From 78bef24e8477653853eb028dfc18471f05e54955 Mon Sep 17 00:00:00 2001
From: Matt Fleming <matt.fleming@intel.com>
Date: Mon, 8 Oct 2012 11:33:05 +0100
Subject: [PATCH 01/10] MAINTAINERS: Add EFI git repository location
People keep asking for the whereabouts of this git tree, so add it to
MAINTAINERS.
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
---
MAINTAINERS | 1 +
1 file changed, 1 insertion(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index e73060fe0788..fe95ef189db0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2801,6 +2801,7 @@ F: sound/usb/misc/ua101.c
EXTENSIBLE FIRMWARE INTERFACE (EFI)
M: Matt Fleming <matt.fleming@intel.com>
L: linux-efi@vger.kernel.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/efi.git
S: Maintained
F: Documentation/x86/efi-stub.txt
F: arch/ia64/kernel/efi.c
From 7b16bbf97375d9fb7fc107b3f80afeb94a204e44 Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Thu, 18 Oct 2012 14:33:23 +0800
Subject: [PATCH 02/10] Revert "x86/mm: Fix the size calculation of mapping
tables"
Commit:
722bc6b16771 x86/mm: Fix the size calculation of mapping tables
Tried to address the issue that the first 2/4M should use 4k pages
if PSE enabled, but extra counts should only be valid for x86_32.
This commit caused a kdump regression: the kdump kernel hangs.
Work is in progress to fundamentally fix the various page table
initialization issues that we have, via the design suggested
by H. Peter Anvin, but it's not ready yet to be merged.
So, to get a working kdump revert to the last known working version,
which is the revert of this commit and of a followup fix (which was
incomplete):
bd2753b2dda7 x86/mm: Only add extra pages count for the first memory range during pre-allocation
Tested kdump on physical and virtual machines.
Signed-off-by: Dave Young <dyoung@redhat.com>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Flavio Leitner <fbl@redhat.com>
Tested-by: Flavio Leitner <fbl@redhat.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Flavio Leitner <fbl@redhat.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: ianfang.cn@gmail.com
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: <stable@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/mm/init.c | 22 +++++++++-------------
1 file changed, 9 insertions(+), 13 deletions(-)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index ab1f6a93b527..8653b3a722be 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -29,14 +29,8 @@ int direct_gbpages
#endif
;
-struct map_range {
- unsigned long start;
- unsigned long end;
- unsigned page_size_mask;
-};
-
-static void __init find_early_table_space(struct map_range *mr, unsigned long end,
- int use_pse, int use_gbpages)
+static void __init find_early_table_space(unsigned long end, int use_pse,
+ int use_gbpages)
{
unsigned long puds, pmds, ptes, tables, start = 0, good_end = end;
phys_addr_t base;
@@ -61,10 +55,6 @@ static void __init find_early_table_space(struct map_range *mr, unsigned long en
#ifdef CONFIG_X86_32
extra += PMD_SIZE;
#endif
- /* The first 2/4M doesn't use large pages. */
- if (mr->start < PMD_SIZE)
- extra += mr->end - mr->start;
-
ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
} else
ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -95,6 +85,12 @@ void __init native_pagetable_reserve(u64 start, u64 end)
memblock_reserve(start, end - start);
}
+struct map_range {
+ unsigned long start;
+ unsigned long end;
+ unsigned page_size_mask;
+};
+
#ifdef CONFIG_X86_32
#define NR_RANGE_MR 3
#else /* CONFIG_X86_64 */
@@ -267,7 +263,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
* nodes are discovered.
*/
if (!after_bootmem)
- find_early_table_space(&mr[0], end, use_pse, use_gbpages);
+ find_early_table_space(end, use_pse, use_gbpages);
for (i = 0; i < nr_range; i++)
ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
From 876ee61aadf01aa0db981b5d249cbdd53dc28b5e Mon Sep 17 00:00:00 2001
From: Jan Beulich <JBeulich@suse.com>
Date: Thu, 4 Oct 2012 14:48:10 +0100
Subject: [PATCH 03/10] x86-64: Fix page table accounting
Commit 20167d3421a089a1bf1bd680b150dc69c9506810 ("x86-64: Fix
accounting in kernel_physical_mapping_init()") went a little too
far by entirely removing the counting of pre-populated page
tables: this should be done at boot time (to cover the page
tables set up in early boot code), but shouldn't be done during
memory hot add.
