From 95099d4622f8cb224d94e314c7a8e0df60b13f87 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 08:38:01 +0000
Subject: [PATCH] enable docker ppp
---
kernel/arch/arm64/mm/mmu.c | 944 +++++++++++++++++++++++++++++++++++++++++++++++-----------
1 files changed, 763 insertions(+), 181 deletions(-)
diff --git a/kernel/arch/arm64/mm/mmu.c b/kernel/arch/arm64/mm/mmu.c
index 29238f6..cce2522 100644
--- a/kernel/arch/arm64/mm/mmu.c
+++ b/kernel/arch/arm64/mm/mmu.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Based on arch/arm/mm/mmu.c
*
* Copyright (C) 1995-2005 Russell King
* Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/cache.h>
@@ -28,12 +17,11 @@
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/memblock.h>
+#include <linux/memory.h>
#include <linux/fs.h>
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
-#include <linux/dma-contiguous.h>
-#include <linux/cma.h>
#include <asm/barrier.h>
#include <asm/cputype.h>
@@ -42,18 +30,21 @@
#include <asm/kernel-pgtable.h>
#include <asm/sections.h>
#include <asm/setup.h>
-#include <asm/sizes.h>
+#include <linux/sizes.h>
#include <asm/tlb.h>
-#include <asm/memblock.h>
#include <asm/mmu_context.h>
#include <asm/ptdump.h>
#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
#define NO_BLOCK_MAPPINGS BIT(0)
#define NO_CONT_MAPPINGS BIT(1)
-u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
+u64 idmap_t0sz = TCR_T0SZ(VA_BITS_MIN);
u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
+
+u64 __section(".mmuoff.data.write") vabits_actual;
+EXPORT_SYMBOL(vabits_actual);
u64 kimage_voffset __ro_after_init;
EXPORT_SYMBOL(kimage_voffset);
@@ -69,38 +60,23 @@
static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused;
static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused;
-struct dma_contig_early_reserve {
- phys_addr_t base;
- unsigned long size;
-};
+static DEFINE_SPINLOCK(swapper_pgdir_lock);
+static DEFINE_MUTEX(fixmap_lock);
-static struct dma_contig_early_reserve dma_mmu_remap[MAX_CMA_AREAS];
-static int dma_mmu_remap_num;
-
-void __init dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
+void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd)
{
- if (dma_mmu_remap_num >= ARRAY_SIZE(dma_mmu_remap)) {
- pr_err("ARM64: Not enough slots for DMA fixup reserved regions!\n");
- return;
- }
- dma_mmu_remap[dma_mmu_remap_num].base = base;
- dma_mmu_remap[dma_mmu_remap_num].size = size;
- dma_mmu_remap_num++;
-}
+ pgd_t *fixmap_pgdp;
-static bool dma_overlap(phys_addr_t start, phys_addr_t end)
-{
- int i;
-
- for (i = 0; i < dma_mmu_remap_num; i++) {
- phys_addr_t dma_base = dma_mmu_remap[i].base;
- phys_addr_t dma_end = dma_mmu_remap[i].base +
- dma_mmu_remap[i].size;
-
- if ((dma_base < end) && (dma_end > start))
- return true;
- }
- return false;
+ spin_lock(&swapper_pgdir_lock);
+ fixmap_pgdp = pgd_set_fixmap(__pa_symbol(pgdp));
+ WRITE_ONCE(*fixmap_pgdp, pgd);
+ /*
+ * We need dsb(ishst) here to ensure the page-table-walker sees
+ * our new entry before set_p?d() returns. The fixmap's
+ * flush_tlb_kernel_range() via clear_fixmap() does this for us.
+ */
+ pgd_clear_fixmap();
+ spin_unlock(&swapper_pgdir_lock);
}
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
@@ -114,12 +90,14 @@
}
EXPORT_SYMBOL(phys_mem_access_prot);
-static phys_addr_t __init early_pgtable_alloc(void)
+static phys_addr_t __init early_pgtable_alloc(int shift)
{
phys_addr_t phys;
void *ptr;
- phys = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+ phys = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+ if (!phys)
+ panic("Failed to allocate page table page\n");
/*
* The FIX_{PGD,PUD,PMD} slots may be in active use, but the FIX_PTE
@@ -145,7 +123,7 @@
* The following mapping attributes may be updated in live
* kernel mappings without the need for break-before-make.
*/
- static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
+ pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
/* creating or taking down mappings is always safe */
if (old == 0 || new == 0)
@@ -158,6 +136,17 @@
/* Transitioning from Non-Global to Global is unsafe */
if (old & ~new & PTE_NG)
return false;
+
+ /*
+ * Changing the memory type between Normal and Normal-Tagged is safe
+ * since Tagged is considered a permission attribute from the
+ * mismatched attribute aliases perspective.
