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/init.c | 413 +++++++++++++++++++++++++---------------------------------
1 files changed, 178 insertions(+), 235 deletions(-)
diff --git a/kernel/arch/arm64/mm/init.c b/kernel/arch/arm64/mm/init.c
index 65efa46..82cdb35 100644
--- a/kernel/arch/arm64/mm/init.c
+++ b/kernel/arch/arm64/mm/init.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Based on arch/arm/mm/init.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/kernel.h>
@@ -22,7 +11,6 @@
#include <linux/errno.h>
#include <linux/swap.h>
#include <linux/init.h>
-#include <linux/bootmem.h>
#include <linux/cache.h>
#include <linux/mman.h>
#include <linux/nodemask.h>
@@ -32,28 +20,30 @@
#include <linux/sort.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
#include <linux/efi.h>
#include <linux/swiotlb.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/kexec.h>
#include <linux/crash_dump.h>
+#include <linux/hugetlb.h>
+#include <linux/acpi_iort.h>
+#include <linux/rk-dma-heap.h>
#include <asm/boot.h>
#include <asm/fixmap.h>
#include <asm/kasan.h>
#include <asm/kernel-pgtable.h>
+#include <asm/kvm_host.h>
#include <asm/memory.h>
#include <asm/numa.h>
#include <asm/sections.h>
#include <asm/setup.h>
-#include <asm/sizes.h>
+#include <linux/sizes.h>
#include <asm/tlb.h>
#include <asm/alternative.h>
-
-EXPORT_SYMBOL_GPL(kimage_vaddr);
/*
* We need to be able to catch inadvertent references to memstart_addr
@@ -62,25 +52,48 @@
* that cannot be mistaken for a real physical address.
*/
s64 memstart_addr __ro_after_init = -1;
-phys_addr_t arm64_dma_phys_limit __ro_after_init;
+EXPORT_SYMBOL(memstart_addr);
-#ifdef CONFIG_BLK_DEV_INITRD
-static int __init early_initrd(char *p)
-{
- unsigned long start, size;
- char *endp;
-
- start = memparse(p, &endp);
- if (*endp == ',') {
- size = memparse(endp + 1, NULL);
-
- initrd_start = start;
- initrd_end = start + size;
- }
- return 0;
-}
-early_param("initrd", early_initrd);
+/*
+ * If the corresponding config options are enabled, we create both ZONE_DMA
+ * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory
+ * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
+ * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
+ * otherwise it is empty.
+ *
+ * Memory reservation for crash kernel either done early or deferred
+ * depending on DMA memory zones configs (ZONE_DMA) --
+ *
+ * In absence of ZONE_DMA configs arm64_dma_phys_limit initialized
+ * here instead of max_zone_phys(). This lets early reservation of
+ * crash kernel memory which has a dependency on arm64_dma_phys_limit.
+ * Reserving memory early for crash kernel allows linear creation of block
+ * mappings (greater than page-granularity) for all the memory bank rangs.
+ * In this scheme a comparatively quicker boot is observed.
+ *
+ * If ZONE_DMA configs are defined, crash kernel memory reservation
+ * is delayed until DMA zone memory range size initilazation performed in
+ * zone_sizes_init(). The defer is necessary to steer clear of DMA zone
+ * memory range to avoid overlap allocation. So crash kernel memory boundaries
+ * are not known when mapping all bank memory ranges, which otherwise means
+ * not possible to exclude crash kernel range from creating block mappings
+ * so page-granularity mappings are created for the entire memory range.
+ * Hence a slightly slower boot is observed.
+ *
+ * Note: Page-granularity mapppings are necessary for crash kernel memory
+ * range for shrinking its size via /sys/kernel/kexec_crash_size interface.
+ */
+#if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32)
+phys_addr_t __ro_after_init arm64_dma_phys_limit;
+#else
+phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1;
#endif
+
+/*
+ * Provide a run-time mean of disabling ZONE_DMA32 if it is enabled via
+ * CONFIG_ZONE_DMA32.