Hence, re-add the removed increments of "pages", but make them
and the one in phys_pte_init() conditional upon !after_bootmem.
Reported-Acked-and-Tested-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Cc: <stable@kernel.org>
Link: http://lkml.kernel.org/r/506DAFBA020000780009FA8C@nat28.tlf.novell.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/mm/init_64.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 2b6b4a3c8beb..3baff255adac 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -386,7 +386,8 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
* these mappings are more intelligent.
*/
if (pte_val(*pte)) {
- pages++;
+ if (!after_bootmem)
+ pages++;
continue;
}
@@ -451,6 +452,8 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
* attributes.
*/
if (page_size_mask & (1 << PG_LEVEL_2M)) {
+ if (!after_bootmem)
+ pages++;
last_map_addr = next;
continue;
}
@@ -526,6 +529,8 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
* attributes.
*/
if (page_size_mask & (1 << PG_LEVEL_1G)) {
+ if (!after_bootmem)
+ pages++;
last_map_addr = next;
continue;
}
From 3e8fa263a97079c74880675c451587bb6899e661 Mon Sep 17 00:00:00 2001
From: Matt Fleming <matt.fleming@intel.com>
Date: Fri, 19 Oct 2012 13:25:46 +0100
Subject: [PATCH 04/10] x86/efi: Fix oops caused by incorrect set_memory_uc()
usage
Calling __pa() with an ioremap'd address is invalid. If we
encounter an efi_memory_desc_t without EFI_MEMORY_WB set in
->attribute we currently call set_memory_uc(), which in turn
calls __pa() on a potentially ioremap'd address.
On CONFIG_X86_32 this results in the following oops:
BUG: unable to handle kernel paging request at f7f22280
IP: [<c10257b9>] reserve_ram_pages_type+0x89/0x210
*pdpt = 0000000001978001 *pde = 0000000001ffb067 *pte = 0000000000000000
Oops: 0000 [#1] PREEMPT SMP
Modules linked in:
Pid: 0, comm: swapper Not tainted 3.0.0-acpi-efi-0805 #3
EIP: 0060:[<c10257b9>] EFLAGS: 00010202 CPU: 0
EIP is at reserve_ram_pages_type+0x89/0x210
EAX: 0070e280 EBX: 38714000 ECX: f7814000 EDX: 00000000
ESI: 00000000 EDI: 38715000 EBP: c189fef0 ESP: c189fea8
DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
Process swapper (pid: 0, ti=c189e000 task=c18bbe60 task.ti=c189e000)
Stack:
80000200 ff108000 00000000 c189ff00 00038714 00000000 00000000 c189fed0
c104f8ca 00038714 00000000 00038715 00000000 00000000 00038715 00000000
00000010 38715000 c189ff48 c1025aff 38715000 00000000 00000010 00000000
Call Trace:
[<c104f8ca>] ? page_is_ram+0x1a/0x40
[<c1025aff>] reserve_memtype+0xdf/0x2f0
[<c1024dc9>] set_memory_uc+0x49/0xa0
[<c19334d0>] efi_enter_virtual_mode+0x1c2/0x3aa
[<c19216d4>] start_kernel+0x291/0x2f2
[<c19211c7>] ? loglevel+0x1b/0x1b
[<c19210bf>] i386_start_kernel+0xbf/0xc8
The only time we can call set_memory_uc() for a memory region is
when it is part of the direct kernel mapping. For the case where
we ioremap a memory region we must leave it alone.
This patch reimplements the fix from e8c7106280a3 ("x86, efi:
Calling __pa() with an ioremap()ed address is invalid") which
was reverted in e1ad783b12ec because it caused a regression on
some MacBooks (they hung at boot). The regression was caused
because the commit only marked EFI_RUNTIME_SERVICES_DATA as
E820_RESERVED_EFI, when it should have marked all regions that
have the EFI_MEMORY_RUNTIME attribute.
