Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index dd519f3..a6b5c65 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/arch/x86_64/mm/init.c
*
@@ -20,7 +21,6 @@
#include <linux/init.h>
#include <linux/initrd.h>
#include <linux/pagemap.h>
-#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/proc_fs.h>
#include <linux/pci.h>
@@ -59,6 +59,37 @@
#include "ident_map.c"
+#define DEFINE_POPULATE(fname, type1, type2, init) \
+static inline void fname##_init(struct mm_struct *mm, \
+ type1##_t *arg1, type2##_t *arg2, bool init) \
+{ \
+ if (init) \
+ fname##_safe(mm, arg1, arg2); \
+ else \
+ fname(mm, arg1, arg2); \
+}
+
+DEFINE_POPULATE(p4d_populate, p4d, pud, init)
+DEFINE_POPULATE(pgd_populate, pgd, p4d, init)
+DEFINE_POPULATE(pud_populate, pud, pmd, init)
+DEFINE_POPULATE(pmd_populate_kernel, pmd, pte, init)
+
+#define DEFINE_ENTRY(type1, type2, init) \
+static inline void set_##type1##_init(type1##_t *arg1, \
+ type2##_t arg2, bool init) \
+{ \
+ if (init) \
+ set_##type1##_safe(arg1, arg2); \
+ else \
+ set_##type1(arg1, arg2); \
+}
+
+DEFINE_ENTRY(p4d, p4d, init)
+DEFINE_ENTRY(pud, pud, init)
+DEFINE_ENTRY(pmd, pmd, init)
+DEFINE_ENTRY(pte, pte, init)
+
+
/*
* NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
* physical space so we can cache the place of the first one and move
@@ -197,7 +228,7 @@
if (after_bootmem)
ptr = (void *) get_zeroed_page(GFP_ATOMIC);
else
- ptr = alloc_bootmem_pages(PAGE_SIZE);
+ ptr = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
if (!ptr || ((unsigned long)ptr & ~PAGE_MASK)) {
panic("set_pte_phys: cannot allocate page data %s\n",
@@ -415,7 +446,7 @@
*/
static unsigned long __meminit
phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end,
- pgprot_t prot)
+ pgprot_t prot, bool init)
{
unsigned long pages = 0, paddr_next;
unsigned long paddr_last = paddr_end;
@@ -433,7 +464,7 @@
E820_TYPE_RAM) &&
!e820__mapped_any(paddr & PAGE_MASK, paddr_next,
E820_TYPE_RESERVED_KERN))
- set_pte(pte, __pte(0));
+ set_pte_init(pte, __pte(0), init);
continue;
}
@@ -453,7 +484,7 @@
pr_info(" pte=%p addr=%lx pte=%016lx\n", pte, paddr,
pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL).pte);
pages++;
- set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot));
+ set_pte_init(pte, pfn_pte(paddr >> PAGE_SHIFT, prot), init);
paddr_last = (paddr & PAGE_MASK) + PAGE_SIZE;
}
@@ -469,7 +500,7 @@
*/
static unsigned long __meminit
phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end,
- unsigned long page_size_mask, pgprot_t prot)
+ unsigned long page_size_mask, pgprot_t prot, bool init)
{
unsigned long pages = 0, paddr_next;
unsigned long paddr_last = paddr_end;
@@ -488,7 +519,7 @@
E820_TYPE_RAM) &&
!e820__mapped_any(paddr & PMD_MASK, paddr_next,
E820_TYPE_RESERVED_KERN))
- set_pmd(pmd, __pmd(0));
+ set_pmd_init(pmd, __pmd(0), init);
continue;
}
@@ -497,7 +528,8 @@
spin_lock(&init_mm.page_table_lock);
pte = (pte_t *)pmd_page_vaddr(*pmd);
paddr_last = phys_pte_init(pte, paddr,
