summaryrefslogtreecommitdiff
path: root/arch/x86/mm/kaslr.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/mm/kaslr.c')
-rw-r--r--arch/x86/mm/kaslr.c165
1 files changed, 78 insertions, 87 deletions
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 3f452ffed7e9..3c306de52fd4 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -22,11 +22,10 @@
#include <linux/kernel.h>
#include <linux/init.h>
-#include <linux/random.h>
+#include <linux/prandom.h>
#include <linux/memblock.h>
+#include <linux/pgtable.h>
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
#include <asm/setup.h>
#include <asm/kaslr.h>
@@ -48,28 +47,34 @@ static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE;
*/
static __initdata struct kaslr_memory_region {
unsigned long *base;
+ unsigned long *end;
unsigned long size_tb;
} kaslr_regions[] = {
- { &page_offset_base, 0 },
- { &vmalloc_base, 0 },
- { &vmemmap_base, 1 },
+ {
+ .base = &page_offset_base,
+ .end = &direct_map_physmem_end,
+ },
+ {
+ .base = &vmalloc_base,
+ },
+ {
+ .base = &vmemmap_base,
+ },
};
+/*
+ * The end of the physical address space that can be mapped directly by the
+ * kernel. This starts out at (1<<MAX_PHYSMEM_BITS) - 1), but KASLR may reduce
+ * that in order to increase the available entropy for mapping other regions.
+ */
+unsigned long direct_map_physmem_end __ro_after_init;
+
/* Get size in bytes used by the memory region */
static inline unsigned long get_padding(struct kaslr_memory_region *region)
{
return (region->size_tb << TB_SHIFT);
}
-/*
- * Apply no randomization if KASLR was disabled at boot or if KASAN
- * is enabled. KASAN shadow mappings rely on regions being PGD aligned.
- */
-static inline bool kaslr_memory_enabled(void)
-{
- return kaslr_enabled() && !IS_ENABLED(CONFIG_KASAN);
-}
-
/* Initialize base and padding for each memory region randomized with KASLR */
void __init kernel_randomize_memory(void)
{
@@ -78,6 +83,7 @@ void __init kernel_randomize_memory(void)
unsigned long rand, memory_tb;
struct rnd_state rand_state;
unsigned long remain_entropy;
+ unsigned long vmemmap_size;
vaddr_start = pgtable_l5_enabled() ? __PAGE_OFFSET_BASE_L5 : __PAGE_OFFSET_BASE_L4;
vaddr = vaddr_start;
@@ -91,10 +97,12 @@ void __init kernel_randomize_memory(void)
BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE);
BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
+ /* Preset the end of the possible address space for physical memory */
+ direct_map_physmem_end = ((1ULL << MAX_PHYSMEM_BITS) - 1);
if (!kaslr_memory_enabled())
return;
- kaslr_regions[0].size_tb = 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT);
+ kaslr_regions[0].size_tb = 1 << (MAX_PHYSMEM_BITS - TB_SHIFT);
kaslr_regions[1].size_tb = VMALLOC_SIZE_TB;
/*
@@ -105,10 +113,24 @@ void __init kernel_randomize_memory(void)
memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) +
CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING;
- /* Adapt phyiscal memory region size based on available memory */
- if (memory_tb < kaslr_regions[0].size_tb)
+ /*
+ * Adapt physical memory region size based on available memory,
+ * except when CONFIG_PCI_P2PDMA is enabled. P2PDMA exposes the
+ * device BAR space assuming the direct map space is large enough
+ * for creating a ZONE_DEVICE mapping in the direct map corresponding
+ * to the physical BAR address.
+ */
+ if (!IS_ENABLED(CONFIG_PCI_P2PDMA) && (memory_tb < kaslr_regions[0].size_tb))
kaslr_regions[0].size_tb = memory_tb;
+ /*
+ * Calculate the vmemmap region size in TBs, aligned to a TB
+ * boundary.
+ */
+ vmemmap_size = (kaslr_regions[0].size_tb << (TB_SHIFT - PAGE_SHIFT)) *
+ sizeof(struct page);
+ kaslr_regions[2].size_tb = DIV_ROUND_UP(vmemmap_size, 1UL << TB_SHIFT);
+
/* Calculate entropy available between regions */
remain_entropy = vaddr_end - vaddr_start;
for (i = 0; i < ARRAY_SIZE(kaslr_regions); i++)
@@ -125,96 +147,65 @@ void __init kernel_randomize_memory(void)
*/
entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i);
prandom_bytes_state(&rand_state, &rand, sizeof(rand));
- if (pgtable_l5_enabled())
- entropy = (rand % (entropy + 1)) & P4D_MASK;
- else
- entropy = (rand % (entropy + 1)) & PUD_MASK;
+ entropy = (rand % (entropy + 1)) & PUD_MASK;
vaddr += entropy;
*kaslr_regions[i].base = vaddr;
+ /* Calculate the end of the region */
+ vaddr += get_padding(&kaslr_regions[i]);
/*
- * Jump the region and add a minimum padding based on
- * randomization alignment.
