summaryrefslogtreecommitdiffstats
path: root/arch/arm/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm/mm')
-rw-r--r--arch/arm/mm/Kconfig3
-rw-r--r--arch/arm/mm/alignment.c74
-rw-r--r--arch/arm/mm/cache-aurora-l2.h55
-rw-r--r--arch/arm/mm/cache-l2x0.c18
-rw-r--r--arch/arm/mm/copypage-xscale.c6
-rw-r--r--arch/arm/mm/dma-mapping-nommu.c5
-rw-r--r--arch/arm/mm/dma-mapping.c123
-rw-r--r--arch/arm/mm/fault.c4
-rw-r--r--arch/arm/mm/fault.h1
-rw-r--r--arch/arm/mm/flush.c7
-rw-r--r--arch/arm/mm/init.c13
-rw-r--r--arch/arm/mm/mm.h3
-rw-r--r--arch/arm/mm/mmap.c52
-rw-r--r--arch/arm/mm/mmu.c21
-rw-r--r--arch/arm/mm/proc-v7m.S6
15 files changed, 179 insertions, 212 deletions
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 820b60a50125..0ab3a86b1f52 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -106,7 +106,7 @@ config CPU_ARM922T
help
The ARM922T is a version of the ARM920T, but with smaller
instruction and data caches. It is used in Altera's
- Excalibur XA device family and Micrel's KS8695 Centaur.
+ Excalibur XA device family and the ARM Integrator.
Say Y if you want support for the ARM922T processor.
Otherwise, say N.
@@ -663,6 +663,7 @@ config ARM_LPAE
depends on MMU && CPU_32v7 && !CPU_32v6 && !CPU_32v5 && \
!CPU_32v4 && !CPU_32v3
select PHYS_ADDR_T_64BIT
+ select SWIOTLB
help
Say Y if you have an ARMv7 processor supporting the LPAE page
table format and you would like to access memory beyond the
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 8cdb78642e93..788c5cf46de5 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -324,7 +324,7 @@ union offset_union {
__put32_unaligned_check("strbt", val, addr)
static void
-do_alignment_finish_ldst(unsigned long addr, unsigned long instr, struct pt_regs *regs, union offset_union offset)
+do_alignment_finish_ldst(unsigned long addr, u32 instr, struct pt_regs *regs, union offset_union offset)
{
if (!LDST_U_BIT(instr))
offset.un = -offset.un;
@@ -337,7 +337,7 @@ do_alignment_finish_ldst(unsigned long addr, unsigned long instr, struct pt_regs
}
static int
-do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldrhstrh(unsigned long addr, u32 instr, struct pt_regs *regs)
{
unsigned int rd = RD_BITS(instr);
@@ -386,8 +386,7 @@ do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *r
}
static int
-do_alignment_ldrdstrd(unsigned long addr, unsigned long instr,
- struct pt_regs *regs)
+do_alignment_ldrdstrd(unsigned long addr, u32 instr, struct pt_regs *regs)
{
unsigned int rd = RD_BITS(instr);
unsigned int rd2;
@@ -449,7 +448,7 @@ do_alignment_ldrdstrd(unsigned long addr, unsigned long instr,
}
static int
-do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldrstr(unsigned long addr, u32 instr, struct pt_regs *regs)
{
unsigned int rd = RD_BITS(instr);
@@ -498,7 +497,7 @@ do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *reg
* PU = 10 A B
*/
static int
-do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldmstm(unsigned long addr, u32 instr, struct pt_regs *regs)
{
unsigned int rd, rn, correction, nr_regs, regbits;
unsigned long eaddr, newaddr;
@@ -539,7 +538,7 @@ do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *reg
* processor for us.