- paddr_end, prot);
+ paddr_end, prot,
+ init);
spin_unlock(&init_mm.page_table_lock);
continue;
}
@@ -525,19 +557,20 @@
if (page_size_mask & (1<<PG_LEVEL_2M)) {
pages++;
spin_lock(&init_mm.page_table_lock);
- set_pte((pte_t *)pmd,
- pfn_pte((paddr & PMD_MASK) >> PAGE_SHIFT,
- __pgprot(pgprot_val(prot) | _PAGE_PSE)));
+ set_pte_init((pte_t *)pmd,
+ pfn_pte((paddr & PMD_MASK) >> PAGE_SHIFT,
+ __pgprot(pgprot_val(prot) | _PAGE_PSE)),
+ init);
spin_unlock(&init_mm.page_table_lock);
paddr_last = paddr_next;
continue;
}
pte = alloc_low_page();
- paddr_last = phys_pte_init(pte, paddr, paddr_end, new_prot);
+ paddr_last = phys_pte_init(pte, paddr, paddr_end, new_prot, init);
spin_lock(&init_mm.page_table_lock);
- pmd_populate_kernel(&init_mm, pmd, pte);
+ pmd_populate_kernel_init(&init_mm, pmd, pte, init);
spin_unlock(&init_mm.page_table_lock);
}
update_page_count(PG_LEVEL_2M, pages);
@@ -552,7 +585,7 @@
*/
static unsigned long __meminit
phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
- unsigned long page_size_mask)
+ unsigned long page_size_mask, bool init)
{
unsigned long pages = 0, paddr_next;
unsigned long paddr_last = paddr_end;
@@ -574,7 +607,7 @@
E820_TYPE_RAM) &&
!e820__mapped_any(paddr & PUD_MASK, paddr_next,
E820_TYPE_RESERVED_KERN))
- set_pud(pud, __pud(0));
+ set_pud_init(pud, __pud(0), init);
continue;
}
@@ -584,8 +617,7 @@
paddr_last = phys_pmd_init(pmd, paddr,
paddr_end,
page_size_mask,
- prot);
- __flush_tlb_all();
+ prot, init);
continue;
}
/*
@@ -612,9 +644,10 @@
if (page_size_mask & (1<<PG_LEVEL_1G)) {
pages++;
spin_lock(&init_mm.page_table_lock);
- set_pte((pte_t *)pud,
- pfn_pte((paddr & PUD_MASK) >> PAGE_SHIFT,
- PAGE_KERNEL_LARGE));
+ set_pte_init((pte_t *)pud,
+ pfn_pte((paddr & PUD_MASK) >> PAGE_SHIFT,
+ PAGE_KERNEL_LARGE),
+ init);
spin_unlock(&init_mm.page_table_lock);
paddr_last = paddr_next;
continue;
@@ -622,13 +655,12 @@
pmd = alloc_low_page();
paddr_last = phys_pmd_init(pmd, paddr, paddr_end,
- page_size_mask, prot);
+ page_size_mask, prot, init);
spin_lock(&init_mm.page_table_lock);
- pud_populate(&init_mm, pud, pmd);
+ pud_populate_init(&init_mm, pud, pmd, init);
spin_unlock(&init_mm.page_table_lock);
}
- __flush_tlb_all();
update_page_count(PG_LEVEL_1G, pages);
@@ -637,64 +669,60 @@
static unsigned long __meminit
phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
- unsigned long page_size_mask)
+ unsigned long page_size_mask, bool init)
{
- unsigned long paddr_next, paddr_last = paddr_end;
- unsigned long vaddr = (unsigned long)__va(paddr);
- int i = p4d_index(vaddr);
+ unsigned long vaddr, vaddr_end, vaddr_next, paddr_next, paddr_last;
+
+ paddr_last = paddr_end;
+ vaddr = (unsigned long)__va(paddr);
+ vaddr_end = (unsigned long)__va(paddr_end);
if (!pgtable_l5_enabled())
- return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end, page_size_mask);
+ return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end,
+ page_size_mask, init);