+ */
+static bool disable_dma32 __ro_after_init;
#ifdef CONFIG_KEXEC_CORE
/*
@@ -105,7 +118,7 @@
if (crash_base == 0) {
/* Current arm64 boot protocol requires 2MB alignment */
- crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT,
+ crash_base = memblock_find_in_range(0, arm64_dma_phys_limit,
crash_size, SZ_2M);
if (crash_base == 0) {
pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
@@ -137,33 +150,8 @@
crashk_res.start = crash_base;
crashk_res.end = crash_base + crash_size - 1;
}
-
-static void __init kexec_reserve_crashkres_pages(void)
-{
-#ifdef CONFIG_HIBERNATION
- phys_addr_t addr;
- struct page *page;
-
- if (!crashk_res.end)
- return;
-
- /*
- * To reduce the size of hibernation image, all the pages are
- * marked as Reserved initially.
- */
- for (addr = crashk_res.start; addr < (crashk_res.end + 1);
- addr += PAGE_SIZE) {
- page = phys_to_page(addr);
- SetPageReserved(page);
- }
-#endif
-}
#else
static void __init reserve_crashkernel(void)
-{
-}
-
-static void __init kexec_reserve_crashkres_pages(void)
{
}
#endif /* CONFIG_KEXEC_CORE */
@@ -218,104 +206,90 @@
{
}
#endif /* CONFIG_CRASH_DUMP */
-/*
- * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). It
- * currently assumes that for memory starting above 4G, 32-bit devices will
- * use a DMA offset.
- */
-static phys_addr_t __init max_zone_dma_phys(void)
-{
- phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32);
- return min(offset + (1ULL << 32), memblock_end_of_DRAM());
-}
-#ifdef CONFIG_NUMA
+/*
+ * Return the maximum physical address for a zone accessible by the given bits
+ * limit. If DRAM starts above 32-bit, expand the zone to the maximum
+ * available memory, otherwise cap it at 32-bit.
+ */
+static phys_addr_t __init max_zone_phys(unsigned int zone_bits)
+{
+ phys_addr_t zone_mask = DMA_BIT_MASK(zone_bits);
+ phys_addr_t phys_start = memblock_start_of_DRAM();
+
+ if (phys_start > U32_MAX)
+ zone_mask = PHYS_ADDR_MAX;
+ else if (phys_start > zone_mask)
+ zone_mask = U32_MAX;
+
+ return min(zone_mask, memblock_end_of_DRAM() - 1) + 1;
+}
static void __init zone_sizes_init(unsigned long min, unsigned long max)
{
unsigned long max_zone_pfns[MAX_NR_ZONES] = {0};
+ unsigned int __maybe_unused acpi_zone_dma_bits;
+ unsigned int __maybe_unused dt_zone_dma_bits;
+ phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32);
+#ifdef CONFIG_ZONE_DMA
+ acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address());
+ dt_zone_dma_bits = fls64(of_dma_get_max_cpu_address(NULL));
+ zone_dma_bits = min3(32U, dt_zone_dma_bits, acpi_zone_dma_bits);
+ arm64_dma_phys_limit = max_zone_phys(zone_dma_bits);
+ max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
+#endif
#ifdef CONFIG_ZONE_DMA32
- max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys());
+ max_zone_pfns[ZONE_DMA32] = disable_dma32 ? 0 : PFN_DOWN(dma32_phys_limit);
+ if (!arm64_dma_phys_limit)
+ arm64_dma_phys_limit = dma32_phys_limit;
#endif
max_zone_pfns[ZONE_NORMAL] = max;
- free_area_init_nodes(max_zone_pfns);
+ free_area_init(max_zone_pfns);
}
-#else
-
-static void __init zone_sizes_init(unsigned long min, unsigned long max)
+static int __init early_disable_dma32(char *buf)
{
- struct memblock_region *reg;
- unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
- unsigned long max_dma = min;
+ if (!buf)
+ return -EINVAL;
- memset(zone_size, 0, sizeof(zone_size));
+ if (!strcmp(buf, "on"))
+ disable_dma32 = true;
- /* 4GB maximum for 32-bit only capable devices */
-#ifdef CONFIG_ZONE_DMA32
- max_dma = PFN_DOWN(arm64_dma_phys_limit);
- zone_size[ZONE_DMA32] = max_dma - min;
-#endif
- zone_size[ZONE_NORMAL] = max - max_dma;
-
- memcpy(zhole_size, zone_size, sizeof(zhole_size));
-
