From: Yinghai Lu <yhlu.kernel@gmail.com>
To: Ingo Molnar <mingo@elte.hu>, Thomas Gleixner <tglx@linutronix.de>,
"H. Peter Anvin" <hpa@zytor.com>,
Suresh Siddha <suresh.b.siddha@intel.com>
Cc: LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH] x86: introduce max_low_pfn_mapped for 64bit
Date: Thu, 10 Jul 2008 20:38:26 -0700 [thread overview]
Message-ID: <200807102038.26591.yhlu.kernel@gmail.com> (raw)
In-Reply-To: <200807092017.51004.yhlu.kernel@gmail.com>
when 4g more memory installed, don't map big hole below 4g.
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
arch/x86/kernel/acpi/boot.c | 2 +-
arch/x86/kernel/cpu/amd_64.c | 10 +++++++---
arch/x86/kernel/e820.c | 23 ++++++++++++++++++++---
arch/x86/kernel/efi.c | 2 +-
arch/x86/kernel/setup.c | 22 ++++++++++++++++++----
arch/x86/mm/init_32.c | 1 +
arch/x86/mm/init_64.c | 1 +
arch/x86/mm/pageattr.c | 19 +++++++++++++++++--
arch/x86/mm/pat.c | 3 ++-
arch/x86/pci/i386.c | 4 +++-
include/asm-x86/e820.h | 3 ++-
include/asm-x86/page.h | 1 +
12 files changed, 74 insertions(+), 17 deletions(-)
Index: linux-2.6/arch/x86/kernel/acpi/boot.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/acpi/boot.c
+++ linux-2.6/arch/x86/kernel/acpi/boot.c
@@ -130,7 +130,7 @@ char *__init __acpi_map_table(unsigned l
if (!phys || !size)
return NULL;
- if (phys+size <= (max_pfn_mapped << PAGE_SHIFT))
+ if (phys+size <= (max_low_pfn_mapped << PAGE_SHIFT))
return __va(phys);
offset = phys & (PAGE_SIZE - 1);
Index: linux-2.6/arch/x86/kernel/cpu/amd_64.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/cpu/amd_64.c
+++ linux-2.6/arch/x86/kernel/cpu/amd_64.c
@@ -199,10 +199,14 @@ static void __cpuinit init_amd(struct cp
* Don't do it for gbpages because there seems very little
* benefit in doing so.
*/
- if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg) &&
- (tseg >> PMD_SHIFT) <
- (max_pfn_mapped >> (PMD_SHIFT-PAGE_SHIFT)))
+ if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+ if ((tseg>>PMD_SHIFT) <
+ (max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) ||
+ ((tseg>>PMD_SHIFT) <
+ (max_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) &&
+ (tseg>>PMD_SHIFT) >= (1ULL<<(32 - PMD_SHIFT))))
set_memory_4k((unsigned long)__va(tseg), 1);
+ }
}
}
Index: linux-2.6/arch/x86/kernel/e820.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/e820.c
+++ linux-2.6/arch/x86/kernel/e820.c
@@ -1056,7 +1056,7 @@ unsigned long __initdata end_user_pfn =
/*
* Find the highest page frame number we have available
*/
-unsigned long __init e820_end(void)
+static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
{
int i;
unsigned long last_pfn = 0;
@@ -1064,12 +1064,21 @@ unsigned long __init e820_end(void)
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
+ unsigned long start_pfn;
unsigned long end_pfn;
- if (ei->type != E820_RAM)
+ if (ei->type != type)
continue;
+ start_pfn = ei->addr >> PAGE_SHIFT;
end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT;
+
+ if (start_pfn >= limit_pfn)
+ continue;
+ if (end_pfn > limit_pfn) {
+ last_pfn = limit_pfn;
+ break;
+ }
if (end_pfn > last_pfn)
last_pfn = end_pfn;
}
@@ -1083,7 +1092,15 @@ unsigned long __init e820_end(void)
last_pfn, max_arch_pfn);
return last_pfn;
}
+unsigned long __init e820_end_of_ram_pfn(void)
+{
+ return e820_end_pfn(MAX_ARCH_PFN, E820_RAM);
+}
+unsigned long __init e820_end_of_low_ram_pfn(void)
+{
+ return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM);
+}
/*
* Finds an active region in the address range from start_pfn to last_pfn and
* returns its range in ei_startpfn and ei_endpfn for the e820 entry.
@@ -1206,7 +1223,7 @@ static int __init parse_memmap_opt(char
* the real mem size before original memory map is
* reset.
