mirror of
https://github.com/torvalds/linux.git
synced 2024-12-12 14:12:51 +00:00
12f03ee606
1/ Introduce ZONE_DEVICE and devm_memremap_pages() as a generic mechanism for adding device-driver-discovered memory regions to the kernel's direct map. This facility is used by the pmem driver to enable pfn_to_page() operations on the page frames returned by DAX ('direct_access' in 'struct block_device_operations'). For now, the 'memmap' allocation for these "device" pages comes from "System RAM". Support for allocating the memmap from device memory will arrive in a later kernel. 2/ Introduce memremap() to replace usages of ioremap_cache() and ioremap_wt(). memremap() drops the __iomem annotation for these mappings to memory that do not have i/o side effects. The replacement of ioremap_cache() with memremap() is limited to the pmem driver to ease merging the api change in v4.3. Completion of the conversion is targeted for v4.4. 3/ Similar to the usage of memcpy_to_pmem() + wmb_pmem() in the pmem driver, update the VFS DAX implementation and PMEM api to provide persistence guarantees for kernel operations on a DAX mapping. 4/ Convert the ACPI NFIT 'BLK' driver to map the block apertures as cacheable to improve performance. 5/ Miscellaneous updates and fixes to libnvdimm including support for issuing "address range scrub" commands, clarifying the optimal 'sector size' of pmem devices, a clarification of the usage of the ACPI '_STA' (status) property for DIMM devices, and other minor fixes. -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABAgAGBQJV6Nx7AAoJEB7SkWpmfYgCWyYQAI5ju6Gvw27RNFtPovHcZUf5 JGnxXejI6/AqeTQ+IulgprxtEUCrXOHjCDA5dkjr1qvsoqK1qxug+vJHOZLgeW0R OwDtmdW4Qrgeqm+CPoxETkorJ8wDOc8mol81kTiMgeV3UqbYeeHIiTAmwe7VzZ0C nNdCRDm5g8dHCjTKcvK3rvozgyoNoWeBiHkPe76EbnxDICxCB5dak7XsVKNMIVFQ NuYlnw6IYN7+rMHgpgpRux38NtIW8VlYPWTmHExejc2mlioWMNBG/bmtwLyJ6M3e zliz4/cnonTMUaizZaVozyinTa65m7wcnpjK+vlyGV2deDZPJpDRvSOtB0lH30bR 1gy+qrKzuGKpaN6thOISxFLLjmEeYwzYd7SvC9n118r32qShz+opN9XX0WmWSFlA sajE1ehm4M7s5pkMoa/dRnAyR8RUPu4RNINdQ/Z9jFfAOx+Q26rLdQXwf9+uqbEb bIeSQwOteK5vYYCstvpAcHSMlJAglzIX5UfZBvtEIJN7rlb0VhmGWfxAnTu+ktG1 o9cqAt+J4146xHaFwj5duTsyKhWb8BL9+xqbKPNpXEp+PbLsrnE/+WkDLFD67jxz dgIoK60mGnVXp+16I2uMqYYDgAyO5zUdmM4OygOMnZNa1mxesjbDJC6Wat1Wsndn slsw6DkrWT60CRE42nbK =o57/ -----END PGP SIGNATURE----- Merge tag 'libnvdimm-for-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm Pull libnvdimm updates from Dan Williams: "This update has successfully completed a 0day-kbuild run and has appeared in a linux-next release. The changes outside of the typical drivers/nvdimm/ and drivers/acpi/nfit.[ch] paths are related to the removal of IORESOURCE_CACHEABLE, the introduction of memremap(), and the introduction of ZONE_DEVICE + devm_memremap_pages(). Summary: - Introduce ZONE_DEVICE and devm_memremap_pages() as a generic mechanism for adding device-driver-discovered memory regions to the kernel's direct map. This facility is used by the pmem driver to enable pfn_to_page() operations on the page frames returned by DAX ('direct_access' in 'struct block_device_operations'). For now, the 'memmap' allocation for these "device" pages comes from "System RAM". Support for allocating the memmap from device memory will arrive in a later kernel. - Introduce memremap() to replace usages of ioremap_cache() and ioremap_wt(). memremap() drops the __iomem annotation for these mappings to memory that do not have i/o side effects. The replacement of ioremap_cache() with memremap() is limited to the pmem driver to ease merging the api change in v4.3. Completion of the conversion is targeted for v4.4. - Similar to the usage of memcpy_to_pmem() + wmb_pmem() in the pmem driver, update the VFS DAX implementation and PMEM api to provide persistence guarantees for kernel operations on a DAX mapping. - Convert the ACPI NFIT 'BLK' driver to map the block apertures as cacheable to improve performance. - Miscellaneous updates and fixes to libnvdimm including support for issuing "address range scrub" commands, clarifying the optimal 'sector size' of pmem devices, a clarification of the usage of the ACPI '_STA' (status) property for DIMM devices, and other minor fixes" * tag 'libnvdimm-for-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (34 commits) libnvdimm, pmem: direct map legacy pmem by default libnvdimm, pmem: 'struct page' for pmem libnvdimm, pfn: 'struct page' provider infrastructure x86, pmem: clarify that ARCH_HAS_PMEM_API implies PMEM mapped WB add devm_memremap_pages mm: ZONE_DEVICE for "device memory" mm: move __phys_to_pfn and __pfn_to_phys to asm/generic/memory_model.h dax: drop size parameter to ->direct_access() nd_blk: change aperture mapping from WC to WB nvdimm: change to use generic kvfree() pmem, dax: have direct_access use __pmem annotation dax: update I/O path to do proper PMEM flushing pmem: add copy_from_iter_pmem() and clear_pmem() pmem, x86: clean up conditional pmem includes pmem: remove layer when calling arch_has_wmb_pmem() pmem, x86: move x86 PMEM API to new pmem.h header libnvdimm, e820: make CONFIG_X86_PMEM_LEGACY a tristate option pmem: switch to devm_ allocations devres: add devm_memremap libnvdimm, btt: write and validate parent_uuid ...