- for (; i < PTRS_PER_P4D; i++, paddr = paddr_next) {
- p4d_t *p4d;
+ for (; vaddr < vaddr_end; vaddr = vaddr_next) {
+ p4d_t *p4d = p4d_page + p4d_index(vaddr);
pud_t *pud;
- vaddr = (unsigned long)__va(paddr);
- p4d = p4d_page + p4d_index(vaddr);
- paddr_next = (paddr & P4D_MASK) + P4D_SIZE;
+ vaddr_next = (vaddr & P4D_MASK) + P4D_SIZE;
+ paddr = __pa(vaddr);
if (paddr >= paddr_end) {
+ paddr_next = __pa(vaddr_next);
if (!after_bootmem &&
!e820__mapped_any(paddr & P4D_MASK, paddr_next,
E820_TYPE_RAM) &&
!e820__mapped_any(paddr & P4D_MASK, paddr_next,
E820_TYPE_RESERVED_KERN))
- set_p4d(p4d, __p4d(0));
+ set_p4d_init(p4d, __p4d(0), init);
continue;
}
if (!p4d_none(*p4d)) {
pud = pud_offset(p4d, 0);
- paddr_last = phys_pud_init(pud, paddr,
- paddr_end,
- page_size_mask);
- __flush_tlb_all();
+ paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end),
+ page_size_mask, init);
continue;
}
pud = alloc_low_page();
- paddr_last = phys_pud_init(pud, paddr, paddr_end,
- page_size_mask);
+ paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end),
+ page_size_mask, init);
spin_lock(&init_mm.page_table_lock);
- p4d_populate(&init_mm, p4d, pud);
+ p4d_populate_init(&init_mm, p4d, pud, init);
spin_unlock(&init_mm.page_table_lock);
}
- __flush_tlb_all();
return paddr_last;
}
-/*
- * Create page table mapping for the physical memory for specific physical
- * addresses. The virtual and physical addresses have to be aligned on PMD level
- * down. It returns the last physical address mapped.
- */
-unsigned long __meminit
-kernel_physical_mapping_init(unsigned long paddr_start,
- unsigned long paddr_end,
- unsigned long page_size_mask)
+static unsigned long __meminit
+__kernel_physical_mapping_init(unsigned long paddr_start,
+ unsigned long paddr_end,
+ unsigned long page_size_mask,
+ bool init)
{
bool pgd_changed = false;
unsigned long vaddr, vaddr_start, vaddr_end, vaddr_next, paddr_last;
@@ -714,19 +742,22 @@
p4d = (p4d_t *)pgd_page_vaddr(*pgd);
paddr_last = phys_p4d_init(p4d, __pa(vaddr),
__pa(vaddr_end),
- page_size_mask);
+ page_size_mask,
+ init);
continue;
}
p4d = alloc_low_page();
paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end),
- page_size_mask);
+ page_size_mask, init);
spin_lock(&init_mm.page_table_lock);
if (pgtable_l5_enabled())
- pgd_populate(&init_mm, pgd, p4d);
+ pgd_populate_init(&init_mm, pgd, p4d, init);
else
- p4d_populate(&init_mm, p4d_offset(pgd, vaddr), (pud_t *) p4d);
+ p4d_populate_init(&init_mm, p4d_offset(pgd, vaddr),
+ (pud_t *) p4d, init);
+
spin_unlock(&init_mm.page_table_lock);
pgd_changed = true;
}
@@ -734,11 +765,40 @@
if (pgd_changed)
sync_global_pgds(vaddr_start, vaddr_end - 1);
- __flush_tlb_all();
-
return paddr_last;
}
+
+/*
+ * Create page table mapping for the physical memory for specific physical
+ * addresses. Note that it can only be used to populate non-present entries.
+ * The virtual and physical addresses have to be aligned on PMD level
+ * down. It returns the last physical address mapped.