*/
- saved_max_pfn = e820_end();
+ saved_max_pfn = e820_end_of_ram_pfn();
#endif
e820.nr_map = 0;
userdef = 1;
Index: linux-2.6/arch/x86/kernel/efi.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/efi.c
+++ linux-2.6/arch/x86/kernel/efi.c
@@ -473,7 +473,7 @@ void __init efi_enter_virtual_mode(void)
size = md->num_pages << EFI_PAGE_SHIFT;
end = md->phys_addr + size;
- if (PFN_UP(end) <= max_pfn_mapped)
+ if (PFN_UP(end) <= max_low_pfn_mapped)
va = __va(md->phys_addr);
else
va = efi_ioremap(md->phys_addr, size);
Index: linux-2.6/arch/x86/kernel/setup.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/setup.c
+++ linux-2.6/arch/x86/kernel/setup.c
@@ -719,14 +719,14 @@ void __init setup_arch(char **cmdline_p)
* partially used pages are not usable - thus
* we are rounding upwards:
*/
- max_pfn = e820_end();
+ max_pfn = e820_end_of_ram_pfn();
/* preallocate 4k for mptable mpc */
early_reserve_e820_mpc_new();
/* update e820 for memory not covered by WB MTRRs */
mtrr_bp_init();
if (mtrr_trim_uncached_memory(max_pfn))
- max_pfn = e820_end();
+ max_pfn = e820_end_of_ram_pfn();
#ifdef CONFIG_X86_32
/* max_low_pfn get updated here */
@@ -738,12 +738,26 @@ void __init setup_arch(char **cmdline_p)
/* How many end-of-memory variables you have, grandma! */
/* need this before calling reserve_initrd */
- max_low_pfn = max_pfn;
+ if (max_pfn > (1UL<<(32 - PAGE_SHIFT)))
+ max_low_pfn = e820_end_of_low_ram_pfn();
+ else
+ max_low_pfn = max_pfn;
+
high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
#endif
/* max_pfn_mapped is updated here */
- max_pfn_mapped = init_memory_mapping(0, (max_low_pfn << PAGE_SHIFT));
+ max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
+ max_pfn_mapped = max_low_pfn_mapped;
+
+#ifdef CONFIG_X86_64
+ if (max_pfn > max_low_pfn) {
+ max_pfn_mapped = init_memory_mapping(1UL<<32,
+ max_pfn<<PAGE_SHIFT);
+ /* can we preseve max_low_pfn ?*/
+ max_low_pfn = max_pfn;
+ }
+#endif
/*
* NOTE: On x86-32, only from this point on, fixmaps are ready for use.
Index: linux-2.6/arch/x86/mm/init_32.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/init_32.c
+++ linux-2.6/arch/x86/mm/init_32.c
@@ -50,6 +50,7 @@
unsigned int __VMALLOC_RESERVE = 128 << 20;
+unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;
DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
Index: linux-2.6/arch/x86/mm/init_64.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/init_64.c
+++ linux-2.6/arch/x86/mm/init_64.c
@@ -53,6 +53,7 @@
* The direct mapping extends to max_pfn_mapped, so that we can directly access
* apertures, ACPI and other tables without having to play with fixmaps.
*/
+unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;
static unsigned long dma_reserve __initdata;
Index: linux-2.6/arch/x86/mm/pageattr.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/pageattr.c
+++ linux-2.6/arch/x86/mm/pageattr.c
@@ -537,8 +537,14 @@ static int split_large_page(pte_t *kpte,
set_pte(&pbase[i], pfn_pte(pfn, ref_prot));
if (address >= (unsigned long)__va(0) &&
+ address < (unsigned long)__va(max_low_pfn_mapped << PAGE_SHIFT))
+ split_page_count(level);
+
+#ifdef CONFIG_X86_64
+ if (address >= (unsigned long)__va(1UL<<32) &&
address < (unsigned long)__va(max_pfn_mapped << PAGE_SHIFT))
split_page_count(level);
+#endif
/*
* Install the new, split up pagetable. Important details here:
@@ -655,12 +661,21 @@ static int cpa_process_alias(struct cpa_
if (cpa->pfn > max_pfn_mapped)