*/
if (addr != eaddr) {
- pr_err("LDMSTM: PC = %08lx, instr = %08lx, "
+ pr_err("LDMSTM: PC = %08lx, instr = %08x, "
"addr = %08lx, eaddr = %08lx\n",
instruction_pointer(regs), instr, addr, eaddr);
show_regs(regs);
@@ -695,7 +694,7 @@ thumb2arm(u16 tinstr)
return subset[(L<<1) | ((tinstr & (1<<8)) >> 8)] |
(tinstr & 255); /* register_list */
}
- /* Else fall through for illegal instruction case */
+ /* Else, fall through - for illegal instruction case */
default:
return BAD_INSTR;
@@ -716,10 +715,10 @@ thumb2arm(u16 tinstr)
* 2. Register name Rt from ARMv7 is same as Rd from ARMv6 (Rd is Rt)
*/
static void *
-do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs,
+do_alignment_t32_to_handler(u32 *pinstr, struct pt_regs *regs,
union offset_union *poffset)
{
- unsigned long instr = *pinstr;
+ u32 instr = *pinstr;
u16 tinst1 = (instr >> 16) & 0xffff;
u16 tinst2 = instr & 0xffff;
@@ -751,6 +750,8 @@ do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs,
case 0xe8e0:
case 0xe9e0:
poffset->un = (tinst2 & 0xff) << 2;
+ /* Fall through */
+
case 0xe940:
case 0xe9c0:
return do_alignment_ldrdstrd;
@@ -765,17 +766,48 @@ do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs,
return NULL;
}
+static int alignment_get_arm(struct pt_regs *regs, u32 *ip, u32 *inst)
+{
+ u32 instr = 0;
+ int fault;
+
+ if (user_mode(regs))
+ fault = get_user(instr, ip);
+ else
+ fault = probe_kernel_address(ip, instr);
+
+ *inst = __mem_to_opcode_arm(instr);
+
+ return fault;
+}
+
+static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst)
+{
+ u16 instr = 0;
+ int fault;
+
+ if (user_mode(regs))
+ fault = get_user(instr, ip);
+ else
+ fault = probe_kernel_address(ip, instr);
+
+ *inst = __mem_to_opcode_thumb16(instr);
+
+ return fault;
+}
+
static int
do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
union offset_union uninitialized_var(offset);
- unsigned long instr = 0, instrptr;
- int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs);
+ unsigned long instrptr;
+ int (*handler)(unsigned long addr, u32 instr, struct pt_regs *regs);
unsigned int type;
- unsigned int fault;
+ u32 instr = 0;
u16 tinstr = 0;
int isize = 4;
int thumb2_32b = 0;
+ int fault;
if (interrupts_enabled(regs))
local_irq_enable();
@@ -784,15 +816,14 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
if (thumb_mode(regs)) {
u16 *ptr = (u16 *)(instrptr & ~1);
- fault = probe_kernel_address(ptr, tinstr);
- tinstr = __mem_to_opcode_thumb16(tinstr);
+
+ fault = alignment_get_thumb(regs, ptr, &tinstr);
if (!fault) {
if (cpu_architecture() >= CPU_ARCH_ARMv7 &&
IS_T32(tinstr)) {
/* Thumb-2 32-bit */
- u16 tinst2 = 0;
- fault = probe_kernel_address(ptr + 1, tinst2);
- tinst2 = __mem_to_opcode_thumb16(tinst2);
+ u16 tinst2;
+ fault = alignment_get_thumb(regs, ptr + 1, &tinst2);
instr = __opcode_thumb32_compose(tinstr, tinst2);
thumb2_32b = 1;
} else {
@@ -801,8 +832,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
}
}
} else {
- fault = probe_kernel_address((void *)instrptr, instr);
- instr = __mem_to_opcode_arm(instr);
+ fault = alignment_get_arm(regs, (void *)instrptr, &instr);
}
if (fault) {
@@ -924,7 +954,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
* Oops, we didn't handle the instruction.