- for_each_memblock(memory, reg) {
- unsigned long start = memblock_region_memory_base_pfn(reg);
- unsigned long end = memblock_region_memory_end_pfn(reg);
-
- if (start >= max)
- continue;
-
-#ifdef CONFIG_ZONE_DMA32
- if (start < max_dma) {
- unsigned long dma_end = min(end, max_dma);
- zhole_size[ZONE_DMA32] -= dma_end - start;
- }
-#endif
- if (end > max_dma) {
- unsigned long normal_end = min(end, max);
- unsigned long normal_start = max(start, max_dma);
- zhole_size[ZONE_NORMAL] -= normal_end - normal_start;
- }
- }
-
- free_area_init_node(0, zone_size, min, zhole_size);
+ return 0;
}
+early_param("disable_dma32", early_disable_dma32);
-#endif /* CONFIG_NUMA */
-
-#ifdef CONFIG_HAVE_ARCH_PFN_VALID
int pfn_valid(unsigned long pfn)
{
phys_addr_t addr = pfn << PAGE_SHIFT;
if ((addr >> PAGE_SHIFT) != pfn)
return 0;
+
+#ifdef CONFIG_SPARSEMEM
+ if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
+ return 0;
+
+ if (!valid_section(__pfn_to_section(pfn)))
+ return 0;
+
+ /*
+ * ZONE_DEVICE memory does not have the memblock entries.
+ * memblock_is_map_memory() check for ZONE_DEVICE based
+ * addresses will always fail. Even the normal hotplugged
+ * memory will never have MEMBLOCK_NOMAP flag set in their
+ * memblock entries. Skip memblock search for all non early
+ * memory sections covering all of hotplug memory including
+ * both normal and ZONE_DEVICE based.
+ */
+ if (!early_section(__pfn_to_section(pfn)))
+ return pfn_section_valid(__pfn_to_section(pfn), pfn);
+#endif
return memblock_is_map_memory(addr);
}
EXPORT_SYMBOL(pfn_valid);
-#endif
-
-#ifndef CONFIG_SPARSEMEM
-static void __init arm64_memory_present(void)
-{
-}
-#else
-static void __init arm64_memory_present(void)
-{
- struct memblock_region *reg;
-
- for_each_memblock(memory, reg) {
- int nid = memblock_get_region_node(reg);
-
- memory_present(nid, memblock_region_memory_base_pfn(reg),
- memblock_region_memory_end_pfn(reg));
- }
-}
-#endif
static phys_addr_t memory_limit = PHYS_ADDR_MAX;
@@ -368,20 +342,13 @@
void __init arm64_memblock_init(void)
{
- const s64 linear_region_size = -(s64)PAGE_OFFSET;
+ const s64 linear_region_size = BIT(vabits_actual - 1);
/* Handle linux,usable-memory-range property */
fdt_enforce_memory_region();
/* Remove memory above our supported physical address size */
memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX);
-
- /*
- * Ensure that the linear region takes up exactly half of the kernel
- * virtual address space. This way, we can distinguish a linear address
- * from a kernel/module/vmalloc address by testing a single bit.
- */
- BUILD_BUG_ON(linear_region_size != BIT(VA_BITS - 1));
/*
* Select a suitable value for the base of physical memory.
@@ -404,6 +371,16 @@
}
/*
+ * If we are running with a 52-bit kernel VA config on a system that
+ * does not support it, we have to place the available physical
+ * memory in the 48-bit addressable part of the linear region, i.e.,
+ * we have to move it upward. Since memstart_addr represents the
+ * physical address of PAGE_OFFSET, we have to *subtract* from it.
+ */
+ if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52))
+ memstart_addr -= _PAGE_OFFSET(48) - _PAGE_OFFSET(52);
+
+ /*
* Apply the memory limit if it was set. Since the kernel may be loaded
* high up in memory, add back the kernel region that must be accessible
* via the linear mapping.
@@ -413,14 +390,14 @@
memblock_add(__pa_symbol(_text), (u64)(_end - _text));
}
- if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && initrd_start) {
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) {
/*
* Add back the memory we just removed if it results in the
* initrd to become inaccessible via the linear mapping.