231 lines
5.7 KiB
C
231 lines
5.7 KiB
C
/*
|
|
* S390 version
|
|
* Copyright IBM Corp. 1999
|
|
* Author(s): Hartmut Penner (hp@de.ibm.com)
|
|
*
|
|
* Derived from "arch/i386/mm/init.c"
|
|
* Copyright (C) 1995 Linus Torvalds
|
|
*/
|
|
|
|
#include <linux/signal.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/string.h>
|
|
#include <linux/types.h>
|
|
#include <linux/ptrace.h>
|
|
#include <linux/mman.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/init.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/bootmem.h>
|
|
#include <linux/memory.h>
|
|
#include <linux/pfn.h>
|
|
#include <linux/poison.h>
|
|
#include <linux/initrd.h>
|
|
#include <linux/export.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/memblock.h>
|
|
#include <asm/processor.h>
|
|
#include <asm/uaccess.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/dma.h>
|
|
#include <asm/lowcore.h>
|
|
#include <asm/tlb.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/sections.h>
|
|
#include <asm/ctl_reg.h>
|
|
#include <asm/sclp.h>
|
|
|
|
pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((__aligned__(PAGE_SIZE)));
|
|
|
|
unsigned long empty_zero_page, zero_page_mask;
|
|
EXPORT_SYMBOL(empty_zero_page);
|
|
EXPORT_SYMBOL(zero_page_mask);
|
|
|
|
static void __init setup_zero_pages(void)
|
|
{
|
|
struct cpuid cpu_id;
|
|
unsigned int order;
|
|
struct page *page;
|
|
int i;
|
|
|
|
get_cpu_id(&cpu_id);
|
|
switch (cpu_id.machine) {
|
|
case 0x9672: /* g5 */
|
|
case 0x2064: /* z900 */
|
|
case 0x2066: /* z900 */
|
|
case 0x2084: /* z990 */
|
|
case 0x2086: /* z990 */
|
|
case 0x2094: /* z9-109 */
|
|
case 0x2096: /* z9-109 */
|
|
order = 0;
|
|
break;
|
|
case 0x2097: /* z10 */
|
|
case 0x2098: /* z10 */
|
|
case 0x2817: /* z196 */
|
|
case 0x2818: /* z196 */
|
|
order = 2;
|
|
break;
|
|
case 0x2827: /* zEC12 */
|
|
case 0x2828: /* zEC12 */
|
|
order = 5;
|
|
break;
|
|
case 0x2964: /* z13 */
|
|
default:
|
|
order = 7;
|
|
break;
|
|
}
|
|
/* Limit number of empty zero pages for small memory sizes */
|
|
while (order > 2 && (totalram_pages >> 10) < (1UL << order))
|
|
order--;
|
|
|
|
empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
|
|
if (!empty_zero_page)
|
|
panic("Out of memory in setup_zero_pages");
|
|
|
|
page = virt_to_page((void *) empty_zero_page);
|
|
split_page(page, order);
|
|
for (i = 1 << order; i > 0; i--) {
|
|
mark_page_reserved(page);
|
|
page++;
|
|
}
|
|
|
|
zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK;
|
|
}
|
|
|
|
/*
|
|
* paging_init() sets up the page tables
|
|
*/
|
|
void __init paging_init(void)
|
|
{
|
|
unsigned long max_zone_pfns[MAX_NR_ZONES];
|
|
unsigned long pgd_type, asce_bits;
|
|
|
|
init_mm.pgd = swapper_pg_dir;
|
|
if (VMALLOC_END > (1UL << 42)) {
|
|
asce_bits = _ASCE_TYPE_REGION2 | _ASCE_TABLE_LENGTH;
|
|
pgd_type = _REGION2_ENTRY_EMPTY;
|
|
} else {
|
|
asce_bits = _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH;
|
|
pgd_type = _REGION3_ENTRY_EMPTY;
|
|
}
|
|
S390_lowcore.kernel_asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
|
|
clear_table((unsigned long *) init_mm.pgd, pgd_type,
|
|
sizeof(unsigned long)*2048);
|
|
vmem_map_init();
|
|
|
|
/* enable virtual mapping in kernel mode */
|
|