+ */
+ if (((old & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL) ||
+ (old & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL_TAGGED)) &&
+ ((new & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL) ||
+ (new & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL_TAGGED)))
+ mask |= PTE_ATTRINDX_MASK;
return ((old ^ new) & ~mask) == 0;
}
@@ -189,7 +178,7 @@
static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
unsigned long end, phys_addr_t phys,
pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void),
+ phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long next;
@@ -199,7 +188,7 @@
if (pmd_none(pmd)) {
phys_addr_t pte_phys;
BUG_ON(!pgtable_alloc);
- pte_phys = pgtable_alloc();
+ pte_phys = pgtable_alloc(PAGE_SHIFT);
__pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
pmd = READ_ONCE(*pmdp);
}
@@ -223,7 +212,7 @@
static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void), int flags)
+ phys_addr_t (*pgtable_alloc)(int), int flags)
{
unsigned long next;
pmd_t *pmdp;
@@ -236,8 +225,7 @@
/* try section mapping first */
if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
- (flags & NO_BLOCK_MAPPINGS) == 0 &&
- !dma_overlap(phys, phys + next - addr)) {
+ (flags & NO_BLOCK_MAPPINGS) == 0) {
pmd_set_huge(pmdp, phys, prot);
/*
@@ -262,7 +250,7 @@
static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
unsigned long end, phys_addr_t phys,
pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void), int flags)
+ phys_addr_t (*pgtable_alloc)(int), int flags)
{
unsigned long next;
pud_t pud = READ_ONCE(*pudp);
@@ -274,7 +262,7 @@
if (pud_none(pud)) {
phys_addr_t pmd_phys;
BUG_ON(!pgtable_alloc);
- pmd_phys = pgtable_alloc();
+ pmd_phys = pgtable_alloc(PMD_SHIFT);
__pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
pud = READ_ONCE(*pudp);
}
@@ -310,23 +298,30 @@
static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void),
+ phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long next;
pud_t *pudp;
- pgd_t pgd = READ_ONCE(*pgdp);
+ p4d_t *p4dp = p4d_offset(pgdp, addr);
+ p4d_t p4d = READ_ONCE(*p4dp);
- if (pgd_none(pgd)) {
+ if (p4d_none(p4d)) {
phys_addr_t pud_phys;
BUG_ON(!pgtable_alloc);
- pud_phys = pgtable_alloc();
- __pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE);
- pgd = READ_ONCE(*pgdp);
+ pud_phys = pgtable_alloc(PUD_SHIFT);
+ __p4d_populate(p4dp, pud_phys, PUD_TYPE_TABLE);
+ p4d = READ_ONCE(*p4dp);
}
- BUG_ON(pgd_bad(pgd));
+ BUG_ON(p4d_bad(p4d));
- pudp = pud_set_fixmap_offset(pgdp, addr);
+ /*
+ * No need for locking during early boot. And it doesn't work as
+ * expected with KASLR enabled.
+ */
+ if (system_state != SYSTEM_BOOTING)
+ mutex_lock(&fixmap_lock);
+ pudp = pud_set_fixmap_offset(p4dp, addr);
do {
pud_t old_pud = READ_ONCE(*pudp);
@@ -336,8 +331,7 @@
* For 4K granule only, attempt to put down a 1GB block
*/
if (use_1G_block(addr, next, phys) &&
- (flags & NO_BLOCK_MAPPINGS) == 0 &&
- !dma_overlap(phys, phys + next - addr)) {
+ (flags & NO_BLOCK_MAPPINGS) == 0) {
pud_set_huge(pudp, phys, prot);
/*
@@ -357,16 +351,18 @@
} while (pudp++, addr = next, addr != end);
pud_clear_fixmap();
+ if (system_state != SYSTEM_BOOTING)
+ mutex_unlock(&fixmap_lock);
}
static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void),
+ phys_addr_t (*pgtable_alloc)(int),
int flags)
{
- unsigned long addr, length, end, next;
- pgd_t *pgdp = pgd_offset_raw(pgdir, virt);
+ unsigned long addr, end, next;
+ pgd_t *pgdp = pgd_offset_pgd(pgdir, virt);
/*
* If the virtual and physical address don't have the same offset
@@ -377,9 +373,8 @@
phys &= PAGE_MASK;
addr = virt & PAGE_MASK;
- length = PAGE_ALIGN(size + (virt & ~PAGE_MASK));
+ end = PAGE_ALIGN(virt + size);
- end = addr + length;
do {
next = pgd_addr_end(addr, end);
alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc,
@@ -388,37 +383,35 @@
} while (pgdp++, addr = next, addr != end);
}
-static phys_addr_t pgd_pgtable_alloc(void)
+static phys_addr_t __pgd_pgtable_alloc(int shift)
{
- void *ptr = (void *)__get_free_page(PGALLOC_GFP);
- if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
- BUG();
+ void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL);
+ BUG_ON(!ptr);
/* Ensure the zeroed page is visible to the page table walker */
dsb(ishst);
return __pa(ptr);
}
-/**
- * create_pgtable_mapping - create a pagetable mapping for given
- * physical start and end addresses.
- * @start: physical start address.
- * @end: physical end address.
- */
-void create_pgtable_mapping(phys_addr_t start, phys_addr_t end)
+static phys_addr_t pgd_pgtable_alloc(int shift)
{
- unsigned long virt = (unsigned long)phys_to_virt(start);
+ phys_addr_t pa = __pgd_pgtable_alloc(shift);
- if (virt < VMALLOC_START) {
- pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
- &start, virt);
- return;
- }
+ /*
+ * Call proper page table ctor in case later we need to
+ * call core mm functions like apply_to_page_range() on
+ * this pre-allocated page table.
+ *
+ * We don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK if pmd is
+ * folded, and if so pgtable_pmd_page_ctor() becomes nop.
