aboutsummaryrefslogtreecommitdiff
path: root/arch/arm64/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64/mm')
-rw-r--r--arch/arm64/mm/Makefile2
-rw-r--r--arch/arm64/mm/dma-mapping.c164
-rw-r--r--arch/arm64/mm/init.c22
-rw-r--r--arch/arm64/mm/ioremap.c26
-rw-r--r--arch/arm64/mm/pageattr.c96
-rw-r--r--arch/arm64/mm/proc.S15
6 files changed, 293 insertions, 32 deletions
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 3ecb56c624d3..c56179ed2c09 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -1,5 +1,5 @@
obj-y := dma-mapping.o extable.o fault.o init.o \
cache.o copypage.o flush.o \
ioremap.o mmap.o pgd.o mmu.o \
- context.o proc.o
+ context.o proc.o pageattr.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index f39a55d58918..eeb1cf3ff299 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -20,6 +20,7 @@
#include <linux/gfp.h>
#include <linux/export.h>
#include <linux/slab.h>
+#include <linux/genalloc.h>
#include <linux/dma-mapping.h>
#include <linux/dma-contiguous.h>
#include <linux/of.h>
@@ -43,6 +44,54 @@ static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
return prot;
}
+static struct gen_pool *atomic_pool;
+
+#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K
+static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE;
+
+static int __init early_coherent_pool(char *p)
+{
+ atomic_pool_size = memparse(p, &p);
+ return 0;
+}
+early_param("coherent_pool", early_coherent_pool);
+
+static void *__alloc_from_pool(size_t size, struct page **ret_page)
+{
+ unsigned long val;
+ void *ptr = NULL;
+
+ if (!atomic_pool) {
+ WARN(1, "coherent pool not initialised!\n");
+ return NULL;
+ }
+
+ val = gen_pool_alloc(atomic_pool, size);
+ if (val) {
+ phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);
+
+ *ret_page = phys_to_page(phys);
+ ptr = (void *)val;
+ }
+
+ return ptr;
+}
+
+static bool __in_atomic_pool(void *start, size_t size)
+{
+ return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
+}
+
+static int __free_from_pool(void *start, size_t size)
+{
+ if (!__in_atomic_pool(start, size))
+ return 0;
+
+ gen_pool_free(atomic_pool, (unsigned long)start, size);
+
+ return 1;
+}
+
static void *__dma_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t flags,
struct dma_attrs *attrs)
@@ -50,7 +99,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
if (IS_ENABLED(CONFIG_ZONE_DMA) &&
dev->coherent_dma_mask <= DMA_BIT_MASK(32))
flags |= GFP_DMA;
- if (IS_ENABLED(CONFIG_DMA_CMA)) {
+ if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) {
struct page *page;
size = PAGE_ALIGN(size);
@@ -70,50 +119,54 @@ static void __dma_free_coherent(struct device *dev, size_t size,
void *vaddr, dma_addr_t dma_handle,
struct dma_attrs *attrs)
{
+ bool freed;
+ phys_addr_t paddr = dma_to_phys(dev, dma_handle);
+
if (dev == NULL) {
WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
return;
}
- if (IS_ENABLED(CONFIG_DMA_CMA)) {
- phys_addr_t paddr = dma_to_phys(dev, dma_handle);
-
- dma_release_from_contiguous(dev,
+ freed = dma_release_from_contiguous(dev,
phys_to_page(paddr),
size >> PAGE_SHIFT);
- } else {
+ if (!freed)
swiotlb_free_coherent(dev, size, vaddr, dma_handle);
- }
}
static void *__dma_alloc_noncoherent(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t flags,
struct dma_attrs *attrs)
{
- struct page *page, **map;
+ struct page *page;
void *ptr, *coherent_ptr;
- int order, i;
size = PAGE_ALIGN(size);
- order = get_order(size);
+
+ if (!(flags & __GFP_WAIT)) {
+ struct page *page = NULL;
+ void *addr = __alloc_from_pool(size, &page);
+
+ if (addr)
+ *dma_handle = phys_to_dma(dev, page_to_phys(page));
+
+ return addr;
+
+ }
ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs);
if (!ptr)
goto no_mem;
- map = kmalloc(sizeof(struct page *) << order, flags & ~GFP_DMA);
- if (!map)
- goto no_map;
/* remove any dirty cache lines on the kernel alias */
__dma_flush_range(ptr, ptr + size);
/* create a coherent mapping */
page = virt_to_page(ptr);
- for (i = 0; i < (size >> PAGE_SHIFT); i++)
- map[i] = page + i;
- coherent_ptr = vmap(map, size >> PAGE_SHIFT, VM_MAP,
- __get_dma_pgprot(attrs, __pgprot(PROT_NORMAL_NC), false));
- kfree(map);
+ coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP,
+ __get_dma_pgprot(attrs,
+ __pgprot(PROT_NORMAL_NC), false),
+ NULL);
if (!coherent_ptr)
goto no_map;
@@ -132,6 +185,8 @@ static void __dma_free_noncoherent(struct device *dev, size_t size,
{
void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));
+ if (__free_from_pool(vaddr, size))
+ return;
vunmap(vaddr);
__dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs);
}
@@ -329,6 +384,67 @@ static struct notifier_block amba_bus_nb = {
extern int swiotlb_late_init_with_default_size(size_t default_size);
+static int __init atomic_pool_init(void)
+{
+ pgprot_t prot = __pgprot(PROT_NORMAL_NC);
+ unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT;
+ struct page *page;
+ void *addr;
+ unsigned int pool_size_order = get_order(atomic_pool_size);
+
+ if (dev_get_cma_area(NULL))
+ page = dma_alloc_from_contiguous(NULL, nr_pages,
+ pool_size_order);
+ else
+ page = alloc_pages(GFP_DMA, pool_size_order);
+
+ if (page) {
+ int ret;
+ void *page_addr = page_address(page);
+
+ memset(page_addr, 0, atomic_pool_size);
+ __dma_flush_range(page_addr, page_addr + atomic_pool_size);
+
+ atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
+ if (!atomic_pool)
+ goto free_page;
+
+ addr = dma_common_contiguous_remap(page, atomic_pool_size,
+ VM_USERMAP, prot, atomic_pool_init);
+
+ if (!addr)
+ goto destroy_genpool;
+
+ ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr,
+ page_to_phys(page),
+ atomic_pool_size, -1);
+ if (ret)
+ goto remove_mapping;
+
+ gen_pool_set_algo(atomic_pool,
+ gen_pool_first_fit_order_align,
+ (void *)PAGE_SHIFT);
+
+ pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
+ atomic_pool_size / 1024);
+ return 0;
+ }
+ goto out;
+
+remove_mapping:
+ dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP);
+destroy_genpool:
+ gen_pool_destroy(atomic_pool);
+ atomic_pool = NULL;
+free_page:
+ if (!dma_release_from_contiguous(NULL, page, nr_pages))
+ __free_pages(page, pool_size_order);
+out:
+ pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n",
+ atomic_pool_size / 1024);
+ return -ENOMEM;
+}
+
static int __init swiotlb_late_init(void)
{
size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT);
@@ -343,7 +459,17 @@ static int __init swiotlb_late_init(void)
return swiotlb_late_init_with_default_size(swiotlb_size);
}
-arch_initcall(swiotlb_late_init);
+
+static int __init arm64_dma_init(void)
+{
+ int ret = 0;
+
+ ret |= swiotlb_late_init();
+ ret |= atomic_pool_init();
+
+ return ret;
+}
+arch_initcall(arm64_dma_init);
#define PREALLOC_DMA_DEBUG_ENTRIES 4096
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 81bdd29df3a4..d0f86b74fce6 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -68,6 +68,17 @@ static int __init early_initrd(char *p)
}
early_param("initrd", early_initrd);
+/*
+ * Return the maximum physical address for ZONE_DMA (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 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());
+}
+
static void __init zone_sizes_init(unsigned long min, unsigned long max)
{
struct memblock_region *reg;
@@ -78,9 +89,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
/* 4GB maximum for 32-bit only capable devices */
if (IS_ENABLED(CONFIG_ZONE_DMA)) {
- unsigned long max_dma_phys =
- (unsigned long)dma_to_phys(NULL, DMA_BIT_MASK(32) + 1);
- max_dma = max(min, min(max, max_dma_phys >> PAGE_SHIFT));
+ max_dma = PFN_DOWN(max_zone_dma_phys());
zone_size[ZONE_DMA] = max_dma - min;
}
zone_size[ZONE_NORMAL] = max - max_dma;
@@ -135,6 +144,7 @@ static void arm64_memory_present(void)
void __init arm64_memblock_init(void)
{
u64 *reserve_map, base, size;
+ phys_addr_t dma_phys_limit = 0;
/*
* Register the kernel text, kernel data, initrd, and initial
@@ -171,7 +181,11 @@ void __init arm64_memblock_init(void)
}
early_init_fdt_scan_reserved_mem();
- dma_contiguous_reserve(0);
+
+ /* 4GB maximum for 32-bit only capable devices */
+ if (IS_ENABLED(CONFIG_ZONE_DMA))
+ dma_phys_limit = max_zone_dma_phys();
+ dma_contiguous_reserve(dma_phys_limit);
memblock_allow_resize();
memblock_dump_all();
diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c
index 00d315ae1de9..cf25fa9aa68f 100644
