess_err = 1;
- regs->ip += fixup->fixup;
- return 1;
+ new_ip -= 0x7ffffff0;
}
- regs->ip = fixup->fixup;
+ regs->ip = new_ip;
return 1;
}
return 0;
}
+
+/* Restricted version used during very early boot */
+int __init early_fixup_exception(unsigned long *ip)
+{
+ const struct exception_table_entry *fixup;
+ unsigned long new_ip;
+
+ fixup = search_exception_tables(*ip);
+ if (fixup) {
+ new_ip = ex_fixup_addr(fixup);
+
+ if (fixup->fixup - fixup->insn >= 0x7ffffff0 - 4) {
+ /* uaccess handling not supported during early boot */
+ return 0;
+ }
+
+ *ip = new_ip;
+ return 1;
+ }
+
+ return 0;
+}
+
+/*
+ * Search one exception table for an entry corresponding to the
+ * given instruction address, and return the address of the entry,
+ * or NULL if none is found.
+ * We use a binary search, and thus we assume that the table is
+ * already sorted.
+ */
+const struct exception_table_entry *
+search_extable(const struct exception_table_entry *first,
+ const struct exception_table_entry *last,
+ unsigned long value)
+{
+ while (first <= last) {
+ const struct exception_table_entry *mid;
+ unsigned long addr;
+
+ mid = ((last - first) >> 1) + first;
+ addr = ex_insn_addr(mid);
+ if (addr < value)
+ first = mid + 1;
+ else if (addr > value)
+ last = mid - 1;
+ else
+ return mid;
+ }
+ return NULL;
+}
+
+/*
+ * The exception table needs to be sorted so that the binary
+ * search that we use to find entries in it works properly.
+ * This is used both for the kernel exception table and for
+ * the exception tables of modules that get loaded.
+ *
+ */
+static int cmp_ex(const void *a, const void *b)
+{
+ const struct exception_table_entry *x = a, *y = b;
+
+ /*
+ * This value will always end up fittin in an int, because on
+ * both i386 and x86-64 the kernel symbol-reachable address
+ * space is < 2 GiB.
+ *
+ * This compare is only valid after normalization.
+ */
+ return x->insn - y->insn;
+}
+
+void sort_extable(struct exception_table_entry *start,
+ struct exception_table_entry *finish)
+{
+ struct exception_table_entry *p;
+ int i;
+
+ /* Convert all entries to being relative to the start of the section */
+ i = 0;
+ for (p = start; p < finish; p++) {
+ p->insn += i;
+ i += 4;
+ p->fixup += i;
+ i += 4;
+ }
+
+ sort(start, finish - start, sizeof(struct exception_table_entry),
+ cmp_ex, NULL);
+
+ /* Denormalize all entries */
+ i = 0;
+ for (p = start; p < finish; p++) {
+ p->insn -= i;
+ i += 4;
+ p->fixup -= i;
+ i += 4;
+ }
+}
+
+#ifdef CONFIG_MODULES
+/*
+ * If the exception table is sorted, any referring to the module init
+ * will be at the beginning or the end.
+ */
+void trim_init_extable(struct module *m)
+{
+ /*trim the beginning*/
+ while (m->num_exentries &&
+ within_module_init(ex_insn_addr(&m->extable[0]), m)) {
+ m->extable++;
+ m->num_exentries--;
+ }
+ /*trim the end*/
+ while (m->num_exentries &&
+ within_module_init(ex_insn_addr(&m->extable[m->num_exentries-1]), m))
+ m->num_exentries--;
+}
+#endif /* CONFIG_MODULES */
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 4f0cec7e4ffb..319b6f2fb8b9 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -29,8 +29,14 @@ int direct_gbpages
#endif
;
-static void __init find_early_table_space(unsigned long end, int use_pse,
- int use_gbpages)
+struct map_range {
+ unsigned long start;
+ unsigned long end;
+ unsigned page_size_mask;
+};
+
+static void __init find_early_table_space(struct map_range *mr, unsigned long end,
+ int use_pse, int use_gbpages)
{
unsigned long puds, pmds, ptes, tables, start = 0, good_end = end;
phys_addr_t base;
@@ -55,6 +61,9 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
#ifdef CONFIG_X86_32
extra += PMD_SIZE;
#endif
+ /* The first 2/4M doesn't use large pages. */
+ extra += mr->end - mr->start;
+
ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
} else
ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -84,12 +93,6 @@ void __init native_pagetable_reserve(u64 start, u64 end)
memblock_reserve(start, end - start);
}
-struct map_range {
- unsigned long start;
- unsigned long end;
- unsigned page_size_mask;
-};
-
#ifdef CONFIG_X86_32
#define NR_RANGE_MR 3
#else /* CONFIG_X86_64 */
@@ -261,7 +264,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
* nodes are discovered.