+ */
+ if (shift == PAGE_SHIFT)
+ BUG_ON(!pgtable_pte_page_ctor(phys_to_page(pa)));
+ else if (shift == PMD_SHIFT)
+ BUG_ON(!pgtable_pmd_page_ctor(phys_to_page(pa)));
- __create_pgd_mapping(init_mm.pgd, start, virt, end - start,
- PAGE_KERNEL, NULL, 0);
+ return pa;
}
-EXPORT_SYMBOL_GPL(create_pgtable_mapping);
/*
* This function can only be used to modify existing table entries,
@@ -428,7 +421,7 @@
static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
phys_addr_t size, pgprot_t prot)
{
- if (virt < VMALLOC_START) {
+ if ((virt >= PAGE_END) && (virt < VMALLOC_START)) {
pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
&phys, virt);
return;
@@ -455,7 +448,7 @@
static void update_mapping_prot(phys_addr_t phys, unsigned long virt,
phys_addr_t size, pgprot_t prot)
{
- if (virt < VMALLOC_START) {
+ if ((virt >= PAGE_END) && (virt < VMALLOC_START)) {
pr_warn("BUG: not updating mapping for %pa at 0x%016lx - outside kernel range\n",
&phys, virt);
return;
@@ -485,14 +478,31 @@
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_end = __pa_symbol(__init_begin);
- struct memblock_region *reg;
+ phys_addr_t start, end;
int flags = 0;
+ u64 i;
- if (debug_pagealloc_enabled())
+ if (rodata_full || debug_pagealloc_enabled() ||
+ IS_ENABLED(CONFIG_KFENCE))
flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
/*
@@ -502,23 +512,29 @@
* 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));
+ if (crash_mem_map) {
+ if (IS_ENABLED(CONFIG_ZONE_DMA) ||
+ IS_ENABLED(CONFIG_ZONE_DMA32))
+ flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+ else if (crashk_res.end)
+ memblock_mark_nomap(crashk_res.start,
+ resource_size(&crashk_res));
+ }
#endif
/* map all the memory banks */
- for_each_memblock(memory, reg) {
- phys_addr_t start = reg->base;
- phys_addr_t end = start + reg->size;
-
+ for_each_mem_range(i, &start, &end) {
if (start >= end)
break;
- if (memblock_is_nomap(reg))
- continue;
-
- __map_memblock(pgdp, start, end, PAGE_KERNEL, flags);
+ /*
+ * The linear map must allow allocation tags reading/writing
+ * if MTE is present. Otherwise, it has the same attributes as
+ * PAGE_KERNEL.
+ */
+ __map_memblock(pgdp, start, end, pgprot_tagged(PAGE_KERNEL),
+ flags);
}
/*
@@ -535,18 +551,22 @@
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));
+#ifdef CONFIG_KEXEC_CORE
+ if (crash_mem_map &&
+ !IS_ENABLED(CONFIG_ZONE_DMA) && !IS_ENABLED(CONFIG_ZONE_DMA32)) {
+ 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
}
@@ -593,13 +613,27 @@
static int __init parse_rodata(char *arg)
{
- return strtobool(arg, &rodata_enabled);
+ int ret = strtobool(arg, &rodata_enabled);
+ if (!ret) {
+ rodata_full = false;
+ return 0;
+ }
+
+ /* permit 'full' in addition to boolean options */
+ if (strcmp(arg, "full"))
+ return -EINVAL;
+
+ rodata_enabled = true;
+ rodata_full = true;
+ return 0;
}
early_param("rodata", parse_rodata);
#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
static int __init map_entry_trampoline(void)
{
+ int i;
+
pgprot_t prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start);
@@ -608,11 +642,15 @@
/* Map only the text into the trampoline page table */
memset(tramp_pg_dir, 0, PGD_SIZE);
- __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
- prot, pgd_pgtable_alloc, 0);
+ __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS,
+ entry_tramp_text_size(), prot,
+ __pgd_pgtable_alloc, NO_BLOCK_MAPPINGS);
/* Map both the text and data into the kernel page table */
- __set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
+ for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++)
+ __set_fixmap(FIX_ENTRY_TRAMP_TEXT1 - i,
+ pa_start + i * PAGE_SIZE, prot);
+
if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
extern char __entry_tramp_data_start[];
@@ -625,6 +663,22 @@
}
core_initcall(map_entry_trampoline);
#endif
+
+/*
+ * Open coded check for BTI, only for use to determine configuration
+ * for early mappings for before the cpufeature code has run.
+ */
+static bool arm64_early_this_cpu_has_bti(void)
+{
+ u64 pfr1;
+
+ if (!IS_ENABLED(CONFIG_ARM64_BTI_KERNEL))
+ return false;
+
+ pfr1 = __read_sysreg_by_encoding(SYS_ID_AA64PFR1_EL1);
+ return cpuid_feature_extract_unsigned_field(pfr1,
+ ID_AA64PFR1_BT_SHIFT);
+}
/*
* Create fine-grained mappings for the kernel.
@@ -642,6 +696,14 @@
pgprot_t text_prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
/*
+ * If we have a CPU that supports BTI and a kernel built for
+ * BTI then mark the kernel executable text as guarded pages
+ * now so we don't have to rewrite the page tables later.
+ */
+ if (arm64_early_this_cpu_has_bti())
+ text_prot = __pgprot_modify(text_prot, PTE_GP, PTE_GP);
+
+ /*
* Only rodata will be remapped with different permissions later on,
* all other segments are allowed to use contiguous mappings.
