summaryrefslogtreecommitdiff
path: root/arch/x86/mm/init.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/mm/init.c')
-rw-r--r--arch/x86/mm/init.c171
1 files changed, 97 insertions, 74 deletions
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 679893ea5e68..7456df985d96 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -7,6 +7,7 @@
#include <linux/swapops.h>
#include <linux/kmemleak.h>
#include <linux/sched/task.h>
+#include <linux/execmem.h>
#include <asm/set_memory.h>
#include <asm/cpu_device_id.h>
@@ -27,6 +28,7 @@
#include <asm/text-patching.h>
#include <asm/memtype.h>
#include <asm/paravirt.h>
+#include <asm/mmu_context.h>
/*
* We need to define the tracepoints somewhere, and tlb.c
@@ -172,11 +174,7 @@ __ref void *alloc_low_pages(unsigned int num)
* randomization is enabled.
*/
-#ifndef CONFIG_X86_5LEVEL
-#define INIT_PGD_PAGE_TABLES 3
-#else
#define INIT_PGD_PAGE_TABLES 4
-#endif
#ifndef CONFIG_RANDOMIZE_MEMORY
#define INIT_PGD_PAGE_COUNT (2 * INIT_PGD_PAGE_TABLES)
@@ -261,33 +259,34 @@ static void __init probe_page_size_mask(void)
}
}
-#define INTEL_MATCH(_model) { .vendor = X86_VENDOR_INTEL, \
- .family = 6, \
- .model = _model, \
- }
/*
- * INVLPG may not properly flush Global entries
- * on these CPUs when PCIDs are enabled.
+ * INVLPG may not properly flush Global entries on
+ * these CPUs. New microcode fixes the issue.
*/
static const struct x86_cpu_id invlpg_miss_ids[] = {
- INTEL_MATCH(INTEL_FAM6_ALDERLAKE ),
- INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ),
- INTEL_MATCH(INTEL_FAM6_ATOM_GRACEMONT ),
- INTEL_MATCH(INTEL_FAM6_RAPTORLAKE ),
- INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P),
- INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S),
+ X86_MATCH_VFM(INTEL_ALDERLAKE, 0x2e),
+ X86_MATCH_VFM(INTEL_ALDERLAKE_L, 0x42c),
+ X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, 0x11),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE, 0x118),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_P, 0x4117),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_S, 0x2e),
{}
};
static void setup_pcid(void)
{
+ const struct x86_cpu_id *invlpg_miss_match;
+
if (!IS_ENABLED(CONFIG_X86_64))
return;
if (!boot_cpu_has(X86_FEATURE_PCID))
return;
- if (x86_match_cpu(invlpg_miss_ids)) {
+ invlpg_miss_match = x86_match_cpu(invlpg_miss_ids);
+
+ if (invlpg_miss_match &&
+ boot_cpu_data.microcode < invlpg_miss_match->driver_data) {
pr_info("Incomplete global flushes, disabling PCID");
setup_clear_cpu_cap(X86_FEATURE_PCID);
return;
@@ -643,8 +642,13 @@ static void __init memory_map_top_down(unsigned long map_start,
*/
addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start,
map_end);
- memblock_phys_free(addr, PMD_SIZE);
- real_end = addr + PMD_SIZE;
+ if (!addr) {
+ pr_warn("Failed to release memory for alloc_low_pages()");
+ real_end = max(map_start, ALIGN_DOWN(map_end, PMD_SIZE));
+ } else {
+ memblock_phys_free(addr, PMD_SIZE);
+ real_end = addr + PMD_SIZE;
+ }
/* step_size need to be small so pgt_buf from BRK could cover it */
step_size = PMD_SIZE;
@@ -817,31 +821,33 @@ void __init poking_init(void)
spinlock_t *ptl;
pte_t *ptep;
- poking_mm = mm_alloc();
- BUG_ON(!poking_mm);
+ text_poke_mm = mm_alloc();
+ BUG_ON(!text_poke_mm);
/* Xen PV guests need the PGD to be pinned. */
- paravirt_enter_mmap(poking_mm);
+ paravirt_enter_mmap(text_poke_mm);
+
+ set_notrack_mm(text_poke_mm);
/*
* Randomize the poking address, but make sure that the following page
* will be mapped at the same PMD. We need 2 pages, so find space for 3,
* and adjust the address if the PMD ends after the first one.