Despite first impressions, it's not possible to use
ioremap_cache() to map all cached memory regions on
CONFIG_X86_64 because of the way that the memory map might be
configured as detailed in the following bug report,
https://bugzilla.redhat.com/show_bug.cgi?id=748516
e.g. some of the EFI memory regions *need* to be mapped as part
of the direct kernel mapping.
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
Cc: Matthew Garrett <mjg@redhat.com>
Cc: Zhang Rui <rui.zhang@intel.com>
Cc: Huang Ying <huang.ying.caritas@gmail.com>
Cc: Keith Packard <keithp@keithp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1350649546-23541-1-git-send-email-matt@console-pimps.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/include/asm/efi.h | 5 +++--
arch/x86/platform/efi/efi.c | 29 ++++++++++++++++++-----------
arch/x86/platform/efi/efi_64.c | 7 +++++--
3 files changed, 26 insertions(+), 15 deletions(-)
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index c9dcc181d4d1..36ff332da130 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -35,7 +35,7 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...);
#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \
efi_call_virt(f, a1, a2, a3, a4, a5, a6)
-#define efi_ioremap(addr, size, type) ioremap_cache(addr, size)
+#define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size)
#else /* !CONFIG_X86_32 */
@@ -89,7 +89,7 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
(u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
- u32 type);
+ u32 type, u64 attribute);
#endif /* CONFIG_X86_32 */
@@ -98,6 +98,7 @@ extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
extern int efi_memblock_x86_reserve_range(void);
extern void efi_call_phys_prelog(void);
extern void efi_call_phys_epilog(void);
+extern void efi_memory_uc(u64 addr, unsigned long size);
#ifndef CONFIG_EFI
/*
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index aded2a91162a..cb34839c97c5 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -810,6 +810,16 @@ void __iomem *efi_lookup_mapped_addr(u64 phys_addr)
return NULL;
}
+void efi_memory_uc(u64 addr, unsigned long size)
+{
+ unsigned long page_shift = 1UL << EFI_PAGE_SHIFT;
+ u64 npages;
+
+ npages = round_up(size, page_shift) / page_shift;
+ memrange_efi_to_native(&addr, &npages);
+ set_memory_uc(addr, npages);
+}
+
/*
* This function will switch the EFI runtime services to virtual mode.
* Essentially, look through the EFI memmap and map every region that
@@ -823,7 +833,7 @@ void __init efi_enter_virtual_mode(void)
efi_memory_desc_t *md, *prev_md = NULL;
efi_status_t status;
unsigned long size;
- u64 end, systab, addr, npages, end_pfn;
+ u64 end, systab, end_pfn;
void *p, *va, *new_memmap = NULL;
int count = 0;
@@ -879,10 +889,14 @@ void __init efi_enter_virtual_mode(void)
end_pfn = PFN_UP(end);
if (end_pfn <= max_low_pfn_mapped
|| (end_pfn > (1UL << (32 - PAGE_SHIFT))
- && end_pfn <= max_pfn_mapped))
+ && end_pfn <= max_pfn_mapped)) {
va = __va(md->phys_addr);
- else
- va = efi_ioremap(md->phys_addr, size, md->type);
+
+ if (!(md->attribute & EFI_MEMORY_WB))
+ efi_memory_uc((u64)(unsigned long)va, size);
+ } else
+ va = efi_ioremap(md->phys_addr, size,
+ md->type, md->attribute);
md->virt_addr = (u64) (unsigned long) va;
@@ -892,13 +906,6 @@ void __init efi_enter_virtual_mode(void)
continue;
}
- if (!(md->attribute & EFI_MEMORY_WB)) {
- addr = md->virt_addr;
- npages = md->num_pages;
- memrange_efi_to_native(&addr, &npages);
- set_memory_uc(addr, npages);
- }
-
systab = (u64) (unsigned long) efi_phys.systab;
if (md->phys_addr <= systab && systab < end) {
systab += md->virt_addr - md->phys_addr;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ac3aa54e2654..95fd505dfeb6 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -82,7 +82,7 @@ void __init efi_call_phys_epilog(void)
}
void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
- u32 type)
+ u32 type, u64 attribute)
{
unsigned long last_map_pfn;
@@ -92,8 +92,11 @@ void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size);
if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) {
unsigned long top = last_map_pfn << PAGE_SHIFT;
- efi_ioremap(top, size - (top - phys_addr), type);
+ efi_ioremap(top, size - (top - phys_addr), type, attribute);
}
+ if (!(attribute & EFI_MEMORY_WB))
+ efi_memory_uc((u64)(unsigned long)__va(phys_addr), size);
+
return (void __iomem *)__va(phys_addr);
}
From 94777fc51b3ad85ff9f705ddf7cdd0eb3bbad5a6 Mon Sep 17 00:00:00 2001
From: Dimitri Sivanich <sivanich@sgi.com>
Date: Tue, 16 Oct 2012 07:50:21 -0500
Subject: [PATCH 05/10] x86/irq/ioapic: Check for valid irq_cfg pointer in
smp_irq_move_cleanup_interrupt
Posting this patch to fix an issue concerning sparse irq's that
I raised a while back. There was discussion about adding
refcounting to sparse irqs (to fix other potential race
conditions), but that does not appear to have been addressed
yet. This covers the only issue of this type that I've
encountered in this area.