*/
@@ -655,15 +717,18 @@
&vmlinux_initdata, 0, VM_NO_GUARD);
map_kernel_segment(pgdp, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0);
- if (!READ_ONCE(pgd_val(*pgd_offset_raw(pgdp, FIXADDR_START)))) {
+ if (!READ_ONCE(pgd_val(*pgd_offset_pgd(pgdp, FIXADDR_START)))) {
/*
* The fixmap falls in a separate pgd to the kernel, and doesn't
* live in the carveout for the swapper_pg_dir. We can simply
* re-use the existing dir for the fixmap.
*/
- set_pgd(pgd_offset_raw(pgdp, FIXADDR_START),
+ set_pgd(pgd_offset_pgd(pgdp, FIXADDR_START),
READ_ONCE(*pgd_offset_k(FIXADDR_START)));
} else if (CONFIG_PGTABLE_LEVELS > 3) {
+ pgd_t *bm_pgdp;
+ p4d_t *bm_p4dp;
+ pud_t *bm_pudp;
/*
* The fixmap shares its top level pgd entry with the kernel
* mapping. This can really only occur when we are running
@@ -671,9 +736,10 @@
* entry instead.
*/
BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
- pud_populate(&init_mm,
- pud_set_fixmap_offset(pgdp, FIXADDR_START),
- lm_alias(bm_pmd));
+ bm_pgdp = pgd_offset_pgd(pgdp, FIXADDR_START);
+ bm_p4dp = p4d_offset(bm_pgdp, FIXADDR_START);
+ bm_pudp = pud_set_fixmap_offset(bm_p4dp, FIXADDR_START);
+ pud_populate(&init_mm, bm_pudp, lm_alias(bm_pmd));
pud_clear_fixmap();
} else {
BUG();
@@ -682,40 +748,22 @@
kasan_copy_shadow(pgdp);
}
-/*
- * paging_init() sets up the page tables, initialises the zone memory
- * maps and sets up the zero page.
- */
void __init paging_init(void)
{
- phys_addr_t pgd_phys = early_pgtable_alloc();
- pgd_t *pgdp = pgd_set_fixmap(pgd_phys);
+ pgd_t *pgdp = pgd_set_fixmap(__pa_symbol(swapper_pg_dir));
map_kernel(pgdp);
map_mem(pgdp);
- /*
- * We want to reuse the original swapper_pg_dir so we don't have to
- * communicate the new address to non-coherent secondaries in
- * secondary_entry, and so cpu_switch_mm can generate the address with
- * adrp+add rather than a load from some global variable.
- *
- * To do this we need to go via a temporary pgd.
- */
- cpu_replace_ttbr1(__va(pgd_phys));
- memcpy(swapper_pg_dir, pgdp, PGD_SIZE);
- cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
-
pgd_clear_fixmap();
- memblock_free(pgd_phys, PAGE_SIZE);
- /*
- * We only reuse the PGD from the swapper_pg_dir, not the pud + pmd
- * allocated with it.
- */
- memblock_free(__pa_symbol(swapper_pg_dir) + PAGE_SIZE,
- __pa_symbol(swapper_pg_end) - __pa_symbol(swapper_pg_dir)
- - PAGE_SIZE);
+ cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+ init_mm.pgd = swapper_pg_dir;
+
+ memblock_free(__pa_symbol(init_pg_dir),
+ __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir));
+
+ memblock_allow_resize();
}
/*
@@ -724,10 +772,12 @@
int kern_addr_valid(unsigned long addr)
{
pgd_t *pgdp;
+ p4d_t *p4dp;
pud_t *pudp, pud;
pmd_t *pmdp, pmd;
pte_t *ptep, pte;
+ addr = arch_kasan_reset_tag(addr);
if ((((long)addr) >> VA_BITS) != -1UL)
return 0;
@@ -735,7 +785,11 @@
if (pgd_none(READ_ONCE(*pgdp)))
return 0;
- pudp = pud_offset(pgdp, addr);
+ p4dp = p4d_offset(pgdp, addr);
+ if (p4d_none(READ_ONCE(*p4dp)))
+ return 0;
+
+ pudp = pud_offset(p4dp, addr);
pud = READ_ONCE(*pudp);
if (pud_none(pud))
return 0;
@@ -758,13 +812,336 @@
return pfn_valid(pte_pfn(pte));
}
-EXPORT_SYMBOL_GPL(kern_addr_valid);
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static void free_hotplug_page_range(struct page *page, size_t size,
+ struct vmem_altmap *altmap)
+{
+ if (altmap) {
+ vmem_altmap_free(altmap, size >> PAGE_SHIFT);
+ } else {
+ WARN_ON(PageReserved(page));
+ free_pages((unsigned long)page_address(page), get_order(size));
+ }
+}
+
+static void free_hotplug_pgtable_page(struct page *page)
+{
+ free_hotplug_page_range(page, PAGE_SIZE, NULL);
+}
+
+static bool pgtable_range_aligned(unsigned long start, unsigned long end,
+ unsigned long floor, unsigned long ceiling,
+ unsigned long mask)
+{
+ start &= mask;
+ if (start < floor)
+ return false;
+
+ if (ceiling) {
+ ceiling &= mask;
+ if (!ceiling)
+ return false;
+ }
+
+ if (end - 1 > ceiling - 1)
+ return false;
+ return true;
+}
+
+static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr,
+ unsigned long end, bool free_mapped,
+ struct vmem_altmap *altmap)
+{
+ pte_t *ptep, pte;
+
+ do {
+ ptep = pte_offset_kernel(pmdp, addr);
+ pte = READ_ONCE(*ptep);
+ if (pte_none(pte))
+ continue;
+
+ WARN_ON(!pte_present(pte));
+ pte_clear(&init_mm, addr, ptep);
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+ if (free_mapped)
+ free_hotplug_page_range(pte_page(pte),
+ PAGE_SIZE, altmap);
+ } while (addr += PAGE_SIZE, addr < end);
+}
+
+static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr,
+ unsigned long end, bool free_mapped,
+ struct vmem_altmap *altmap)
+{
+ unsigned long next;
+ pmd_t *pmdp, pmd;
+
+ do {
+ next = pmd_addr_end(addr, end);
+ pmdp = pmd_offset(pudp, addr);
+ pmd = READ_ONCE(*pmdp);
+ if (pmd_none(pmd))
+ continue;
+
+ WARN_ON(!pmd_present(pmd));
+ if (pmd_sect(pmd)) {
+ pmd_clear(pmdp);
+
+ /*
+ * One TLBI should be sufficient here as the PMD_SIZE
+ * range is mapped with a single block entry.