return 0;
+#ifdef CONFIG_X86_64
+ if (cpa->pfn > max_low_pfn_mapped && cpa->pfn < (1UL<<(32-PAGE_SHIFT)))
+ return 0;
+#endif
/*
* No need to redo, when the primary call touched the direct
* mapping already:
*/
- if (!within(cpa->vaddr, PAGE_OFFSET,
- PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))) {
+ if (!(within(cpa->vaddr, PAGE_OFFSET,
+ PAGE_OFFSET + (max_low_pfn_mapped << PAGE_SHIFT))
+#ifdef CONFIG_X86_64
+ || within(cpa->vaddr, PAGE_OFFSET + (1UL<<32),
+ PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))
+#endif
+ )) {
alias_cpa = *cpa;
alias_cpa.vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT);
Index: linux-2.6/arch/x86/mm/pat.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/pat.c
+++ linux-2.6/arch/x86/mm/pat.c
@@ -449,7 +449,8 @@ int phys_mem_access_prot_allowed(struct
if (retval < 0)
return 0;
- if (pfn <= max_pfn_mapped &&
+ if (((pfn <= max_low_pfn_mapped) ||
+ (pfn >= (1UL<<(32 - PAGE_SHIFT)) && pfn <= max_pfn_mapped)) &&
ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) {
free_memtype(offset, offset + size);
printk(KERN_INFO
Index: linux-2.6/arch/x86/pci/i386.c
===================================================================
--- linux-2.6.orig/arch/x86/pci/i386.c
+++ linux-2.6/arch/x86/pci/i386.c
@@ -334,7 +334,9 @@ int pci_mmap_page_range(struct pci_dev *
flags = new_flags;
}
- if (vma->vm_pgoff <= max_pfn_mapped &&
+ if (((vma->vm_pgoff <= max_low_pfn_mapped) ||
+ (vma->vm_pgoff >= (1UL<<(32 - PAGE_SHIFT)) &&
+ vma->vm_pgoff <= max_pfn_mapped)) &&
ioremap_change_attr((unsigned long)__va(addr), len, flags)) {
free_memtype(addr, addr + len);
return -EINVAL;
Index: linux-2.6/include/asm-x86/e820.h
===================================================================
--- linux-2.6.orig/include/asm-x86/e820.h
+++ linux-2.6/include/asm-x86/e820.h
@@ -99,7 +99,8 @@ extern void free_early(u64 start, u64 en
extern void early_res_to_bootmem(u64 start, u64 end);
extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
-extern unsigned long e820_end(void);
+extern unsigned long e820_end_of_ram_pfn(void);
+extern unsigned long e820_end_of_low_ram_pfn(void);
extern int e820_find_active_region(const struct e820entry *ei,
unsigned long start_pfn,
unsigned long last_pfn,
Index: linux-2.6/include/asm-x86/page.h
===================================================================
--- linux-2.6.orig/include/asm-x86/page.h
+++ linux-2.6/include/asm-x86/page.h
@@ -61,6 +61,7 @@ extern void map_devmem(unsigned long pfn
extern void unmap_devmem(unsigned long pfn, unsigned long size,
pgprot_t vma_prot);
+extern unsigned long max_low_pfn_mapped;
extern unsigned long max_pfn_mapped;
struct page;
next prev parent reply other threads:[~2008-07-11 3:39 UTC|newest]
Thread overview: 84+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-07-08 8:41 [PATCH] x86: introduce page_size_mask for 64bit Yinghai Lu
2008-07-08 8:43 ` [PATCH] x86: not overmap than end in init_memory_mapping - 64bit Yinghai Lu
2008-07-09 7:38 ` Ingo Molnar
2008-07-09 8:34 ` Ingo Molnar
2008-07-09 8:37 ` Yinghai Lu
2008-07-09 8:46 ` Ingo Molnar
2008-07-09 8:58 ` Yinghai Lu
2008-07-09 10:01 ` Yinghai Lu
2008-07-09 10:30 ` Ingo Molnar
2008-07-09 8:45 ` Ingo Molnar
2008-07-10 3:15 ` [PATCh] x86: overmapped fix when 4K pages on tail " Yinghai Lu
2008-07-10 3:16 ` [PATCH] x86: merge __acpi_map_table Yinghai Lu
2008-07-10 3:17 ` [PATCH] x86: make e820_end return end_of_ram again for 64bit Yinghai Lu