A NULL pointer dereference can occur in
smp_irq_move_cleanup_interrupt() if we haven't yet setup the
irq_cfg pointer in the irq_desc.irq_data.chip_data.
In create_irq_nr() there is a window where we have set
vector_irq in __assign_irq_vector(), but not yet called
irq_set_chip_data() to set the irq_cfg pointer.
Should an IRQ_MOVE_CLEANUP_VECTOR hit the cpu in question during
this time, smp_irq_move_cleanup_interrupt() will attempt to
process the aforementioned irq, but panic when accessing
irq_cfg.
Only continue processing the irq if irq_cfg is non-NULL.
Signed-off-by: Dimitri Sivanich <sivanich@sgi.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Joerg Roedel <joerg.roedel@amd.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Alexander Gordeev <agordeev@redhat.com>
Link: http://lkml.kernel.org/r/20121016125021.GA22935@sgi.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/kernel/apic/io_apic.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index c265593ec2cd..1817fa911024 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2257,6 +2257,9 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
continue;
cfg = irq_cfg(irq);
+ if (!cfg)
+ continue;
+
raw_spin_lock(&desc->lock);
/*
From 6ede1fd3cb404c0016de6ac529df46d561bd558b Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Mon, 22 Oct 2012 16:35:18 -0700
Subject: [PATCH 06/10] x86, mm: Trim memory in memblock to be page aligned
We will not map partial pages, so need to make sure memblock
allocation will not allocate those bytes out.
Also we will use for_each_mem_pfn_range() to loop to map memory
range to keep them consistent.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/CAE9FiQVZirvaBMFYRfXMmWEcHbKSicQEHz4VAwUv0xFCk51ZNw@mail.gmail.com
Acked-by: Jacob Shin <jacob.shin@amd.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: <stable@vger.kernel.org>
---
arch/x86/kernel/e820.c | 3 +++
include/linux/memblock.h | 1 +
mm/memblock.c | 24 ++++++++++++++++++++++++
3 files changed, 28 insertions(+)
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index ed858e9e9a74..df06ade26bef 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1077,6 +1077,9 @@ void __init memblock_x86_fill(void)
memblock_add(ei->addr, ei->size);
}
+ /* throw away partial pages */
+ memblock_trim_memory(PAGE_SIZE);
+
memblock_dump_all();
}
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 569d67d4243e..d452ee191066 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -57,6 +57,7 @@ int memblock_add(phys_addr_t base, phys_addr_t size);
int memblock_remove(phys_addr_t base, phys_addr_t size);
int memblock_free(phys_addr_t base, phys_addr_t size);
int memblock_reserve(phys_addr_t base, phys_addr_t size);
+void memblock_trim_memory(phys_addr_t align);
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
diff --git a/mm/memblock.c b/mm/memblock.c
index 931eef145af5..625905523c2a 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -930,6 +930,30 @@ int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t si
return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
}
+void __init_memblock memblock_trim_memory(phys_addr_t align)
+{
+ int i;
+ phys_addr_t start, end, orig_start, orig_end;
+ struct memblock_type *mem = &memblock.memory;
+
+ for (i = 0; i < mem->cnt; i++) {
+ orig_start = mem->regions[i].base;
+ orig_end = mem->regions[i].base + mem->regions[i].size;
+ start = round_up(orig_start, align);
+ end = round_down(orig_end, align);
+
+ if (start == orig_start && end == orig_end)
+ continue;
+
+ if (start < end) {
+ mem->regions[i].base = start;
+ mem->regions[i].size = end - start;
+ } else {
+ memblock_remove_region(mem, i);
+ i--;
+ }
+ }
+}
void __init_memblock memblock_set_current_limit(phys_addr_t limit)
{
From 1f2ff682ac951ed82cc043cf140d2851084512df Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Mon, 22 Oct 2012 16:35:18 -0700
Subject: [PATCH 07/10] x86, mm: Use memblock memory loop instead of e820_RAM
We need to handle E820_RAM and E820_RESERVED_KERNEL at the same time.