+ * KASLR trims the maximum possible size of the
+ * direct-map. Update the direct_map_physmem_end boundary.
+ * No rounding required as the region starts
+ * PUD aligned and size is in units of TB.
*/
- vaddr += get_padding(&kaslr_regions[i]);
- if (pgtable_l5_enabled())
- vaddr = round_up(vaddr + 1, P4D_SIZE);
- else
- vaddr = round_up(vaddr + 1, PUD_SIZE);
+ if (kaslr_regions[i].end)
+ *kaslr_regions[i].end = __pa_nodebug(vaddr - 1);
+
+ /* Add a minimum padding based on randomization alignment. */
+ vaddr = round_up(vaddr + 1, PUD_SIZE);
remain_entropy -= entropy;
}
}
-static void __meminit init_trampoline_pud(void)
+void __meminit init_trampoline_kaslr(void)
{
- unsigned long paddr, paddr_next;
+ pud_t *pud_page_tramp, *pud, *pud_tramp;
+ p4d_t *p4d_page_tramp, *p4d, *p4d_tramp;
+ unsigned long paddr, vaddr;
pgd_t *pgd;
- pud_t *pud_page, *pud_page_tramp;
- int i;
pud_page_tramp = alloc_low_page();
+ /*
+ * There are two mappings for the low 1MB area, the direct mapping
+ * and the 1:1 mapping for the real mode trampoline:
+ *
+ * Direct mapping: virt_addr = phys_addr + PAGE_OFFSET
+ * 1:1 mapping: virt_addr = phys_addr
+ */
paddr = 0;
- pgd = pgd_offset_k((unsigned long)__va(paddr));
- pud_page = (pud_t *) pgd_page_vaddr(*pgd);
+ vaddr = (unsigned long)__va(paddr);
+ pgd = pgd_offset_k(vaddr);
- for (i = pud_index(paddr); i < PTRS_PER_PUD; i++, paddr = paddr_next) {
- pud_t *pud, *pud_tramp;
- unsigned long vaddr = (unsigned long)__va(paddr);
+ p4d = p4d_offset(pgd, vaddr);
+ pud = pud_offset(p4d, vaddr);
- pud_tramp = pud_page_tramp + pud_index(paddr);
- pud = pud_page + pud_index(vaddr);
- paddr_next = (paddr & PUD_MASK) + PUD_SIZE;
+ pud_tramp = pud_page_tramp + pud_index(paddr);
+ *pud_tramp = *pud;
- *pud_tramp = *pud;
- }
-
- set_pgd(&trampoline_pgd_entry,
- __pgd(_KERNPG_TABLE | __pa(pud_page_tramp)));
-}
-
-static void __meminit init_trampoline_p4d(void)
-{
- unsigned long paddr, paddr_next;
- pgd_t *pgd;
- p4d_t *p4d_page, *p4d_page_tramp;
- int i;
-
- p4d_page_tramp = alloc_low_page();
-
- paddr = 0;
- pgd = pgd_offset_k((unsigned long)__va(paddr));
- p4d_page = (p4d_t *) pgd_page_vaddr(*pgd);
-
- for (i = p4d_index(paddr); i < PTRS_PER_P4D; i++, paddr = paddr_next) {
- p4d_t *p4d, *p4d_tramp;
- unsigned long vaddr = (unsigned long)__va(paddr);
+ if (pgtable_l5_enabled()) {
+ p4d_page_tramp = alloc_low_page();
p4d_tramp = p4d_page_tramp + p4d_index(paddr);
- p4d = p4d_page + p4d_index(vaddr);
- paddr_next = (paddr & P4D_MASK) + P4D_SIZE;
- *p4d_tramp = *p4d;
- }
-
- set_pgd(&trampoline_pgd_entry,
- __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp)));
-}
+ set_p4d(p4d_tramp,
+ __p4d(_KERNPG_TABLE | __pa(pud_page_tramp)));
-/*
- * Create PGD aligned trampoline table to allow real mode initialization
- * of additional CPUs. Consume only 1 low memory page.
- */
-void __meminit init_trampoline(void)
-{
-
- if (!kaslr_memory_enabled()) {
- init_trampoline_default();
- return;
+ trampoline_pgd_entry =
+ __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp));
+ } else {
+ trampoline_pgd_entry =
+ __pgd(_KERNPG_TABLE | __pa(pud_page_tramp));
}
-
- if (pgtable_l5_enabled())
- init_trampoline_p4d();
- else
- init_trampoline_pud();
}
generated by cgit (git 2.34.1) at 2025-12-24 21:53:15 +0000