summaryrefslogtreecommitdiff
path: root/arch/x86/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/mm')
-rw-r--r--arch/x86/mm/amdtopology.c22
-rw-r--r--arch/x86/mm/fault.c32
-rw-r--r--arch/x86/mm/init.c4
-rw-r--r--arch/x86/mm/kaslr.c26
-rw-r--r--arch/x86/mm/numa.c27
-rw-r--r--arch/x86/mm/pageattr.c21
-rw-r--r--arch/x86/mm/tlb.c15
7 files changed, 103 insertions, 44 deletions
diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c
index ba47524f56e8..d1c7de095808 100644
--- a/arch/x86/mm/amdtopology.c
+++ b/arch/x86/mm/amdtopology.c
@@ -52,21 +52,6 @@ static __init int find_northbridge(void)
return -ENOENT;
}
-static __init void early_get_boot_cpu_id(void)
-{
- /*
- * need to get the APIC ID of the BSP so can use that to
- * create apicid_to_node in amd_scan_nodes()
- */
-#ifdef CONFIG_X86_MPPARSE
- /*
- * get boot-time SMP configuration:
- */
- if (smp_found_config)
- early_get_smp_config();
-#endif
-}
-
int __init amd_numa_init(void)
{
u64 start = PFN_PHYS(0);
@@ -180,8 +165,11 @@ int __init amd_numa_init(void)
cores = 1 << bits;
apicid_base = 0;
- /* get the APIC ID of the BSP early for systems with apicid lifting */
- early_get_boot_cpu_id();
+ /*
+ * get boot-time SMP configuration:
+ */
+ early_get_smp_config();
+
if (boot_cpu_physical_apicid > 0) {
pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid);
apicid_base = boot_cpu_physical_apicid;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 79ae05477d94..1e525122cbe4 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -753,6 +753,38 @@ no_context(struct pt_regs *regs, unsigned long error_code,
return;
}
+#ifdef CONFIG_VMAP_STACK
+ /*
+ * Stack overflow? During boot, we can fault near the initial
+ * stack in the direct map, but that's not an overflow -- check
+ * that we're in vmalloc space to avoid this.
+ */
+ if (is_vmalloc_addr((void *)address) &&
+ (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) ||
+ address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) {
+ register void *__sp asm("rsp");
+ unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *);
+ /*
+ * We're likely to be running with very little stack space
+ * left. It's plausible that we'd hit this condition but
+ * double-fault even before we get this far, in which case
+ * we're fine: the double-fault handler will deal with it.
+ *
+ * We don't want to make it all the way into the oops code
+ * and then double-fault, though, because we're likely to
+ * break the console driver and lose most of the stack dump.
+ */
+ asm volatile ("movq %[stack], %%rsp\n\t"
+ "call handle_stack_overflow\n\t"
+ "1: jmp 1b"
+ : "+r" (__sp)
+ : "D" ("kernel stack overflow (page fault)"),
+ "S" (regs), "d" (address),
+ [stack] "rm" (stack));
+ unreachable();
+ }
+#endif
+
/*
* 32-bit:
*
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index d28a2d741f9e..22af912d66d2 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -699,8 +699,10 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
}
}
-void free_initmem(void)
+void __ref free_initmem(void)
{
+ e820_reallocate_tables();
+
free_init_pages("unused kernel",
(unsigned long)(&__init_begin),
(unsigned long)(&__init_end));
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index bda8d5eef04d..ddd2661c4502 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -40,17 +40,26 @@
* You need to add an if/def entry if you introduce a new memory region
* compatible with KASLR. Your entry must be in logical order with memory
* layout. For example, ESPFIX is before EFI because its virtual address is
- * before. You also need to add a BUILD_BUG_ON in kernel_randomize_memory to
+ * before. You also need to add a BUILD_BUG_ON() in kernel_randomize_memory() to
* ensure that this order is correct and won't be changed.
*/
static const unsigned long vaddr_start = __PAGE_OFFSET_BASE;
-static const unsigned long vaddr_end = VMEMMAP_START;
+
+#if defined(CONFIG_X86_ESPFIX64)
+static const unsigned long vaddr_end = ESPFIX_BASE_ADDR;
+#elif defined(CONFIG_EFI)
+static const unsigned long vaddr_end = EFI_VA_START;
+#else
+static const unsigned long vaddr_end = __START_KERNEL_map;
+#endif
/* Default values */
unsigned long page_offset_base = __PAGE_OFFSET_BASE;
EXPORT_SYMBOL(page_offset_base);
unsigned long vmalloc_base = __VMALLOC_BASE;
EXPORT_SYMBOL(vmalloc_base);
+unsigned long vmemmap_base = __VMEMMAP_BASE;
+EXPORT_SYMBOL(vmemmap_base);
/*
* Memory regions randomized by KASLR (except modules that use a separate logic
@@ -63,6 +72,7 @@ static __initdata struct kaslr_memory_region {
} kaslr_regions[] = {
{ &page_offset_base, 64/* Maximum */ },
{ &vmalloc_base, VMALLOC_SIZE_TB },
+ { &vmemmap_base, 1 },
};
/* Get size in bytes used by the memory region */
@@ -89,6 +99,18 @@ void __init kernel_randomize_memory(void)
struct rnd_state rand_state;
unsigned long remain_entropy;
+ /*
+ * All these BUILD_BUG_ON checks ensures the memory layout is
+ * consistent with the vaddr_start/vaddr_end variables.