Also memblock has page aligned range for ram, so we could avoid mapping
partial pages.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/CAE9FiQVZirvaBMFYRfXMmWEcHbKSicQEHz4VAwUv0xFCk51ZNw@mail.gmail.com
Acked-by: Jacob Shin <jacob.shin@amd.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: <stable@vger.kernel.org>
---
arch/x86/kernel/setup.c | 17 +++++++++--------
1 file changed, 9 insertions(+), 8 deletions(-)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 468e98dfd44e..5d888af8682a 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -921,18 +921,19 @@ void __init setup_arch(char **cmdline_p)
#ifdef CONFIG_X86_64
if (max_pfn > max_low_pfn) {
int i;
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *ei = &e820.map[i];
+ unsigned long start, end;
+ unsigned long start_pfn, end_pfn;
- if (ei->addr + ei->size <= 1UL << 32)
- continue;
-
- if (ei->type == E820_RESERVED)
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn,
+ NULL) {
+
+ end = PFN_PHYS(end_pfn);
+ if (end <= (1UL<<32))
continue;
+ start = PFN_PHYS(start_pfn);
max_pfn_mapped = init_memory_mapping(
- ei->addr < 1UL << 32 ? 1UL << 32 : ei->addr,
- ei->addr + ei->size);
+ max((1UL<<32), start), end);
}
/* can we preseve max_low_pfn ?*/
From 844ab6f993b1d32eb40512503d35ff6ad0c57030 Mon Sep 17 00:00:00 2001
From: Jacob Shin <jacob.shin@amd.com>
Date: Wed, 24 Oct 2012 14:24:44 -0500
Subject: [PATCH 08/10] x86, mm: Find_early_table_space based on ranges that
are actually being mapped
Current logic finds enough space for direct mapping page tables from 0
to end. Instead, we only need to find enough space to cover mr[0].start
to mr[nr_range].end -- the range that is actually being mapped by
init_memory_mapping()
This is needed after 1bbbbe779aabe1f0768c2bf8f8c0a5583679b54a, to address
the panic reported here:
https://lkml.org/lkml/2012/10/20/160
https://lkml.org/lkml/2012/10/21/157
Signed-off-by: Jacob Shin <jacob.shin@amd.com>
Link: http://lkml.kernel.org/r/20121024195311.GB11779@jshin-Toonie
Tested-by: Tom Rini <trini@ti.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
arch/x86/mm/init.c | 70 +++++++++++++++++++++++++++-------------------
1 file changed, 41 insertions(+), 29 deletions(-)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 8653b3a722be..bc287d62bf1e 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -29,36 +29,54 @@ int direct_gbpages
#endif
;
-static void __init find_early_table_space(unsigned long end, int use_pse,
- int use_gbpages)
+struct map_range {
+ unsigned long start;
+ unsigned long end;
+ unsigned page_size_mask;
+};
+
+/*
+ * First calculate space needed for kernel direct mapping page tables to cover
+ * mr[0].start to mr[nr_range - 1].end, while accounting for possible 2M and 1GB
+ * pages. Then find enough contiguous space for those page tables.