+ */
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+ if (free_mapped)
+ free_hotplug_page_range(pmd_page(pmd),
+ PMD_SIZE, altmap);
+ continue;
+ }
+ WARN_ON(!pmd_table(pmd));
+ unmap_hotplug_pte_range(pmdp, addr, next, free_mapped, altmap);
+ } while (addr = next, addr < end);
+}
+
+static void unmap_hotplug_pud_range(p4d_t *p4dp, unsigned long addr,
+ unsigned long end, bool free_mapped,
+ struct vmem_altmap *altmap)
+{
+ unsigned long next;
+ pud_t *pudp, pud;
+
+ do {
+ next = pud_addr_end(addr, end);
+ pudp = pud_offset(p4dp, addr);
+ pud = READ_ONCE(*pudp);
+ if (pud_none(pud))
+ continue;
+
+ WARN_ON(!pud_present(pud));
+ if (pud_sect(pud)) {
+ pud_clear(pudp);
+
+ /*
+ * One TLBI should be sufficient here as the PUD_SIZE
+ * range is mapped with a single block entry.
+ */
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+ if (free_mapped)
+ free_hotplug_page_range(pud_page(pud),
+ PUD_SIZE, altmap);
+ continue;
+ }
+ WARN_ON(!pud_table(pud));
+ unmap_hotplug_pmd_range(pudp, addr, next, free_mapped, altmap);
+ } while (addr = next, addr < end);
+}
+
+static void unmap_hotplug_p4d_range(pgd_t *pgdp, unsigned long addr,
+ unsigned long end, bool free_mapped,
+ struct vmem_altmap *altmap)
+{
+ unsigned long next;
+ p4d_t *p4dp, p4d;
+
+ do {
+ next = p4d_addr_end(addr, end);
+ p4dp = p4d_offset(pgdp, addr);
+ p4d = READ_ONCE(*p4dp);
+ if (p4d_none(p4d))
+ continue;
+
+ WARN_ON(!p4d_present(p4d));
+ unmap_hotplug_pud_range(p4dp, addr, next, free_mapped, altmap);
+ } while (addr = next, addr < end);
+}
+
+static void unmap_hotplug_range(unsigned long addr, unsigned long end,
+ bool free_mapped, struct vmem_altmap *altmap)
+{
+ unsigned long next;
+ pgd_t *pgdp, pgd;
+
+ /*
+ * altmap can only be used as vmemmap mapping backing memory.
+ * In case the backing memory itself is not being freed, then
+ * altmap is irrelevant. Warn about this inconsistency when
+ * encountered.
+ */
+ WARN_ON(!free_mapped && altmap);
+
+ do {
+ next = pgd_addr_end(addr, end);
+ pgdp = pgd_offset_k(addr);
+ pgd = READ_ONCE(*pgdp);
+ if (pgd_none(pgd))
+ continue;
+
+ WARN_ON(!pgd_present(pgd));
+ unmap_hotplug_p4d_range(pgdp, addr, next, free_mapped, altmap);
+ } while (addr = next, addr < end);
+}
+
+static void free_empty_pte_table(pmd_t *pmdp, unsigned long addr,
+ unsigned long end, unsigned long floor,
+ unsigned long ceiling)
+{
+ pte_t *ptep, pte;
+ unsigned long i, start = addr;
+
+ do {
+ ptep = pte_offset_kernel(pmdp, addr);
+ pte = READ_ONCE(*ptep);
+
+ /*
+ * This is just a sanity check here which verifies that
+ * pte clearing has been done by earlier unmap loops.
+ */
+ WARN_ON(!pte_none(pte));
+ } while (addr += PAGE_SIZE, addr < end);
+
+ if (!pgtable_range_aligned(start, end, floor, ceiling, PMD_MASK))
+ return;
+
+ /*
+ * Check whether we can free the pte page if the rest of the
+ * entries are empty. Overlap with other regions have been
+ * handled by the floor/ceiling check.