*/
pr_err("Alignment trap: not handling instruction "
- "%0*lx at [<%08lx>]\n",
+ "%0*x at [<%08lx>]\n",
isize << 1,
isize == 2 ? tinstr : instr, instrptr);
ai_skipped += 1;
@@ -934,7 +964,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
ai_user += 1;
if (ai_usermode & UM_WARN)
- printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*lx "
+ printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*x "
"Address=0x%08lx FSR 0x%03x\n", current->comm,
task_pid_nr(current), instrptr,
isize << 1,
diff --git a/arch/arm/mm/cache-aurora-l2.h b/arch/arm/mm/cache-aurora-l2.h
deleted file mode 100644
index c86124769831..000000000000
--- a/arch/arm/mm/cache-aurora-l2.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
- * AURORA shared L2 cache controller support
- *
- * Copyright (C) 2012 Marvell
- *
- * Yehuda Yitschak <yehuday@marvell.com>
- * Gregory CLEMENT <gregory.clement@free-electrons.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __ASM_ARM_HARDWARE_AURORA_L2_H
-#define __ASM_ARM_HARDWARE_AURORA_L2_H
-
-#define AURORA_SYNC_REG 0x700
-#define AURORA_RANGE_BASE_ADDR_REG 0x720
-#define AURORA_FLUSH_PHY_ADDR_REG 0x7f0
-#define AURORA_INVAL_RANGE_REG 0x774
-#define AURORA_CLEAN_RANGE_REG 0x7b4
-#define AURORA_FLUSH_RANGE_REG 0x7f4
-
-#define AURORA_ACR_REPLACEMENT_OFFSET 27
-#define AURORA_ACR_REPLACEMENT_MASK \
- (0x3 << AURORA_ACR_REPLACEMENT_OFFSET)
-#define AURORA_ACR_REPLACEMENT_TYPE_WAYRR \
- (0 << AURORA_ACR_REPLACEMENT_OFFSET)
-#define AURORA_ACR_REPLACEMENT_TYPE_LFSR \
- (1 << AURORA_ACR_REPLACEMENT_OFFSET)
-#define AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU \
- (3 << AURORA_ACR_REPLACEMENT_OFFSET)
-
-#define AURORA_ACR_FORCE_WRITE_POLICY_OFFSET 0
-#define AURORA_ACR_FORCE_WRITE_POLICY_MASK \
- (0x3 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
-#define AURORA_ACR_FORCE_WRITE_POLICY_DIS \
- (0 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
-#define AURORA_ACR_FORCE_WRITE_BACK_POLICY \
- (1 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
-#define AURORA_ACR_FORCE_WRITE_THRO_POLICY \
- (2 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
-
-#define MAX_RANGE_SIZE 1024
-
-#define AURORA_WAY_SIZE_SHIFT 2
-
-#define AURORA_CTRL_FW 0x100
-
-/* chose a number outside L2X0_CACHE_ID_PART_MASK to be sure to make
- * the distinction between a number coming from hardware and a number
- * coming from the device tree */
-#define AURORA_CACHE_ID 0x100
-
-#endif /* __ASM_ARM_HARDWARE_AURORA_L2_H */
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 5b251c8ecd45..12c26eb88afb 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -18,8 +18,8 @@
#include <asm/cp15.h>
#include <asm/cputype.h>
#include <asm/hardware/cache-l2x0.h>
+#include <asm/hardware/cache-aurora-l2.h>
#include "cache-tauros3.h"
-#include "cache-aurora-l2.h"
struct l2c_init_data {
const char *type;
@@ -1352,8 +1352,8 @@ static unsigned long aurora_range_end(unsigned long start, unsigned long end)
* since cache range operations stall the CPU pipeline
* until completion.
*/
- if (end > start + MAX_RANGE_SIZE)
- end = start + MAX_RANGE_SIZE;
+ if (end > start + AURORA_MAX_RANGE_SIZE)
+ end = start + AURORA_MAX_RANGE_SIZE;
/*
* Cache range operations can't straddle a page boundary.