+ */
+static void __init find_early_table_space(struct map_range *mr, int nr_range)
{
- unsigned long puds, pmds, ptes, tables, start = 0, good_end = end;
+ int i;
+ unsigned long puds = 0, pmds = 0, ptes = 0, tables;
+ unsigned long start = 0, good_end;
phys_addr_t base;
- puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
- tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
+ for (i = 0; i < nr_range; i++) {
+ unsigned long range, extra;
- if (use_gbpages) {
- unsigned long extra;
+ range = mr[i].end - mr[i].start;
+ puds += (range + PUD_SIZE - 1) >> PUD_SHIFT;
- extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
- pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
- } else
- pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
+ if (mr[i].page_size_mask & (1 << PG_LEVEL_1G)) {
+ extra = range - ((range >> PUD_SHIFT) << PUD_SHIFT);
+ pmds += (extra + PMD_SIZE - 1) >> PMD_SHIFT;
+ } else {
+ pmds += (range + PMD_SIZE - 1) >> PMD_SHIFT;
+ }
- tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
-
- if (use_pse) {
- unsigned long extra;
-
- extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
+ if (mr[i].page_size_mask & (1 << PG_LEVEL_2M)) {
+ extra = range - ((range >> PMD_SHIFT) << PMD_SHIFT);
#ifdef CONFIG_X86_32
- extra += PMD_SIZE;
+ extra += PMD_SIZE;
#endif
- ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
- } else
- ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ /* The first 2/4M doesn't use large pages. */
+ if (mr[i].start < PMD_SIZE)
+ extra += range;
+ ptes += (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ } else {
+ ptes += (range + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ }
+ }
+
+ tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
+ tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
#ifdef CONFIG_X86_32
@@ -76,7 +94,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT);
printk(KERN_DEBUG "kernel direct mapping tables up to %#lx @ [mem %#010lx-%#010lx]\n",
- end - 1, pgt_buf_start << PAGE_SHIFT,
+ mr[nr_range - 1].end - 1, pgt_buf_start << PAGE_SHIFT,
(pgt_buf_top << PAGE_SHIFT) - 1);
}
@@ -85,12 +103,6 @@ void __init native_pagetable_reserve(u64 start, u64 end)
memblock_reserve(start, end - start);
}
-struct map_range {
- unsigned long start;
- unsigned long end;
- unsigned page_size_mask;
-};
-
#ifdef CONFIG_X86_32
#define NR_RANGE_MR 3
#else /* CONFIG_X86_64 */
@@ -263,7 +275,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
* nodes are discovered.
*/
if (!after_bootmem)
- find_early_table_space(end, use_pse, use_gbpages);
+ find_early_table_space(mr, nr_range);
for (i = 0; i < nr_range; i++)
ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
From 5189c2a7c7769ee9d037d76c1a7b8550ccf3481c Mon Sep 17 00:00:00 2001
From: Olof Johansson <olof@lixom.net>
Date: Wed, 24 Oct 2012 10:00:44 -0700
Subject: [PATCH 09/10] x86: efi: Turn off efi_enabled after setup on mixed
fw/kernel
When 32-bit EFI is used with 64-bit kernel (or vice versa), turn off
efi_enabled once setup is done. Beyond setup, it is normally used to
determine if runtime services are available and we will have none.
This will resolve issues stemming from efivars modprobe panicking on a
32/64-bit setup, as well as some reboot issues on similar setups.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=45991
Reported-by: Marko Kohtala <marko.kohtala@gmail.com>
Reported-by: Maxim Kammerer <mk@dee.su>
Signed-off-by: Olof Johansson <olof@lixom.net>
Acked-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Cc: stable@kernel.org # 3.4 - 3.6
Cc: Matthew Garrett <mjg@redhat.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
---
arch/x86/include/asm/efi.h | 1 +
arch/x86/kernel/setup.c | 12 ++++++++++++
arch/x86/platform/efi/efi.c | 18 ++++++++++--------
3 files changed, 23 insertions(+), 8 deletions(-)
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index c9dcc181d4d1..029189db84de 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -98,6 +98,7 @@ extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
extern int efi_memblock_x86_reserve_range(void);
extern void efi_call_phys_prelog(void);
extern void efi_call_phys_epilog(void);
+extern void efi_unmap_memmap(void);
#ifndef CONFIG_EFI
/*
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index a2bb18e02839..6fd7752cee96 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1035,6 +1035,18 @@ void __init setup_arch(char **cmdline_p)
arch_init_ideal_nops();
register_refined_jiffies(CLOCK_TICK_RATE);
+
+#ifdef CONFIG_EFI
+ /* Once setup is done above, disable efi_enabled on mismatched
+ * firmware/kernel archtectures since there is no support for
+ * runtime services.