+ */
+ ptep = pte_offset_kernel(pmdp, 0UL);
+ for (i = 0; i < PTRS_PER_PTE; i++) {
+ if (!pte_none(READ_ONCE(ptep[i])))
+ return;
+ }
+
+ pmd_clear(pmdp);
+ __flush_tlb_kernel_pgtable(start);
+ free_hotplug_pgtable_page(virt_to_page(ptep));
+}
+
+static void free_empty_pmd_table(pud_t *pudp, unsigned long addr,
+ unsigned long end, unsigned long floor,
+ unsigned long ceiling)
+{
+ pmd_t *pmdp, pmd;
+ unsigned long i, next, start = addr;
+
+ do {
+ next = pmd_addr_end(addr, end);
+ pmdp = pmd_offset(pudp, addr);
+ pmd = READ_ONCE(*pmdp);
+ if (pmd_none(pmd))
+ continue;
+
+ WARN_ON(!pmd_present(pmd) || !pmd_table(pmd) || pmd_sect(pmd));
+ free_empty_pte_table(pmdp, addr, next, floor, ceiling);
+ } while (addr = next, addr < end);
+
+ if (CONFIG_PGTABLE_LEVELS <= 2)
+ return;
+
+ if (!pgtable_range_aligned(start, end, floor, ceiling, PUD_MASK))
+ return;
+
+ /*
+ * Check whether we can free the pmd page if the rest of the
+ * entries are empty. Overlap with other regions have been
+ * handled by the floor/ceiling check.
+ */
+ pmdp = pmd_offset(pudp, 0UL);
+ for (i = 0; i < PTRS_PER_PMD; i++) {
+ if (!pmd_none(READ_ONCE(pmdp[i])))
+ return;
+ }
+
+ pud_clear(pudp);
+ __flush_tlb_kernel_pgtable(start);
+ free_hotplug_pgtable_page(virt_to_page(pmdp));
+}
+
+static void free_empty_pud_table(p4d_t *p4dp, unsigned long addr,
+ unsigned long end, unsigned long floor,
+ unsigned long ceiling)
+{
+ pud_t *pudp, pud;
+ unsigned long i, next, start = addr;
+
+ do {
+ next = pud_addr_end(addr, end);
+ pudp = pud_offset(p4dp, addr);
+ pud = READ_ONCE(*pudp);
+ if (pud_none(pud))
+ continue;
+
+ WARN_ON(!pud_present(pud) || !pud_table(pud) || pud_sect(pud));
+ free_empty_pmd_table(pudp, addr, next, floor, ceiling);
+ } while (addr = next, addr < end);
+
+ if (CONFIG_PGTABLE_LEVELS <= 3)
+ return;
+
+ if (!pgtable_range_aligned(start, end, floor, ceiling, PGDIR_MASK))
+ return;
+
+ /*
+ * Check whether we can free the pud page if the rest of the
+ * entries are empty. Overlap with other regions have been
+ * handled by the floor/ceiling check.
+ */
+ pudp = pud_offset(p4dp, 0UL);
+ for (i = 0; i < PTRS_PER_PUD; i++) {
+ if (!pud_none(READ_ONCE(pudp[i])))
+ return;
+ }
+
+ p4d_clear(p4dp);
+ __flush_tlb_kernel_pgtable(start);
+ free_hotplug_pgtable_page(virt_to_page(pudp));
+}
+
+static void free_empty_p4d_table(pgd_t *pgdp, unsigned long addr,
+ unsigned long end, unsigned long floor,
+ unsigned long ceiling)
+{
+ unsigned long next;
+ p4d_t *p4dp, p4d;
+
+ do {
+ next = p4d_addr_end(addr, end);
+ p4dp = p4d_offset(pgdp, addr);
+ p4d = READ_ONCE(*p4dp);
+ if (p4d_none(p4d))
+ continue;
+
+ WARN_ON(!p4d_present(p4d));
+ free_empty_pud_table(p4dp, addr, next, floor, ceiling);
+ } while (addr = next, addr < end);
+}
+
+static void free_empty_tables(unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
+{
+ unsigned long next;
+ pgd_t *pgdp, pgd;
+
+ do {
+ next = pgd_addr_end(addr, end);
+ pgdp = pgd_offset_k(addr);
+ pgd = READ_ONCE(*pgdp);
+ if (pgd_none(pgd))
+ continue;
+
+ WARN_ON(!pgd_present(pgd));
+ free_empty_p4d_table(pgdp, addr, next, floor, ceiling);
+ } while (addr = next, addr < end);
+}
+#endif
+
#ifdef CONFIG_SPARSEMEM_VMEMMAP
#if !ARM64_SWAPPER_USES_SECTION_MAPS
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap)
{
- return vmemmap_populate_basepages(start, end, node);
+ return vmemmap_populate_basepages(start, end, node, altmap);
}
#else /* !ARM64_SWAPPER_USES_SECTION_MAPS */
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
@@ -773,6 +1150,7 @@
unsigned long addr = start;
unsigned long next;
pgd_t *pgdp;
+ p4d_t *p4dp;
pud_t *pudp;
pmd_t *pmdp;
@@ -783,7 +1161,11 @@
if (!pgdp)
return -ENOMEM;
- pudp = vmemmap_pud_populate(pgdp, addr, node);
+ p4dp = vmemmap_p4d_populate(pgdp, addr, node);
+ if (!p4dp)
+ return -ENOMEM;
+
+ pudp = vmemmap_pud_populate(p4dp, addr, node);
if (!pudp)
return -ENOMEM;
@@ -791,9 +1173,12 @@
if (pmd_none(READ_ONCE(*pmdp))) {
void *p = NULL;
- p = vmemmap_alloc_block_buf(PMD_SIZE, node);
- if (!p)
- return -ENOMEM;
+ p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
+ if (!p) {
+ if (vmemmap_populate_basepages(addr, next, node, altmap))
+ return -ENOMEM;
+ continue;
+ }
pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL));
} else
@@ -802,21 +1187,28 @@
return 0;
}
-#endif /* CONFIG_ARM64_64K_PAGES */
+#endif /* !ARM64_SWAPPER_USES_SECTION_MAPS */
void vmemmap_free(unsigned long start, unsigned long end,
struct vmem_altmap *altmap)
{