2008-07-10 7:00 ` Ingo Molnar
2008-07-10 11:17 ` [PATCH] x86: e820 remove the range instead of update it to reserved Yinghai Lu
2008-07-11 8:20 ` Ingo Molnar
2008-07-11 3:36 ` [PATCH] x86: save slit Yinghai Lu
2008-07-11 8:22 ` Ingo Molnar
2008-07-11 3:38 ` Yinghai Lu [this message]
2008-07-11 8:26 ` [PATCH] x86: introduce max_low_pfn_mapped for 64bit Ingo Molnar
2008-07-11 8:39 ` Yinghai Lu
2008-07-11 8:51 ` Ingo Molnar
2008-07-12 1:41 ` [PATCH] x86: let 32bit use apic_ops too Yinghai Lu
2008-07-12 1:43 ` [PATCH] x86: mach_apicdef.h need to include before smp.h Yinghai Lu
2008-07-12 1:44 ` [PATCH] x86: make read_apic_id return final apicid Yinghai Lu
2008-07-12 8:01 ` [PATCH] x86: make 64bit have get_apic_id Yinghai Lu
2008-07-13 6:28 ` Ingo Molnar
2008-07-13 6:59 ` Ingo Molnar
2008-07-13 7:05 ` Yinghai Lu
2008-07-13 9:23 ` Ingo Molnar
2008-07-13 9:28 ` Ingo Molnar
2008-07-13 16:15 ` Suresh Siddha
2008-07-13 1:19 ` [PATCH] x86: make read_apic_id return final apicid Suresh Siddha
2008-07-13 1:08 ` [PATCH] x86: let 32bit use apic_ops too Suresh Siddha
2008-07-13 2:04 ` Yinghai Lu
2008-07-13 16:28 ` Suresh Siddha
2008-07-13 16:51 ` Maciej W. Rozycki
2008-07-13 17:16 ` Cyrill Gorcunov
2008-07-13 23:46 ` Maciej W. Rozycki
2008-07-14 16:48 ` Cyrill Gorcunov
2008-07-14 17:20 ` Maciej W. Rozycki
2008-07-14 18:09 ` Cyrill Gorcunov
2008-07-14 18:24 ` Maciej W. Rozycki
2008-07-14 18:32 ` Cyrill Gorcunov
2008-07-13 1:43 ` Maciej W. Rozycki
2008-07-13 1:45 ` Yinghai Lu
2008-07-13 1:54 ` Maciej W. Rozycki
2008-07-13 16:43 ` Suresh Siddha
2008-07-13 17:05 ` Maciej W. Rozycki
2008-07-14 5:19 ` [PATCH] x86: let 32bit use apic_ops too - fix Yinghai Lu
2008-07-14 7:12 ` Ingo Molnar
2008-07-14 16:49 ` Suresh Siddha
2008-07-14 17:00 ` Yinghai Lu
2008-07-14 18:03 ` Suresh Siddha
2008-07-18 17:06 ` Ingo Molnar
2008-07-15 17:33 ` Suresh Siddha
2008-07-15 18:10 ` Yinghai Lu
2008-07-15 18:27 ` Suresh Siddha
2008-07-18 17:07 ` Ingo Molnar
2008-07-12 21:30 ` [PATCH] x86: max_low_pfn_mapped fix #1 Yinghai Lu
2008-07-13 9:45 ` Ingo Molnar
2008-07-12 21:31 ` [PATCH] x86: max_low_pfn_mapped fix #2 Yinghai Lu
2008-07-12 21:32 ` [PATCH] x86: max_low_pfn_mapped fix #3 Yinghai Lu
2008-07-13 21:29 ` [PATCH] x86: max_low_pfn_mapped fix #4 Yinghai Lu
2008-07-13 21:30 ` [PATCH] x86: get x86_phys_bits early Yinghai Lu
2008-07-13 21:32 ` [PATCH] x86: make 64bit hpet_set_mapping to use ioremap too Yinghai Lu
2008-07-13 21:50 ` [PATCH] x86: make 64bit hpet_set_mapping to use ioremap too v2 Yinghai Lu
2008-07-10 6:54 ` [PATCH] x86: merge __acpi_map_table Ingo Molnar
2008-07-10 6:53 ` [PATCh] x86: overmapped fix when 4K pages on tail - 64bit Ingo Molnar
2008-07-10 6:57 ` Yinghai Lu
2008-07-10 7:20 ` Ingo Molnar
2008-07-10 7:32 ` Yinghai Lu
2008-07-10 14:16 ` Arjan van de Ven
2008-07-13 14:57 ` Andi Kleen
2008-07-13 15:33 ` Arjan van de Ven
2008-07-13 18:25 ` Andi Kleen
2008-07-13 18:17 ` Yinghai Lu
2008-07-13 18:48 ` Andi Kleen
2008-07-13 19:00 ` Yinghai Lu
2008-07-13 20:32 ` Ingo Molnar
2008-07-13 20:51 ` Andi Kleen
2008-07-14 0:04 ` H. Peter Anvin
2008-07-14 6:39 ` Andi Kleen
2008-07-09 7:38 ` [PATCH] x86: introduce page_size_mask for 64bit Ingo Molnar
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=200807102038.26591.yhlu.kernel@gmail.com \
--to=yhlu.kernel@gmail.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=suresh.b.siddha@intel.com \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.