* Otherwise, this is a no-op
*/
- u64 base = initrd_start & PAGE_MASK;
- u64 size = PAGE_ALIGN(initrd_end) - base;
+ u64 base = phys_initrd_start & PAGE_MASK;
+ u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base;
/*
* We can only add back the initrd memory if we don't end up
@@ -434,7 +411,7 @@
base + size > memblock_start_of_DRAM() +
linear_region_size,
"initrd not fully accessible via the linear mapping -- please check your bootloader ...\n")) {
- initrd_start = 0;
+ phys_initrd_size = 0;
} else {
memblock_remove(base, size); /* clear MEMBLOCK_ flags */
memblock_add(base, size);
@@ -444,15 +421,18 @@
if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
extern u16 memstart_offset_seed;
- u64 range = linear_region_size -
- (memblock_end_of_DRAM() - memblock_start_of_DRAM());
+ u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
+ int parange = cpuid_feature_extract_unsigned_field(
+ mmfr0, ID_AA64MMFR0_PARANGE_SHIFT);
+ s64 range = linear_region_size -
+ BIT(id_aa64mmfr0_parange_to_phys_shift(parange));
/*
* If the size of the linear region exceeds, by a sufficient
- * margin, the size of the region that the available physical
- * memory spans, randomize the linear region as well.
+ * margin, the size of the region that the physical memory can
+ * span, randomize the linear region as well.
*/
- if (memstart_offset_seed > 0 && range >= ARM64_MEMSTART_ALIGN) {
+ if (memstart_offset_seed > 0 && range >= (s64)ARM64_MEMSTART_ALIGN) {
range /= ARM64_MEMSTART_ALIGN;
memstart_addr -= ARM64_MEMSTART_ALIGN *
((range * memstart_offset_seed) >> 16);
@@ -464,33 +444,20 @@
* pagetables with memblock.
*/
memblock_reserve(__pa_symbol(_text), _end - _text);
-#ifdef CONFIG_BLK_DEV_INITRD
- if (initrd_start) {
- memblock_reserve(initrd_start, initrd_end - initrd_start);
-
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) {
/* the generic initrd code expects virtual addresses */
- initrd_start = __phys_to_virt(initrd_start);
- initrd_end = __phys_to_virt(initrd_end);
+ initrd_start = __phys_to_virt(phys_initrd_start);
+ initrd_end = initrd_start + phys_initrd_size;
}
-#endif
early_init_fdt_scan_reserved_mem();
- /* 4GB maximum for 32-bit only capable devices */
- if (IS_ENABLED(CONFIG_ZONE_DMA32))
- arm64_dma_phys_limit = max_zone_dma_phys();
- else
- arm64_dma_phys_limit = PHYS_MASK + 1;
-
- reserve_crashkernel();
-
reserve_elfcorehdr();
+ if (!IS_ENABLED(CONFIG_ZONE_DMA) && !IS_ENABLED(CONFIG_ZONE_DMA32))
+ reserve_crashkernel();
+
high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
-
- dma_contiguous_reserve(arm64_dma_phys_limit);
-
- memblock_allow_resize();
}
void __init bootmem_init(void)
@@ -503,16 +470,42 @@
early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);
max_pfn = max_low_pfn = max;
+ min_low_pfn = min;
arm64_numa_init();
- /*
- * Sparsemem tries to allocate bootmem in memory_present(), so must be
- * done after the fixed reservations.
- */
- arm64_memory_present();
+ /*
+ * must be done after arm64_numa_init() which calls numa_init() to
+ * initialize node_online_map that gets used in hugetlb_cma_reserve()
+ * while allocating required CMA size across online nodes.
+ */
+#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA)
+ arm64_hugetlb_cma_reserve();
+#endif
+
+ dma_pernuma_cma_reserve();
+
+ kvm_hyp_reserve();
+
+ /*
+ * sparse_init() tries to allocate memory from memblock, so must be
+ * done after the fixed reservations
+ */
sparse_init();
zone_sizes_init(min, max);
+
+ /*
+ * Reserve the CMA area after arm64_dma_phys_limit was initialised.
+ */
+ dma_contiguous_reserve(arm64_dma_phys_limit);
+ rk_dma_heap_cma_setup();
+
+ /*
+ * request_standard_resources() depends on crashkernel's memory being
+ * reserved, so do it here.