+#ifdef CONFIG_MEMORY_HOTPLUG
+ WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
+
+ unmap_hotplug_range(start, end, true, altmap);
+ free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END);
+#endif
}
#endif /* CONFIG_SPARSEMEM_VMEMMAP */
static inline pud_t * fixmap_pud(unsigned long addr)
{
pgd_t *pgdp = pgd_offset_k(addr);
- pgd_t pgd = READ_ONCE(*pgdp);
+ p4d_t *p4dp = p4d_offset(pgdp, addr);
+ p4d_t p4d = READ_ONCE(*p4dp);
- BUG_ON(pgd_none(pgd) || pgd_bad(pgd));
+ BUG_ON(p4d_none(p4d) || p4d_bad(p4d));
- return pud_offset_kimg(pgdp, addr);
+ return pud_offset_kimg(p4dp, addr);
}
static inline pmd_t * fixmap_pmd(unsigned long addr)
@@ -842,25 +1234,27 @@
*/
void __init early_fixmap_init(void)
{
- pgd_t *pgdp, pgd;
+ pgd_t *pgdp;
+ p4d_t *p4dp, p4d;
pud_t *pudp;
pmd_t *pmdp;
unsigned long addr = FIXADDR_START;
pgdp = pgd_offset_k(addr);
- pgd = READ_ONCE(*pgdp);
+ p4dp = p4d_offset(pgdp, addr);
+ p4d = READ_ONCE(*p4dp);
if (CONFIG_PGTABLE_LEVELS > 3 &&
- !(pgd_none(pgd) || pgd_page_paddr(pgd) == __pa_symbol(bm_pud))) {
+ !(p4d_none(p4d) || p4d_page_paddr(p4d) == __pa_symbol(bm_pud))) {
/*
* We only end up here if the kernel mapping and the fixmap
* share the top level pgd entry, which should only happen on
* 16k/4 levels configurations.
*/
BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
- pudp = pud_offset_kimg(pgdp, addr);
+ pudp = pud_offset_kimg(p4dp, addr);
} else {
- if (pgd_none(pgd))
- __pgd_populate(pgdp, __pa_symbol(bm_pud), PUD_TYPE_TABLE);
+ if (p4d_none(p4d))
+ __p4d_populate(p4dp, __pa_symbol(bm_pud), PUD_TYPE_TABLE);
pudp = fixmap_pud(addr);
}
if (pud_none(READ_ONCE(*pudp)))
@@ -978,43 +1372,39 @@
* SW table walks can't handle removal of intermediate entries.
*/
return IS_ENABLED(CONFIG_ARM64_4K_PAGES) &&
- !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS);
+ !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
}
int __init arch_ioremap_pmd_supported(void)
{
/* See arch_ioremap_pud_supported() */
- return !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS);
+ return !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
}
int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
{
- pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT |
- pgprot_val(mk_sect_prot(prot)));
- pud_t new_pud = pfn_pud(__phys_to_pfn(phys), sect_prot);
+ pud_t new_pud = pfn_pud(__phys_to_pfn(phys), mk_pud_sect_prot(prot));
/* Only allow permission changes for now */
if (!pgattr_change_is_safe(READ_ONCE(pud_val(*pudp)),
pud_val(new_pud)))
return 0;
- BUG_ON(phys & ~PUD_MASK);
+ VM_BUG_ON(phys & ~PUD_MASK);
set_pud(pudp, new_pud);
return 1;
}
int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot)
{
- pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT |
- pgprot_val(mk_sect_prot(prot)));
- pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), sect_prot);
+ pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), mk_pmd_sect_prot(prot));
/* Only allow permission changes for now */
if (!pgattr_change_is_safe(READ_ONCE(pmd_val(*pmdp)),
pmd_val(new_pmd)))
return 0;
- BUG_ON(phys & ~PMD_MASK);
+ VM_BUG_ON(phys & ~PMD_MASK);
set_pmd(pmdp, new_pmd);
return 1;
}
@@ -1042,10 +1432,8 @@
pmd = READ_ONCE(*pmdp);
- if (!pmd_present(pmd))
- return 1;
if (!pmd_table(pmd)) {
- VM_WARN_ON(!pmd_table(pmd));
+ VM_WARN_ON(1);
return 1;
}
@@ -1065,10 +1453,8 @@
pud = READ_ONCE(*pudp);
- if (!pud_present(pud))
- return 1;
if (!pud_table(pud)) {
- VM_WARN_ON(!pud_table(pud));
+ VM_WARN_ON(1);
return 1;
}
@@ -1085,3 +1471,199 @@
pmd_free(NULL, table);
return 1;
}
+
+int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
+{
+ return 0; /* Don't attempt a block mapping */
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
+{
+ unsigned long end = start + size;
+
+ WARN_ON(pgdir != init_mm.pgd);
+ WARN_ON((start < PAGE_OFFSET) || (end > PAGE_END));
+
+ unmap_hotplug_range(start, end, false, NULL);
+ free_empty_tables(start, end, PAGE_OFFSET, PAGE_END);
+}
+
+static bool inside_linear_region(u64 start, u64 size)
+{
+ u64 start_linear_pa = __pa(_PAGE_OFFSET(vabits_actual));
+ u64 end_linear_pa = __pa(PAGE_END - 1);
+
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+ /*
+ * Check for a wrap, it is possible because of randomized linear
+ * mapping the start physical address is actually bigger than
+ * the end physical address. In this case set start to zero
+ * because [0, end_linear_pa] range must still be able to cover
+ * all addressable physical addresses.