+ */
+ BUILD_BUG_ON(vaddr_start >= vaddr_end);
+ BUILD_BUG_ON(config_enabled(CONFIG_X86_ESPFIX64) &&
+ vaddr_end >= EFI_VA_START);
+ BUILD_BUG_ON((config_enabled(CONFIG_X86_ESPFIX64) ||
+ config_enabled(CONFIG_EFI)) &&
+ vaddr_end >= __START_KERNEL_map);
+ BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
+
if (!kaslr_memory_enabled())
return;
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index fb682108f4dc..3f35b48d1d9d 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -722,22 +722,19 @@ void __init x86_numa_init(void)
numa_init(dummy_numa_init);
}
-static __init int find_near_online_node(int node)
+static void __init init_memory_less_node(int nid)
{
- int n, val;
- int min_val = INT_MAX;
- int best_node = -1;
+ unsigned long zones_size[MAX_NR_ZONES] = {0};
+ unsigned long zholes_size[MAX_NR_ZONES] = {0};
- for_each_online_node(n) {
- val = node_distance(node, n);
+ /* Allocate and initialize node data. Memory-less node is now online.*/
+ alloc_node_data(nid);
+ free_area_init_node(nid, zones_size, 0, zholes_size);
- if (val < min_val) {
- min_val = val;
- best_node = n;
- }
- }
-
- return best_node;
+ /*
+ * All zonelists will be built later in start_kernel() after per cpu
+ * areas are initialized.
+ */
}
/*
@@ -766,8 +763,10 @@ void __init init_cpu_to_node(void)
if (node == NUMA_NO_NODE)
continue;
+
if (!node_online(node))
- node = find_near_online_node(node);
+ init_memory_less_node(node);
+
numa_set_node(cpu, node);
}
}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 849dc09fa4f0..e3353c97d086 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -917,11 +917,11 @@ static void populate_pte(struct cpa_data *cpa,
}
}
-static int populate_pmd(struct cpa_data *cpa,
- unsigned long start, unsigned long end,
- unsigned num_pages, pud_t *pud, pgprot_t pgprot)
+static long populate_pmd(struct cpa_data *cpa,
+ unsigned long start, unsigned long end,
+ unsigned num_pages, pud_t *pud, pgprot_t pgprot)
{
- unsigned int cur_pages = 0;
+ long cur_pages = 0;
pmd_t *pmd;
pgprot_t pmd_pgprot;
@@ -991,12 +991,12 @@ static int populate_pmd(struct cpa_data *cpa,
return num_pages;
}
-static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
- pgprot_t pgprot)
+static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
+ pgprot_t pgprot)
{
pud_t *pud;
unsigned long end;
- int cur_pages = 0;
+ long cur_pages = 0;
pgprot_t pud_pgprot;
end = start + (cpa->numpages << PAGE_SHIFT);
@@ -1052,7 +1052,7 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
/* Map trailing leftover */
if (start < end) {
- int tmp;
+ long tmp;
pud = pud_offset(pgd, start);
if (pud_none(*pud))
@@ -1078,7 +1078,7 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
pud_t *pud = NULL; /* shut up gcc */
pgd_t *pgd_entry;
- int ret;
+ long ret;
pgd_entry = cpa->pgd + pgd_index(addr);
@@ -1327,7 +1327,8 @@ static int cpa_process_alias(struct cpa_data *cpa)
static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
{
- int ret, numpages = cpa->numpages;
+ unsigned long numpages = cpa->numpages;
+ int ret;
while (numpages) {
/*
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 4dbe65622810..a7655f6caf7d 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -77,10 +77,25 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
unsigned cpu = smp_processor_id();
if (likely(prev != next)) {
+ if (IS_ENABLED(CONFIG_VMAP_STACK)) {
+ /*
+ * If our current stack is in vmalloc space and isn't
+ * mapped in the new pgd, we'll double-fault. Forcibly
+ * map it.
+ */
+ unsigned int stack_pgd_index = pgd_index(current_stack_pointer());
+
+ pgd_t *pgd = next->pgd + stack_pgd_index;
+
+ if (unlikely(pgd_none(*pgd)))
+ set_pgd(pgd, init_mm.pgd[stack_pgd_index]);
+ }
+
#ifdef CONFIG_SMP
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
this_cpu_write(cpu_tlbstate.active_mm, next);
#endif
+
cpumask_set_cpu(cpu, mm_cpumask(next));
/*
generated by cgit v1.2.3 (git 2.39.0) at 2025-03-13 05:45:13 +0300