+ */
+ if (IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32))
+ reserve_crashkernel();
memblock_dump_all();
}
@@ -541,7 +534,7 @@
* memmap array.
*/
if (pg < pgend)
- free_bootmem(pg, pgend - pg);
+ memblock_free(pg, pgend - pg);
}
/*
@@ -549,12 +542,10 @@
*/
static void __init free_unused_memmap(void)
{
- unsigned long start, prev_end = 0;
- struct memblock_region *reg;
+ unsigned long start, end, prev_end = 0;
+ int i;
- for_each_memblock(memory, reg) {
- start = __phys_to_pfn(reg->base);
-
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) {
#ifdef CONFIG_SPARSEMEM
/*
* Take care not to free memmap entries that don't exist due
@@ -574,8 +565,7 @@
* memmap entries are valid from the bank end aligned to
* MAX_ORDER_NR_PAGES.
*/
- prev_end = ALIGN(__phys_to_pfn(reg->base + reg->size),
- MAX_ORDER_NR_PAGES);
+ prev_end = ALIGN(end, MAX_ORDER_NR_PAGES);
}
#ifdef CONFIG_SPARSEMEM
@@ -593,20 +583,18 @@
void __init mem_init(void)
{
if (swiotlb_force == SWIOTLB_FORCE ||
- max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+ max_pfn > PFN_DOWN(arm64_dma_phys_limit))
swiotlb_init(1);
else
swiotlb_force = SWIOTLB_NO_FORCE;
- set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
+ set_max_mapnr(max_pfn - PHYS_PFN_OFFSET);
#ifndef CONFIG_SPARSEMEM_VMEMMAP
free_unused_memmap();
#endif
/* this will put all unused low memory onto the freelists */
- free_all_bootmem();
-
- kexec_reserve_crashkres_pages();
+ memblock_free_all();
mem_init_print_info(NULL);
@@ -615,15 +603,7 @@
* detected at build time already.
*/
#ifdef CONFIG_COMPAT
- BUILD_BUG_ON(TASK_SIZE_32 > TASK_SIZE_64);
-#endif
-
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
- /*
- * Make sure we chose the upper bound of sizeof(struct page)
- * correctly when sizing the VMEMMAP array.
- */
- BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT));
+ BUILD_BUG_ON(TASK_SIZE_32 > DEFAULT_MAP_WINDOW_64);
#endif
if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) {
@@ -640,7 +620,7 @@
{
free_reserved_area(lm_alias(__init_begin),
lm_alias(__init_end),
- 0, "unused kernel");
+ POISON_FREE_INITMEM, "unused kernel");
/*
* Unmap the __init region but leave the VM area in place. This
* prevents the region from being reused for kernel modules, which
@@ -649,48 +629,11 @@
unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
}
-#ifdef CONFIG_BLK_DEV_INITRD
-
-static int keep_initrd __initdata;
-
-void __init free_initrd_mem(unsigned long start, unsigned long end)
-{
- if (!keep_initrd) {
- free_reserved_area((void *)start, (void *)end, 0, "initrd");
- memblock_free(__virt_to_phys(start), end - start);
- }
-}
-
-static int __init keepinitrd_setup(char *__unused)
-{
- keep_initrd = 1;
- return 1;
-}
-
-__setup("keepinitrd", keepinitrd_setup);
-#endif
-
-/*
- * Dump out memory limit information on panic.
- */
-static int dump_mem_limit(struct notifier_block *self, unsigned long v, void *p)
+void dump_mem_limit(void)
{
if (memory_limit != PHYS_ADDR_MAX) {
pr_emerg("Memory Limit: %llu MB\n", memory_limit >> 20);
} else {
pr_emerg("Memory Limit: none\n");
}
- return 0;
}
-
-static struct notifier_block mem_limit_notifier = {
- .notifier_call = dump_mem_limit,
-};
-
-static int __init register_mem_limit_dumper(void)
-{
- atomic_notifier_chain_register(&panic_notifier_list,
- &mem_limit_notifier);
- return 0;
-}
-__initcall(register_mem_limit_dumper);
--
Gitblit v1.6.2