summaryrefslogtreecommitdiffstats
path: root/arch/arm64/mm/mmu.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64/mm/mmu.c')
-rw-r--r--arch/arm64/mm/mmu.c149
1 files changed, 117 insertions, 32 deletions
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index ca692a815731..ae0c3d023824 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -464,20 +464,35 @@ void __init mark_linear_text_alias_ro(void)
/*
* Remove the write permissions from the linear alias of .text/.rodata
*/
- update_mapping_prot(__pa_symbol(_text), (unsigned long)lm_alias(_text),
- (unsigned long)__init_begin - (unsigned long)_text,
+ update_mapping_prot(__pa_symbol(_stext), (unsigned long)lm_alias(_stext),
+ (unsigned long)__init_begin - (unsigned long)_stext,
PAGE_KERNEL_RO);
}
+static bool crash_mem_map __initdata;
+
+static int __init enable_crash_mem_map(char *arg)
+{
+ /*
+ * Proper parameter parsing is done by reserve_crashkernel(). We only
+ * need to know if the linear map has to avoid block mappings so that
+ * the crashkernel reservations can be unmapped later.
+ */
+ crash_mem_map = true;
+
+ return 0;
+}
+early_param("crashkernel", enable_crash_mem_map);
+
static void __init map_mem(pgd_t *pgdp)
{
- phys_addr_t kernel_start = __pa_symbol(_text);
+ phys_addr_t kernel_start = __pa_symbol(_stext);
phys_addr_t kernel_end = __pa_symbol(__init_begin);
phys_addr_t start, end;
int flags = 0;
u64 i;
- if (rodata_full || debug_pagealloc_enabled())
+ if (rodata_full || crash_mem_map || debug_pagealloc_enabled())
flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
/*
@@ -487,11 +502,6 @@ static void __init map_mem(pgd_t *pgdp)
* the following for-loop
*/
memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
-#ifdef CONFIG_KEXEC_CORE
- if (crashk_res.end)
- memblock_mark_nomap(crashk_res.start,
- resource_size(&crashk_res));
-#endif
/* map all the memory banks */
for_each_mem_range(i, &start, &end) {
@@ -506,7 +516,7 @@ static void __init map_mem(pgd_t *pgdp)
}
/*
- * Map the linear alias of the [_text, __init_begin) interval
+ * Map the linear alias of the [_stext, __init_begin) interval
* as non-executable now, and remove the write permission in
* mark_linear_text_alias_ro() below (which will be called after
* alternative patching has completed). This makes the contents
@@ -518,21 +528,6 @@ static void __init map_mem(pgd_t *pgdp)
__map_memblock(pgdp, kernel_start, kernel_end,
PAGE_KERNEL, NO_CONT_MAPPINGS);
memblock_clear_nomap(kernel_start, kernel_end - kernel_start);
-
-#ifdef CONFIG_KEXEC_CORE
- /*
- * Use page-level mappings here so that we can shrink the region
- * in page granularity and put back unused memory to buddy system
- * through /sys/kernel/kexec_crash_size interface.
- */
- if (crashk_res.end) {
- __map_memblock(pgdp, crashk_res.start, crashk_res.end + 1,
- PAGE_KERNEL,
- NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
- memblock_clear_nomap(crashk_res.start,
- resource_size(&crashk_res));
- }
-#endif
}
void mark_rodata_ro(void)
@@ -665,7 +660,7 @@ static void __init map_kernel(pgd_t *pgdp)
* Only rodata will be remapped with different permissions later on,
* all other segments are allowed to use contiguous mappings.