+ */
+unsigned long __meminit
+kernel_physical_mapping_init(unsigned long paddr_start,
+ unsigned long paddr_end,
+ unsigned long page_size_mask)
+{
+ return __kernel_physical_mapping_init(paddr_start, paddr_end,
+ page_size_mask, true);
+}
+
+/*
+ * This function is similar to kernel_physical_mapping_init() above with the
+ * exception that it uses set_{pud,pmd}() instead of the set_{pud,pte}_safe()
+ * when updating the mapping. The caller is responsible to flush the TLBs after
+ * the function returns.
+ */
+unsigned long __meminit
+kernel_physical_mapping_change(unsigned long paddr_start,
+ unsigned long paddr_end,
+ unsigned long page_size_mask)
+{
+ return __kernel_physical_mapping_init(paddr_start, paddr_end,
+ page_size_mask, false);
+}
+
#ifndef CONFIG_NUMA
void __init initmem_init(void)
{
@@ -784,11 +844,11 @@
}
int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
- struct vmem_altmap *altmap, bool want_memblock)
+ struct mhp_restrictions *restrictions)
{
int ret;
- ret = __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+ ret = __add_pages(nid, start_pfn, nr_pages, restrictions);
WARN_ON_ONCE(ret);
/* update max_pfn, max_low_pfn and high_memory */
@@ -798,15 +858,15 @@
return ret;
}
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
- bool want_memblock)
+int arch_add_memory(int nid, u64 start, u64 size,
+ struct mhp_restrictions *restrictions)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
init_memory_mapping(start, start + size);
- return add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+ return add_pages(nid, start_pfn, nr_pages, restrictions);
}
#define PAGE_INUSE 0xFD
@@ -1138,7 +1198,6 @@
remove_pagetable(start, end, false, altmap);
}
-#ifdef CONFIG_MEMORY_HOTREMOVE
static void __meminit
kernel_physical_mapping_remove(unsigned long start, unsigned long end)
{
@@ -1148,25 +1207,17 @@
remove_pagetable(start, end, true, NULL);
}
-int __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void __ref arch_remove_memory(int nid, u64 start, u64 size,
+ struct vmem_altmap *altmap)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- struct page *page = pfn_to_page(start_pfn);
- struct zone *zone;
- int ret;
+ struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap);
+ struct zone *zone = page_zone(page);
- /* With altmap the first mapped page is offset from @start */
- if (altmap)
- page += vmem_altmap_offset(altmap);
- zone = page_zone(page);
- ret = __remove_pages(zone, start_pfn, nr_pages, altmap);
- WARN_ON_ONCE(ret);
+ __remove_pages(zone, start_pfn, nr_pages, altmap);
kernel_physical_mapping_remove(start, start + size);
-
- return ret;
}
-#endif
#endif /* CONFIG_MEMORY_HOTPLUG */
static struct kcore_list kcore_vsyscall;
@@ -1188,14 +1239,14 @@
/* clear_bss() already clear the empty_zero_page */
/* this will put all memory onto the freelists */
- free_all_bootmem();
+ memblock_free_all();
after_bootmem = 1;
x86_init.hyper.init_after_bootmem();
/*
* Must be done after boot memory is put on freelist, because here we
* might set fields in deferred struct pages that have not yet been
- * initialized, and free_all_bootmem() initializes all the reserved
+ * initialized, and memblock_free_all() initializes all the reserved
* deferred pages for us.
*/
register_page_bootmem_info();
@@ -1467,7 +1518,9 @@
{
int err;
- if (boot_cpu_has(X86_FEATURE_PSE))
+ if (end - start < PAGES_PER_SECTION * sizeof(struct page))
+ err = vmemmap_populate_basepages(start, end, node);
+ else if (boot_cpu_has(X86_FEATURE_PSE))
err = vmemmap_populate_hugepages(start, end, node, altmap);
else if (altmap) {
pr_err_once("%s: no cpu support for altmap allocations\n",