*/
if (!after_bootmem)
- find_early_table_space(end, use_pse, use_gbpages);
+ find_early_table_space(&mr[0], end, use_pse, use_gbpages);
for (i = 0; i < nr_range; i++)
ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index fc18be0f6f29..2b6b4a3c8beb 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -407,12 +407,12 @@ static unsigned long __meminit
phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
unsigned long page_size_mask, pgprot_t prot)
{
- unsigned long pages = 0;
+ unsigned long pages = 0, next;
unsigned long last_map_addr = end;
int i = pmd_index(address);
- for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
+ for (; i < PTRS_PER_PMD; i++, address = next) {
unsigned long pte_phys;
pmd_t *pmd = pmd_page + pmd_index(address);
pte_t *pte;
@@ -426,6 +426,8 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
break;
}
+ next = (address & PMD_MASK) + PMD_SIZE;
+
if (pmd_val(*pmd)) {
if (!pmd_large(*pmd)) {
spin_lock(&init_mm.page_table_lock);
@@ -449,7 +451,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
* attributes.
*/
if (page_size_mask & (1 << PG_LEVEL_2M)) {
- pages++;
+ last_map_addr = next;
continue;
}
new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
@@ -462,7 +464,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
pfn_pte(address >> PAGE_SHIFT,
__pgprot(pgprot_val(prot) | _PAGE_PSE)));
spin_unlock(&init_mm.page_table_lock);
- last_map_addr = (address & PMD_MASK) + PMD_SIZE;
+ last_map_addr = next;
continue;
}
@@ -482,11 +484,11 @@ static unsigned long __meminit
phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
unsigned long page_size_mask)
{
- unsigned long pages = 0;
+ unsigned long pages = 0, next;
unsigned long last_map_addr = end;
int i = pud_index(addr);
- for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE) {
+ for (; i < PTRS_PER_PUD; i++, addr = next) {
unsigned long pmd_phys;
pud_t *pud = pud_page + pud_index(addr);
pmd_t *pmd;
@@ -495,8 +497,9 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
if (addr >= end)
break;
- if (!after_bootmem &&
- !e820_any_mapped(addr, addr+PUD_SIZE, 0)) {
+ next = (addr & PUD_MASK) + PUD_SIZE;
+
+ if (!after_bootmem && !e820_any_mapped(addr, next, 0)) {
set_pud(pud, __pud(0));
continue;
}
@@ -523,7 +526,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
* attributes.
*/
if (page_size_mask & (1 << PG_LEVEL_1G)) {
- pages++;
+ last_map_addr = next;
continue;
}
prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
@@ -535,7 +538,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
set_pte((pte_t *)pud,
pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
spin_unlock(&init_mm.page_table_lock);
- last_map_addr = (addr & PUD_MASK) + PUD_SIZE;
+ last_map_addr = next;
continue;
}
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index 53489ff6bf82..871dd8868170 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -339,9 +339,11 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
} else {
unsigned long n;
- n = simple_strtoul(emu_cmdline, NULL, 0);
+ n = simple_strtoul(emu_cmdline, &emu_cmdline, 0);
ret = split_nodes_interleave(&ei, &pi, 0, max_addr, n);
}
+ if (*emu_cmdline == ':')
+ emu_cmdline++;
if (ret < 0)
goto no_emu;
@@ -418,7 +420,9 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
int physj = emu_nid_to_phys[j];
int dist;
- if (physi >= numa_dist_cnt || physj >= numa_dist_cnt)
+ if (get_option(&emu_cmdline, &dist) == 2)
+ ;
+ else if (physi >= numa_dist_cnt || physj >= numa_dist_cnt)
dist = physi == physj ?
LOCAL_DISTANCE : REMOTE_DISTANCE;
else
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index d6c0418c3e47..5e57e113b72c 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -61,11 +61,13 @@ static DEFINE_PER_CPU_READ_MOSTLY(int, tlb_vector_offset);
*/
void leave_mm(int cpu)
{
- if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
+ struct mm_struct *active_mm = this_cpu_read(cpu_tlbstate.active_mm);
+ if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
BUG();
- cpumask_clear_cpu(cpu,
- mm_cpumask(percpu_read(cpu_tlbstate.active_mm)));
- load_cr3(swapper_pg_dir);
+ if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) {
+ cpumask_clear_cpu(cpu, mm_cpumask(active_mm));
+ load_cr3(swapper_pg_dir);
+ }
}
EXPORT_SYMBOL_GPL(leave_mm);
@@ -152,8 +154,8 @@ void smp_invalidate_interrupt(struct pt_regs *regs)
* BUG();
*/
- if (f->flush_mm == percpu_read(cpu_tlbstate.active_mm)) {
- if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
+ if (f->flush_mm == this_cpu_read(cpu_tlbstate.active_mm)) {
+ if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
if (f->flush_va == TLB_FLUSH_ALL)
local_flush_tlb();
else
@@ -322,7 +324,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
static void do_flush_tlb_all(void *info)
{
__flush_tlb_all();
- if (percpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
+ if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
leave_mm(smp_processor_id());
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.