--- a/arch/arm64/mm/ioremap.c
+++ b/arch/arm64/mm/ioremap.c
@@ -98,19 +98,25 @@ void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size)
}
EXPORT_SYMBOL(ioremap_cache);
-#ifndef CONFIG_ARM64_64K_PAGES
static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss;
+#ifndef CONFIG_ARM64_64K_PAGES
+static pte_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss;
#endif
-static inline pmd_t * __init early_ioremap_pmd(unsigned long addr)
+static inline pud_t * __init early_ioremap_pud(unsigned long addr)
{
pgd_t *pgd;
- pud_t *pud;
pgd = pgd_offset_k(addr);
BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd));
- pud = pud_offset(pgd, addr);
+ return pud_offset(pgd, addr);
+}
+
+static inline pmd_t * __init early_ioremap_pmd(unsigned long addr)
+{
+ pud_t *pud = early_ioremap_pud(addr);
+
BUG_ON(pud_none(*pud) || pud_bad(*pud));
return pmd_offset(pud, addr);
@@ -127,13 +133,17 @@ static inline pte_t * __init early_ioremap_pte(unsigned long addr)
void __init early_ioremap_init(void)
{
+ pgd_t *pgd;
+ pud_t *pud;
pmd_t *pmd;
+ unsigned long addr = fix_to_virt(FIX_BTMAP_BEGIN);
- pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN));
-#ifndef CONFIG_ARM64_64K_PAGES
- /* need to populate pmd for 4k pagesize only */
+ pgd = pgd_offset_k(addr);
+ pud = pud_offset(pgd, addr);
+ pud_populate(&init_mm, pud, bm_pmd);
+ pmd = pmd_offset(pud, addr);
pmd_populate_kernel(&init_mm, pmd, bm_pte);
-#endif
+
/*
* The boot-ioremap range spans multiple pmds, for which
* we are not prepared:
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
new file mode 100644
index 000000000000..75e744e4cec5
--- /dev/null
+++ b/arch/arm64/mm/pageattr.c
@@ -0,0 +1,96 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only 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.
+ */
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+
+struct page_change_data {
+ pgprot_t set_mask;
+ pgprot_t clear_mask;
+};
+
+static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr,
+ void *data)
+{
+ struct page_change_data *cdata = data;
+ pte_t pte = *ptep;
+
+ pte = clear_pte_bit(pte, cdata->clear_mask);
+ pte = set_pte_bit(pte, cdata->set_mask);
+
+ set_pte(ptep, pte);
+ return 0;
+}
+
+static int change_memory_common(unsigned long addr, int numpages,
+ pgprot_t set_mask, pgprot_t clear_mask)
+{
+ unsigned long start = addr;
+ unsigned long size = PAGE_SIZE*numpages;
+ unsigned long end = start + size;
+ int ret;
+ struct page_change_data data;
+
+ if (!IS_ALIGNED(addr, PAGE_SIZE)) {
+ addr &= PAGE_MASK;
+ WARN_ON_ONCE(1);
+ }
+
+ if (!is_module_address(start) || !is_module_address(end - 1))
+ return -EINVAL;
+
+ data.set_mask = set_mask;
+ data.clear_mask = clear_mask;
+
+ ret = apply_to_page_range(&init_mm, start, size, change_page_range,
+ &data);
+
+ flush_tlb_kernel_range(start, end);
+ return ret;
+}
+
+int set_memory_ro(unsigned long addr, int numpages)
+{
+ return change_memory_common(addr, numpages,
+ __pgprot(PTE_RDONLY),
+ __pgprot(PTE_WRITE));
+}
+EXPORT_SYMBOL_GPL(set_memory_ro);
+
+int set_memory_rw(unsigned long addr, int numpages)
+{
+ return change_memory_common(addr, numpages,
+ __pgprot(PTE_WRITE),
+ __pgprot(PTE_RDONLY));
+}
+EXPORT_SYMBOL_GPL(set_memory_rw);
+
+int set_memory_nx(unsigned long addr, int numpages)
+{
+ return change_memory_common(addr, numpages,
+ __pgprot(PTE_PXN),
+ __pgprot(0));
+}
+EXPORT_SYMBOL_GPL(set_memory_nx);
+
+int set_memory_x(unsigned long addr, int numpages)
+{
+ return change_memory_common(addr, numpages,
+ __pgprot(0),
+ __pgprot(PTE_PXN));
+}
+EXPORT_SYMBOL_GPL(set_memory_x);
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index c3c7b8f83b55..c133ae53ed86 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -69,6 +69,21 @@ ENTRY(cpu_reset)
ret x0
ENDPROC(cpu_reset)
+ENTRY(cpu_soft_restart)
+ /* Save address of cpu_reset() and reset address */
+ mov x19, x0
+ mov x20, x1
+
+ /* Turn D-cache off */
+ bl cpu_cache_off
+
+ /* Push out all dirty data, and ensure cache is empty */
+ bl flush_cache_all
+
+ mov x0, x20
+ ret x19
+ENDPROC(cpu_soft_restart)
+
/*
* cpu_do_idle()
*
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-25 08:37:20 +0000