*/
- map_kernel_segment(pgdp, _text, _etext, text_prot, &vmlinux_text, 0,
+ map_kernel_segment(pgdp, _stext, _etext, text_prot, &vmlinux_text, 0,
VM_NO_GUARD);
map_kernel_segment(pgdp, __start_rodata, __inittext_begin, PAGE_KERNEL,
&vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD);
@@ -1132,8 +1127,11 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
void *p = NULL;
p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
- if (!p)
- return -ENOMEM;
+ if (!p) {
+ if (vmemmap_populate_basepages(addr, next, node, altmap))
+ return -ENOMEM;
+ continue;
+ }
pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL));
} else
@@ -1510,13 +1508,43 @@ static int prevent_bootmem_remove_notifier(struct notifier_block *nb,
unsigned long end_pfn = arg->start_pfn + arg->nr_pages;
unsigned long pfn = arg->start_pfn;
- if (action != MEM_GOING_OFFLINE)
+ if ((action != MEM_GOING_OFFLINE) && (action != MEM_OFFLINE))
return NOTIFY_OK;
for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+ unsigned long start = PFN_PHYS(pfn);
+ unsigned long end = start + (1UL << PA_SECTION_SHIFT);
+
ms = __pfn_to_section(pfn);
- if (early_section(ms))
+ if (!early_section(ms))
+ continue;
+
+ if (action == MEM_GOING_OFFLINE) {
+ /*
+ * Boot memory removal is not supported. Prevent
+ * it via blocking any attempted offline request
+ * for the boot memory and just report it.
+ */
+ pr_warn("Boot memory [%lx %lx] offlining attempted\n", start, end);
return NOTIFY_BAD;
+ } else if (action == MEM_OFFLINE) {
+ /*
+ * This should have never happened. Boot memory
+ * offlining should have been prevented by this
+ * very notifier. Probably some memory removal
+ * procedure might have changed which would then
+ * require further debug.
+ */
+ pr_err("Boot memory [%lx %lx] offlined\n", start, end);
+
+ /*
+ * Core memory hotplug does not process a return
+ * code from the notifier for MEM_OFFLINE events.
+ * The error condition has been reported. Return
+ * from here as if ignored.
+ */
+ return NOTIFY_DONE;
+ }
}
return NOTIFY_OK;
}
@@ -1525,9 +1553,66 @@ static struct notifier_block prevent_bootmem_remove_nb = {
.notifier_call = prevent_bootmem_remove_notifier,
};
+/*
+ * This ensures that boot memory sections on the platform are online
+ * from early boot. Memory sections could not be prevented from being
+ * offlined, unless for some reason they are not online to begin with.
+ * This helps validate the basic assumption on which the above memory
+ * event notifier works to prevent boot memory section offlining and
+ * its possible removal.
+ */
+static void validate_bootmem_online(void)
+{
+ phys_addr_t start, end, addr;
+ struct mem_section *ms;
+ u64 i;
+
+ /*
+ * Scanning across all memblock might be expensive
+ * on some big memory systems. Hence enable this
+ * validation only with DEBUG_VM.
+ */
+ if (!IS_ENABLED(CONFIG_DEBUG_VM))
+ return;
+
+ for_each_mem_range(i, &start, &end) {
+ for (addr = start; addr < end; addr += (1UL << PA_SECTION_SHIFT)) {
+ ms = __pfn_to_section(PHYS_PFN(addr));
+
+ /*
+ * All memory ranges in the system at this point
+ * should have been marked as early sections.
+ */
+ WARN_ON(!early_section(ms));
+
+ /*
+ * Memory notifier mechanism here to prevent boot
+ * memory offlining depends on the fact that each
+ * early section memory on the system is initially
+ * online. Otherwise a given memory section which
+ * is already offline will be overlooked and can
+ * be removed completely. Call out such sections.
+ */
+ if (!online_section(ms))
+ pr_err("Boot memory [%llx %llx] is offline, can be removed\n",
+ addr, addr + (1UL << PA_SECTION_SHIFT));
+ }
+ }
+}
+
static int __init prevent_bootmem_remove_init(void)
{
- return register_memory_notifier(&prevent_bootmem_remove_nb);
+ int ret = 0;
+
+ if (!IS_ENABLED(CONFIG_MEMORY_HOTREMOVE))
+ return ret;
+
+ validate_bootmem_online();
+ ret = register_memory_notifier(&prevent_bootmem_remove_nb);
+ if (ret)
+ pr_err("%s: Notifier registration failed %d\n", __func__, ret);
+
+ return ret;
}
-device_initcall(prevent_bootmem_remove_init);
+early_initcall(prevent_bootmem_remove_init);
#endif
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-02 19:00:55 +0000