@@ -1493,6 +1493,18 @@ static void __init aurora_of_parse(const struct device_node *np,
mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK;
}
+ if (of_property_read_bool(np, "marvell,ecc-enable")) {
+ mask |= AURORA_ACR_ECC_EN;
+ val |= AURORA_ACR_ECC_EN;
+ }
+
+ if (of_property_read_bool(np, "arm,parity-enable")) {
+ mask |= AURORA_ACR_PARITY_EN;
+ val |= AURORA_ACR_PARITY_EN;
+ } else if (of_property_read_bool(np, "arm,parity-disable")) {
+ mask |= AURORA_ACR_PARITY_EN;
+ }
+
*aux_val &= ~mask;
*aux_val |= val;
*aux_mask &= ~mask;
diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c
index 61d834157bc0..382e1c2855e8 100644
--- a/arch/arm/mm/copypage-xscale.c
+++ b/arch/arm/mm/copypage-xscale.c
@@ -42,6 +42,7 @@ static void mc_copy_user_page(void *from, void *to)
* when prefetching destination as well. (NP)
*/
asm volatile ("\
+.arch xscale \n\
pld [%0, #0] \n\
pld [%0, #32] \n\
pld [%1, #0] \n\
@@ -106,8 +107,9 @@ void
xscale_mc_clear_user_highpage(struct page *page, unsigned long vaddr)
{
void *ptr, *kaddr = kmap_atomic(page);
- asm volatile(
- "mov r1, %2 \n\
+ asm volatile("\
+.arch xscale \n\
+ mov r1, %2 \n\
mov r2, #0 \n\
mov r3, #0 \n\
1: mov ip, %0 \n\
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 52b82559d99b..db9247898300 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -68,8 +68,9 @@ static int arm_nommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
if (dma_mmap_from_global_coherent(vma, cpu_addr, size, &ret))
return ret;
-
- return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
+ if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+ return ret;
+ return -ENXIO;
}
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 4789c60a86e3..7d042d5c43e3 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -14,7 +14,9 @@
#include <linux/list.h>
#include <linux/init.h>
#include <linux/device.h>
+#include <linux/dma-direct.h>
#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
#include <linux/dma-contiguous.h>
#include <linux/highmem.h>
#include <linux/memblock.h>
@@ -34,6 +36,7 @@
#include <asm/mach/map.h>
#include <asm/system_info.h>
#include <asm/dma-contiguous.h>
+#include <xen/swiotlb-xen.h>
#include "dma.h"
#include "mm.h"
@@ -191,6 +194,7 @@ const struct dma_map_ops arm_dma_ops = {
.sync_sg_for_cpu = arm_dma_sync_sg_for_cpu,
.sync_sg_for_device = arm_dma_sync_sg_for_device,
.dma_supported = arm_dma_supported,
+ .get_required_mask = dma_direct_get_required_mask,
};
EXPORT_SYMBOL(arm_dma_ops);
@@ -211,6 +215,7 @@ const struct dma_map_ops arm_coherent_dma_ops = {
.map_sg = arm_dma_map_sg,
.map_resource = dma_direct_map_resource,
.dma_supported = arm_dma_supported,
+ .get_required_mask = dma_direct_get_required_mask,
};
EXPORT_SYMBOL(arm_coherent_dma_ops);
@@ -335,25 +340,6 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
pgprot_t prot, struct page **ret_page,
const void *caller, bool want_vaddr);
-static void *
-__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
- const void *caller)
-{
- /*
- * DMA allocation can be mapped to user space, so lets
- * set VM_USERMAP flags too.
- */
- return dma_common_contiguous_remap(page, size,
- VM_ARM_DMA_CONSISTENT | VM_USERMAP,
- prot, caller);
-}
-
-static void __dma_free_remap(void *cpu_addr, size_t size)
-{
- dma_common_free_remap(cpu_addr, size,
- VM_ARM_DMA_CONSISTENT | VM_USERMAP);
-}
-
#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K
static struct gen_pool *atomic_pool __ro_after_init;
@@ -509,7 +495,7 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
if (!want_vaddr)
goto out;
- ptr = __dma_alloc_remap(page, size, gfp, prot, caller);
+ ptr = dma_common_contiguous_remap(page, size, prot, caller);
if (!ptr) {
__dma_free_buffer(page, size);
return NULL;
@@ -576,7 +562,7 @@ static void *__alloc_from_contiguous(struct device *dev, size_t size,
goto out;
if (PageHighMem(page)) {
- ptr = __dma_alloc_remap(page, size, GFP_KERNEL, prot, caller);
+ ptr = dma_common_contiguous_remap(page, size, prot, caller);
if (!ptr) {
dma_release_from_contiguous(dev, page, count);
return NULL;
@@ -596,7 +582,7 @@ static void __free_from_contiguous(struct device *dev, struct page *page,
{
if (want_vaddr) {
if (PageHighMem(page))
- __dma_free_remap(cpu_addr, size);
+ dma_common_free_remap(cpu_addr, size);
else
__dma_remap(page, size, PAGE_KERNEL);
}
@@ -688,7 +674,7 @@ static void *remap_allocator_alloc(struct arm_dma_alloc_args *args,
static void remap_allocator_free(struct arm_dma_free_args *args)
{
if (args->want_vaddr)
- __dma_free_remap(args->cpu_addr, args->size);
+ dma_common_free_remap(args->cpu_addr, args->size);
__dma_free_buffer(args->page, args->size);
}
@@ -876,17 +862,6 @@ static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_add
__arm_dma_free(dev, size, cpu_addr, handle, attrs, true);
}
-/*
- * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems
- * that the intention is to allow exporting memory allocated via the
- * coherent DMA APIs through the dma_buf API, which only accepts a
- * scattertable. This presents a couple of problems:
- * 1. Not all memory allocated via the coherent DMA APIs is backed by
- * a struct page
- * 2. Passing coherent DMA memory into the streaming APIs is not allowed
- * as we will try to flush the memory through a different alias to that
- * actually being used (and the flushes are redundant.)