+ */
+ if (efi_enabled && IS_ENABLED(CONFIG_X86_64) != efi_64bit) {
+ pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+ efi_unmap_memmap();
+ efi_enabled = 0;
+ }
+#endif
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index aded2a91162a..9bae3b73fccc 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -70,11 +70,15 @@ EXPORT_SYMBOL(efi);
struct efi_memory_map memmap;
bool efi_64bit;
-static bool efi_native;
static struct efi efi_phys __initdata;
static efi_system_table_t efi_systab __initdata;
+static inline bool efi_is_native(void)
+{
+ return IS_ENABLED(CONFIG_X86_64) == efi_64bit;
+}
+
static int __init setup_noefi(char *arg)
{
efi_enabled = 0;
@@ -420,7 +424,7 @@ void __init efi_reserve_boot_services(void)
}
}
-static void __init efi_unmap_memmap(void)
+void __init efi_unmap_memmap(void)
{
if (memmap.map) {
early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
@@ -432,7 +436,7 @@ void __init efi_free_boot_services(void)
{
void *p;
- if (!efi_native)
+ if (!efi_is_native())
return;
for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
@@ -684,12 +688,10 @@ void __init efi_init(void)
return;
}
efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab;
- efi_native = !efi_64bit;
#else
efi_phys.systab = (efi_system_table_t *)
(boot_params.efi_info.efi_systab |
((__u64)boot_params.efi_info.efi_systab_hi<<32));
- efi_native = efi_64bit;
#endif
if (efi_systab_init(efi_phys.systab)) {
@@ -723,7 +725,7 @@ void __init efi_init(void)
* that doesn't match the kernel 32/64-bit mode.
*/
- if (!efi_native)
+ if (!efi_is_native())
pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");
else if (efi_runtime_init()) {
efi_enabled = 0;
@@ -735,7 +737,7 @@ void __init efi_init(void)
return;
}
#ifdef CONFIG_X86_32
- if (efi_native) {
+ if (efi_is_native()) {
x86_platform.get_wallclock = efi_get_time;
x86_platform.set_wallclock = efi_set_rtc_mmss;
}
@@ -834,7 +836,7 @@ void __init efi_enter_virtual_mode(void)
* non-native EFI
*/
- if (!efi_native) {
+ if (!efi_is_native()) {
efi_unmap_memmap();
return;
}
From f82f64dd9f485e13f29f369772d4a0e868e5633a Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Thu, 25 Oct 2012 15:45:26 -0700
Subject: [PATCH 10/10] x86, mm: Undo incorrect revert in arch/x86/mm/init.c
Commit
844ab6f9 x86, mm: Find_early_table_space based on ranges that are actually being mapped
added back some lines back wrongly that has been removed in commit
7b16bbf97 Revert "x86/mm: Fix the size calculation of mapping tables"
remove them again.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/CAE9FiQW_vuaYQbmagVnxT2DGsYc=9tNeAbdBq53sYkitPOwxSQ@mail.gmail.com
Acked-by: Jacob Shin <jacob.shin@amd.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
arch/x86/mm/init.c | 4 ----
1 file changed, 4 deletions(-)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index bc287d62bf1e..d7aea41563b3 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -65,10 +65,6 @@ static void __init find_early_table_space(struct map_range *mr, int nr_range)
#ifdef CONFIG_X86_32
extra += PMD_SIZE;
#endif
- /* The first 2/4M doesn't use large pages. */
- if (mr[i].start < PMD_SIZE)
- extra += range;
-
ptes += (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
} else {
ptes += (range + PAGE_SIZE - 1) >> PAGE_SHIFT;