+ */
+ if (start_linear_pa > end_linear_pa)
+ start_linear_pa = 0;
+ }
+
+ WARN_ON(start_linear_pa > end_linear_pa);
+
+ /*
+ * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)]
+ * accommodating both its ends but excluding PAGE_END. Max physical
+ * range which can be mapped inside this linear mapping range, must
+ * also be derived from its end points.
+ */
+ return start >= start_linear_pa && (start + size - 1) <= end_linear_pa;
+}
+
+int arch_add_memory(int nid, u64 start, u64 size,
+ struct mhp_params *params)
+{
+ int ret, flags = 0;
+
+ if (!inside_linear_region(start, size)) {
+ pr_err("[%llx %llx] is outside linear mapping region\n", start, start + size);
+ return -EINVAL;
+ }
+
+ /*
+ * KFENCE requires linear map to be mapped at page granularity, so that
+ * it is possible to protect/unprotect single pages in the KFENCE pool.
+ */
+ if (rodata_full || debug_pagealloc_enabled() ||
+ IS_ENABLED(CONFIG_KFENCE))
+ flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+
+ __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
+ size, params->pgprot, __pgd_pgtable_alloc,
+ flags);
+
+ memblock_clear_nomap(start, size);
+
+ ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
+ params);
+ if (ret)
+ __remove_pgd_mapping(swapper_pg_dir,
+ __phys_to_virt(start), size);
+ else {
+ max_pfn = PFN_UP(start + size);
+ max_low_pfn = max_pfn;
+ }
+
+ return ret;
+}
+
+void 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;
+
+ __remove_pages(start_pfn, nr_pages, altmap);
+ __remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size);
+}
+
+int check_range_driver_managed(u64 start, u64 size, const char *resource_name)
+{
+ struct mem_section *ms;
+ unsigned long pfn = __phys_to_pfn(start);
+ unsigned long end_pfn = __phys_to_pfn(start + size);
+ struct resource *res;
+ unsigned long flags;
+
+ res = lookup_resource(&iomem_resource, start);
+ if (!res) {
+ pr_err("%s: couldn't find memory resource for start 0x%llx\n",
+ __func__, start);
+ return -EINVAL;
+ }
+
+ flags = res->flags;
+
+ if (!(flags & IORESOURCE_SYSRAM_DRIVER_MANAGED) ||
+ strstr(resource_name, "System RAM (") != resource_name)
+ return -EINVAL;
+
+ for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+ ms = __pfn_to_section(pfn);
+ if (early_section(ms))
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+int populate_range_driver_managed(u64 start, u64 size,
+ const char *resource_name)
+{
+ unsigned long virt = (unsigned long)phys_to_virt(start);
+ int flags = 0;
+
+ if (check_range_driver_managed(start, size, resource_name))
+ return -EINVAL;
+
+ /*
+ * When rodata_full is enabled, memory is mapped at page size granule,
+ * as opposed to block mapping.
+ */
+ if (rodata_full || debug_pagealloc_enabled())
+ flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+
+ __create_pgd_mapping(init_mm.pgd, start, virt, size,
+ PAGE_KERNEL, NULL, flags);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(populate_range_driver_managed);
+
+int depopulate_range_driver_managed(u64 start, u64 size,
+ const char *resource_name)
+{
+ if (check_range_driver_managed(start, size, resource_name))
+ return -EINVAL;
+
+ unmap_hotplug_range(start, start + size, false, NULL);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(depopulate_range_driver_managed);
+
+/*
+ * This memory hotplug notifier helps prevent boot memory from being
+ * inadvertently removed as it blocks pfn range offlining process in
+ * __offline_pages(). Hence this prevents both offlining as well as
+ * removal process for boot memory which is initially always online.
+ * In future if and when boot memory could be removed, this notifier
+ * should be dropped and free_hotplug_page_range() should handle any
+ * reserved pages allocated during boot.
+ */
+static int prevent_bootmem_remove_notifier(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ struct mem_section *ms;
+ struct memory_notify *arg = data;
+ unsigned long end_pfn = arg->start_pfn + arg->nr_pages;
+ unsigned long pfn = arg->start_pfn;
+
+ if (action != MEM_GOING_OFFLINE)
+ return NOTIFY_OK;
+
+ for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+ ms = __pfn_to_section(pfn);
+ if (early_section(ms))
+ return NOTIFY_BAD;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block prevent_bootmem_remove_nb = {
+ .notifier_call = prevent_bootmem_remove_notifier,
+};
+
+static int __init prevent_bootmem_remove_init(void)
+{
+ return register_memory_notifier(&prevent_bootmem_remove_nb);
+}
+device_initcall(prevent_bootmem_remove_init);
+#endif
--
Gitblit v1.6.2