- */
int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
void *cpu_addr, dma_addr_t handle, size_t size,
unsigned long attrs)
@@ -1125,6 +1100,15 @@ int arm_dma_supported(struct device *dev, u64 mask)
static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
{
+ /*
+ * When CONFIG_ARM_LPAE is set, physical address can extend above
+ * 32-bits, which then can't be addressed by devices that only support
+ * 32-bit DMA.
+ * Use the generic dma-direct / swiotlb ops code in that case, as that
+ * handles bounce buffering for us.
+ */
+ if (IS_ENABLED(CONFIG_ARM_LPAE))
+ return NULL;
return coherent ? &arm_coherent_dma_ops : &arm_dma_ops;
}
@@ -1359,17 +1343,6 @@ static int __iommu_free_buffer(struct device *dev, struct page **pages,
}
/*
- * Create a CPU mapping for a specified pages
- */
-static void *
-__iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
- const void *caller)
-{
- return dma_common_pages_remap(pages, size,
- VM_ARM_DMA_CONSISTENT | VM_USERMAP, prot, caller);
-}
-
-/*
* Create a mapping in device IO address space for specified pages
*/
static dma_addr_t
@@ -1441,18 +1414,13 @@ static struct page **__atomic_get_pages(void *addr)
static struct page **__iommu_get_pages(void *cpu_addr, unsigned long attrs)
{
- struct vm_struct *area;
-
if (__in_atomic_pool(cpu_addr, PAGE_SIZE))
return __atomic_get_pages(cpu_addr);
if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
return cpu_addr;
- area = find_vm_area(cpu_addr);
- if (area && (area->flags & VM_ARM_DMA_CONSISTENT))
- return area->pages;
- return NULL;
+ return dma_common_find_pages(cpu_addr);
}
static void *__iommu_alloc_simple(struct device *dev, size_t size, gfp_t gfp,
@@ -1525,7 +1493,7 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
return pages;
- addr = __iommu_alloc_remap(pages, size, gfp, prot,
+ addr = dma_common_pages_remap(pages, size, prot,
__builtin_return_address(0));
if (!addr)
goto err_mapping;
@@ -1608,10 +1576,8 @@ void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
return;
}
- if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) == 0) {
- dma_common_free_remap(cpu_addr, size,
- VM_ARM_DMA_CONSISTENT | VM_USERMAP);
- }
+ if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) == 0)
+ dma_common_free_remap(cpu_addr, size);
__iommu_remove_mapping(dev, handle, size);
__iommu_free_buffer(dev, pages, size, attrs);
@@ -2329,6 +2295,9 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
const struct dma_map_ops *dma_ops;
dev->archdata.dma_coherent = coherent;
+#ifdef CONFIG_SWIOTLB
+ dev->dma_coherent = coherent;
+#endif
/*
* Don't override the dma_ops if they have already been set. Ideally
@@ -2346,10 +2315,8 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
set_dma_ops(dev, dma_ops);
#ifdef CONFIG_XEN
- if (xen_initial_domain()) {
- dev->archdata.dev_dma_ops = dev->dma_ops;
- dev->dma_ops = xen_dma_ops;
- }
+ if (xen_initial_domain())
+ dev->dma_ops = &xen_swiotlb_dma_ops;
#endif
dev->archdata.dma_ops_setup = true;
}
@@ -2363,3 +2330,39 @@ void arch_teardown_dma_ops(struct device *dev)
/* Let arch_setup_dma_ops() start again from scratch upon re-probe */
set_dma_ops(dev, NULL);
}
+
+#ifdef CONFIG_SWIOTLB
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
+{
+ __dma_page_cpu_to_dev(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
+ size, dir);
+}
+
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
+{
+ __dma_page_dev_to_cpu(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
+ size, dir);
+}
+
+long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
+ dma_addr_t dma_addr)
+{
+ return dma_to_pfn(dev, dma_addr);
+}
+
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, unsigned long attrs)
+{
+ return __dma_alloc(dev, size, dma_handle, gfp,
+ __get_dma_pgprot(attrs, PAGE_KERNEL), false,
+ attrs, __builtin_return_address(0));
+}
+
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t dma_handle, unsigned long attrs)
+{
+ __arm_dma_free(dev, size, cpu_addr, dma_handle, attrs, false);
+}
+#endif /* CONFIG_SWIOTLB */
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 890eeaac3cbb..bd0f4821f7e1 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -191,7 +191,7 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
{
unsigned int mask = VM_READ | VM_WRITE | VM_EXEC;
- if (fsr & FSR_WRITE)
+ if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
mask = VM_WRITE;
if (fsr & FSR_LNX_PF)
mask = VM_EXEC;
@@ -262,7 +262,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
- if (fsr & FSR_WRITE)
+ if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
flags |= FAULT_FLAG_WRITE;
/*
diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h
index c063708fa503..9ecc2097a87a 100644
--- a/arch/arm/mm/fault.h
+++ b/arch/arm/mm/fault.h
@@ -6,6 +6,7 @@
* Fault status register encodings. We steal bit 31 for our own purposes.