__ctl_load(S390_lowcore.kernel_asce, 1, 1);
|
|
__ctl_load(S390_lowcore.kernel_asce, 7, 7);
|
|
__ctl_load(S390_lowcore.kernel_asce, 13, 13);
|
|
arch_local_irq_restore(4UL << (BITS_PER_LONG - 8));
|
|
|
|
sparse_memory_present_with_active_regions(MAX_NUMNODES);
|
|
sparse_init();
|
|
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
|
|
max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS);
|
|
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
|
|
free_area_init_nodes(max_zone_pfns);
|
|
}
|
|
|
|
void __init mem_init(void)
|
|
{
|
|
if (MACHINE_HAS_TLB_LC)
|
|
cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
|
|
cpumask_set_cpu(0, mm_cpumask(&init_mm));
|
|
atomic_set(&init_mm.context.attach_count, 1);
|
|
|
|
set_max_mapnr(max_low_pfn);
|
|
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
|
|
|
|
/* Setup guest page hinting */
|
|
cmma_init();
|
|
|
|
/* this will put all low memory onto the freelists */
|
|
free_all_bootmem();
|
|
setup_zero_pages(); /* Setup zeroed pages. */
|
|
|
|
mem_init_print_info(NULL);
|
|
printk("Write protected kernel read-only data: %#lx - %#lx\n",
|
|
(unsigned long)&_stext,
|
|
PFN_ALIGN((unsigned long)&_eshared) - 1);
|
|
}
|
|
|
|
void free_initmem(void)
|
|
{
|
|
free_initmem_default(POISON_FREE_INITMEM);
|
|
}
|
|
|
|
#ifdef CONFIG_BLK_DEV_INITRD
|
|
void __init free_initrd_mem(unsigned long start, unsigned long end)
|
|
{
|
|
free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
|
|
"initrd");
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_MEMORY_HOTPLUG
|
|
int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
|
|
{
|
|
unsigned long normal_end_pfn = PFN_DOWN(memblock_end_of_DRAM());
|
|
unsigned long dma_end_pfn = PFN_DOWN(MAX_DMA_ADDRESS);
|
|
unsigned long start_pfn = PFN_DOWN(start);
|
|
unsigned long size_pages = PFN_DOWN(size);
|
|
unsigned long nr_pages;
|
|
int rc, zone_enum;
|
|
|
|
rc = vmem_add_mapping(start, size);
|
|
if (rc)
|
|
return rc;
|
|
|
|
while (size_pages > 0) {
|
|
if (start_pfn < dma_end_pfn) {
|
|
nr_pages = (start_pfn + size_pages > dma_end_pfn) ?
|
|
dma_end_pfn - start_pfn : size_pages;
|
|
zone_enum = ZONE_DMA;
|
|
} else if (start_pfn < normal_end_pfn) {
|
|
nr_pages = (start_pfn + size_pages > normal_end_pfn) ?
|
|
normal_end_pfn - start_pfn : size_pages;
|
|
zone_enum = ZONE_NORMAL;
|
|
} else {
|
|
nr_pages = size_pages;
|
|
zone_enum = ZONE_MOVABLE;
|
|
}
|
|
rc = __add_pages(nid, NODE_DATA(nid)->node_zones + zone_enum,
|
|
start_pfn, size_pages);
|
|
if (rc)
|
|
break;
|
|
start_pfn += nr_pages;
|
|
size_pages -= nr_pages;
|
|
}
|
|
if (rc)
|
|
vmem_remove_mapping(start, size);
|
|
return rc;
|
|
}
|
|
|
|
unsigned long memory_block_size_bytes(void)
|
|
{
|
|
/*
|
|
* Make sure the memory block size is always greater
|
|
* or equal than the memory increment size.
|
|
*/
|
|
return max_t(unsigned long, MIN_MEMORY_BLOCK_SIZE, sclp.rzm);
|
|
}
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
int arch_remove_memory(u64 start, u64 size)
|
|
{
|
|
/*
|
|
* There is no hardware or firmware interface which could trigger a
|
|
* hot memory remove on s390. So there is nothing that needs to be
|
|
* implemented.
|
|
*/
|
|
return -EBUSY;
|
|
}
|
|
#endif
|
|
#endif /* CONFIG_MEMORY_HOTPLUG */
|