*/
- poking_addr = TASK_UNMAPPED_BASE;
+ text_poke_mm_addr = TASK_UNMAPPED_BASE;
if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
- poking_addr += (kaslr_get_random_long("Poking") & PAGE_MASK) %
+ text_poke_mm_addr += (kaslr_get_random_long("Poking") & PAGE_MASK) %
(TASK_SIZE - TASK_UNMAPPED_BASE - 3 * PAGE_SIZE);
- if (((poking_addr + PAGE_SIZE) & ~PMD_MASK) == 0)
- poking_addr += PAGE_SIZE;
+ if (((text_poke_mm_addr + PAGE_SIZE) & ~PMD_MASK) == 0)
+ text_poke_mm_addr += PAGE_SIZE;
/*
* We need to trigger the allocation of the page-tables that will be
* needed for poking now. Later, poking may be performed in an atomic
* section, which might cause allocation to fail.
*/
- ptep = get_locked_pte(poking_mm, poking_addr, &ptl);
+ ptep = get_locked_pte(text_poke_mm, text_poke_mm_addr, &ptl);
BUG_ON(!ptep);
pte_unmap_unlock(ptep, ptl);
}
@@ -990,53 +996,6 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
}
#endif
-/*
- * Calculate the precise size of the DMA zone (first 16 MB of RAM),
- * and pass it to the MM layer - to help it set zone watermarks more
- * accurately.
- *
- * Done on 64-bit systems only for the time being, although 32-bit systems
- * might benefit from this as well.
- */
-void __init memblock_find_dma_reserve(void)
-{
-#ifdef CONFIG_X86_64
- u64 nr_pages = 0, nr_free_pages = 0;
- unsigned long start_pfn, end_pfn;
- phys_addr_t start_addr, end_addr;
- int i;
- u64 u;
-
- /*
- * Iterate over all memory ranges (free and reserved ones alike),
- * to calculate the total number of pages in the first 16 MB of RAM:
- */
- nr_pages = 0;
- for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
- start_pfn = min(start_pfn, MAX_DMA_PFN);
- end_pfn = min(end_pfn, MAX_DMA_PFN);
-
- nr_pages += end_pfn - start_pfn;
- }
-
- /*
- * Iterate over free memory ranges to calculate the number of free
- * pages in the DMA zone, while not counting potential partial
- * pages at the beginning or the end of the range:
- */
- nr_free_pages = 0;
- for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) {
- start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN);
- end_pfn = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN);
-
- if (start_pfn < end_pfn)
- nr_free_pages += end_pfn - start_pfn;
- }
-
- set_dma_reserve(nr_pages - nr_free_pages);
-#endif
-}
-
void __init zone_sizes_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
@@ -1099,3 +1058,67 @@ unsigned long arch_max_swapfile_size(void)
return pages;
}
#endif
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX
+void execmem_fill_trapping_insns(void *ptr, size_t size, bool writeable)
+{
+ /* fill memory with INT3 instructions */
+ if (writeable)
+ memset(ptr, INT3_INSN_OPCODE, size);
+ else
+ text_poke_set(ptr, INT3_INSN_OPCODE, size);
+}
+#endif
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ unsigned long start, offset = 0;
+ enum execmem_range_flags flags;
+ pgprot_t pgprot;
+
+ if (kaslr_enabled())
+ offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
+
+ start = MODULES_VADDR + offset;
+
+ if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) &&
+ cpu_feature_enabled(X86_FEATURE_PSE)) {
+ pgprot = PAGE_KERNEL_ROX;
+ flags = EXECMEM_KASAN_SHADOW | EXECMEM_ROX_CACHE;
+ } else {
+ pgprot = PAGE_KERNEL;
+ flags = EXECMEM_KASAN_SHADOW;
+ }
+
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_MODULE_TEXT] = {
+ .flags = flags,
+ .start = start,
+ .end = MODULES_END,
+ .pgprot = pgprot,
+ .alignment = MODULE_ALIGN,
+ },
+ [EXECMEM_KPROBES ... EXECMEM_BPF] = {
+ .flags = EXECMEM_KASAN_SHADOW,
+ .start = start,
+ .end = MODULES_END,
+ .pgprot = PAGE_KERNEL,
+ .alignment = MODULE_ALIGN,
+ },
+ [EXECMEM_MODULE_DATA] = {
+ .flags = EXECMEM_KASAN_SHADOW,
+ .start = start,
+ .end = MODULES_END,
+ .pgprot = PAGE_KERNEL,
+ .alignment = MODULE_ALIGN,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
generated by cgit (git 2.34.1) at 2025-06-30 20:42:28 +0000