*/
#define FSR_LNX_PF (1 << 31)
+#define FSR_CM (1 << 13)
#define FSR_WRITE (1 << 11)
#define FSR_FS4 (1 << 10)
#define FSR_FS3_0 (15)
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 6ecbda87ee46..6d89db7895d1 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -204,18 +204,17 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
* coherent with the kernels mapping.
*/
if (!PageHighMem(page)) {
- size_t page_size = PAGE_SIZE << compound_order(page);
- __cpuc_flush_dcache_area(page_address(page), page_size);
+ __cpuc_flush_dcache_area(page_address(page), page_size(page));
} else {
unsigned long i;
if (cache_is_vipt_nonaliasing()) {
- for (i = 0; i < (1 << compound_order(page)); i++) {
+ for (i = 0; i < compound_nr(page); i++) {
void *addr = kmap_atomic(page + i);
__cpuc_flush_dcache_area(addr, PAGE_SIZE);
kunmap_atomic(addr);
}
} else {
- for (i = 0; i < (1 << compound_order(page)); i++) {
+ for (i = 0; i < compound_nr(page); i++) {
void *addr = kmap_high_get(page + i);
if (addr) {
__cpuc_flush_dcache_area(addr, PAGE_SIZE);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 4920a206dce9..b4be3baa83d4 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -21,6 +21,7 @@
#include <linux/dma-contiguous.h>
#include <linux/sizes.h>
#include <linux/stop_machine.h>
+#include <linux/swiotlb.h>
#include <asm/cp15.h>
#include <asm/mach-types.h>
@@ -174,6 +175,11 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max_low,
#ifdef CONFIG_HAVE_ARCH_PFN_VALID
int pfn_valid(unsigned long pfn)
{
+ phys_addr_t addr = __pfn_to_phys(pfn);
+
+ if (__phys_to_pfn(addr) != pfn)
+ return 0;
+
return memblock_is_map_memory(__pfn_to_phys(pfn));
}
EXPORT_SYMBOL(pfn_valid);
@@ -463,6 +469,10 @@ static void __init free_highpages(void)
*/
void __init mem_init(void)
{
+#ifdef CONFIG_ARM_LPAE
+ swiotlb_init(1);
+#endif
+
set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
/* this will put all unused low memory onto the freelists */
@@ -623,7 +633,8 @@ static void update_sections_early(struct section_perm perms[], int n)
if (t->flags & PF_KTHREAD)
continue;
for_each_thread(t, s)
- set_section_perms(perms, n, true, s->mm);
+ if (s->mm)
+ set_section_perms(perms, n, true, s->mm);
}
set_section_perms(perms, n, true, current->active_mm);
set_section_perms(perms, n, true, &init_mm);
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 941356d95a67..88c121ac14b3 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -70,9 +70,6 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page
#define VM_ARM_MTYPE(mt) ((mt) << 20)
#define VM_ARM_MTYPE_MASK (0x1f << 20)
-/* consistent regions used by dma_alloc_attrs() */
-#define VM_ARM_DMA_CONSISTENT 0x20000000
-
struct static_vm {
struct vm_struct vm;
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index f866870db749..b8d912ac9e61 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -17,33 +17,6 @@
((((addr)+SHMLBA-1)&~(SHMLBA-1)) + \
(((pgoff)<<PAGE_SHIFT) & (SHMLBA-1)))
-/* gap between mmap and stack */
-#define MIN_GAP (128*1024*1024UL)
-#define MAX_GAP ((TASK_SIZE)/6*5)
-
-static int mmap_is_legacy(struct rlimit *rlim_stack)
-{
- if (current->personality & ADDR_COMPAT_LAYOUT)
- return 1;
-
- if (rlim_stack->rlim_cur == RLIM_INFINITY)
- return 1;
-
- return sysctl_legacy_va_layout;
-}
-
-static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
-{
- unsigned long gap = rlim_stack->rlim_cur;
-
- if (gap < MIN_GAP)
- gap = MIN_GAP;
- else if (gap > MAX_GAP)
- gap = MAX_GAP;
-
- return PAGE_ALIGN(TASK_SIZE - gap - rnd);
-}
-
/*
* We need to ensure that shared mappings are correctly aligned to
* avoid aliasing issues with VIPT caches. We need to ensure that
@@ -171,31 +144,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
return addr;
}
-unsigned long arch_mmap_rnd(void)
-{
- unsigned long rnd;
-
- rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
-
- return rnd << PAGE_SHIFT;
-}
-
-void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
-{
- unsigned long random_factor = 0UL;
-
- if (current->flags & PF_RANDOMIZE)
- random_factor = arch_mmap_rnd();
-
- if (mmap_is_legacy(rlim_stack)) {
- mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
- mm->get_unmapped_area = arch_get_unmapped_area;
- } else {
- mm->mmap_base = mmap_base(random_factor, rlim_stack);
- mm->get_unmapped_area = arch_get_unmapped_area_topdown;
- }
-}
-
/*
* You really shouldn't be using read() or write() on /dev/mem. This
* might go away in the future.
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index d9a0038774a6..48c2888297dd 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -731,7 +731,7 @@ static void *__init late_alloc(unsigned long sz)
{
void *ptr = (void *)__get_free_pages(GFP_PGTABLE_KERNEL, get_order(sz));
- if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
+ if (!ptr || !pgtable_pte_page_ctor(virt_to_page(ptr)))
BUG();
return ptr;
}
@@ -1177,10 +1177,29 @@ void __init adjust_lowmem_bounds(void)
*/
vmalloc_limit = (u64)(uintptr_t)vmalloc_min - PAGE_OFFSET + PHYS_OFFSET;
+ /*
+ * The first usable region must be PMD aligned. Mark its start
+ * as MEMBLOCK_NOMAP if it isn't
+ */
+ for_each_memblock(memory, reg) {
+ if (!memblock_is_nomap(reg)) {
+ if (!IS_ALIGNED(reg->base, PMD_SIZE)) {
+ phys_addr_t len;
+
+ len = round_up(reg->base, PMD_SIZE) - reg->base;
+ memblock_mark_nomap(reg->base, len);
+ }
+ break;
+ }
+ }
+
for_each_memblock(memory, reg) {
phys_addr_t block_start = reg->base;
phys_addr_t block_end = reg->base + reg->size;
+ if (memblock_is_nomap(reg))
+ continue;
+
if (reg->base < vmalloc_limit) {
if (block_end > lowmem_limit)
/*
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 1448f144e7fb..1a49d503eafc 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -132,13 +132,11 @@ __v7m_setup_cont:
dsb
mov r6, lr @ save LR
ldr sp, =init_thread_union + THREAD_START_SP
- stmia sp, {r0-r3, r12}
cpsie i
svc #0
1: cpsid i
- ldr r0, =exc_ret
- orr lr, lr, #EXC_RET_THREADMODE_PROCESSSTACK
- str lr, [r0]
+ /* Calculate exc_ret */
+ orr r10, lr, #EXC_RET_THREADMODE_PROCESSSTACK
ldmia sp, {r0-r3, r12}
str r5, [r12, #11 * 4] @ restore the original SVC vector entry
mov lr, r6 @ restore LR
generated by cgit v1.2.3 (git 2.39.1) at 2025-02-02 08:20:20 +0100