From dacf7333571d770366bff74d10b56aa545434605 Mon Sep 17 00:00:00 2001
From: Jaswinder Singh Rajput <jaswinder@infradead.org>
Date: Wed, 7 Jan 2009 17:26:35 +0530
Subject: x86: smp.h move zap_low_mappings declartion to tlbflush.h
Impact: cleanup, moving NON-SMP stuff from smp.h
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/mm/init_32.c | 1 -
1 file changed, 1 deletion(-)
(limited to 'arch/x86/mm')
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index f99a6c6c432..a9dd0b7ad61 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -49,7 +49,6 @@
#include <asm/paravirt.h>
#include <asm/setup.h>
#include <asm/cacheflush.h>
-#include <asm/smp.h>
unsigned int __VMALLOC_RESERVE = 128 << 20;
--
cgit v1.2.3-70-g09d2
From f313e12308f7c5ea645f18e759d104d088b18615 Mon Sep 17 00:00:00 2001
From: Andi Kleen <andi@firstfloor.org>
Date: Fri, 9 Jan 2009 12:17:43 -0800
Subject: x86: avoid theoretical vmalloc fault loop
Ajith Kumar noticed:
I was going through the vmalloc fault handling for x86_64 and am unclear
about the following lines in the vmalloc_fault() function.
pgd = pgd_offset(current->mm ?: &init_mm, address);
pgd_ref = pgd_offset_k(address);
Here the intention is to get the pgd corresponding to the current process
and sync it up with the pgd in init_mm(obtained from pgd_offset_k).
However, for kernel threads current->mm is NULL and hence pgd =
pgd_offset(init_mm, address) = pgd_ref which means the fault handler
returns without setting the pgd entry in the MM structure in the context
of which the kernel thread has faulted. This could lead to never-ending
faults and busy looping of kernel threads like pdflush. So, shouldn't the
pgd = pgd_offset(current->mm ?: &init_mm, address); be pgd =
pgd_offset(current->active_mm ?: &init_mm, address);
We can use active_mm unconditionally because it should be always set.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/mm/fault.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'arch/x86/mm')
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9e268b6b204..90dfae511a4 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -534,7 +534,7 @@ static int vmalloc_fault(unsigned long address)
happen within a race in page table update. In the later
case just flush. */
- pgd = pgd_offset(current->mm ?: &init_mm, address);
+ pgd = pgd_offset(current->active_mm, address);
pgd_ref = pgd_offset_k(address);
if (pgd_none(*pgd_ref))
return -1;
--
cgit v1.2.3-70-g09d2
From e4b866ed197cef9989348e0479fed8d864ea465b Mon Sep 17 00:00:00 2001
From: "venkatesh.pallipadi@intel.com" <venkatesh.pallipadi@intel.com>
Date: Fri, 9 Jan 2009 16:13:11 -0800
Subject: x86 PAT: change track_pfn_vma_new to take pgprot_t pointer param
Impact: cleanup
Change the protection parameter for track_pfn_vma_new() into a pgprot_t pointer.
Subsequent patch changes the x86 PAT handling to return a compatible
memtype in pgprot_t, if what was requested cannot be allowed due to conflicts.
No fuctionality change in this patch.
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/mm/pat.c | 6 +++---
include/asm-generic/pgtable.h | 4 ++--
mm/memory.c | 7 ++++---
3 files changed, 9 insertions(+), 8 deletions(-)
(limited to 'arch/x86/mm')
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 85cbd3cd372..f88ac80530c 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -741,7 +741,7 @@ cleanup_ret:
* Note that this function can be called with caller trying to map only a
* subrange/page inside the vma.
*/
-int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
+int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long size)
{
int retval = 0;
@@ -758,14 +758,14 @@ int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
if (is_linear_pfn_mapping(vma)) {
/* reserve the whole chunk starting from vm_pgoff */
paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
- return reserve_pfn_range(paddr, vma_size, prot);
+ return reserve_pfn_range(paddr, vma_size, *prot);
}
/* reserve page by page using pfn and size */
base_paddr = (resource_size_t)pfn << PAGE_SHIFT;
for (i = 0; i < size; i += PAGE_SIZE) {
paddr = base_paddr + i;
- retval = reserve_pfn_range(paddr, PAGE_SIZE, prot);
+ retval = reserve_pfn_range(paddr, PAGE_SIZE, *prot);
if (retval)
goto cleanup_ret;
}
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 72ebe91005a..8e6d0ca70ab 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -301,7 +301,7 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
* track_pfn_vma_new is called when a _new_ pfn mapping is being established
* for physical range indicated by pfn and size.
*/
-static inline int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
+static inline int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long size)
{
return 0;
@@ -332,7 +332,7 @@ static inline void untrack_pfn_vma(struct vm_area_struct *vma,
{
}
#else
-extern int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
+extern int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long size);
extern int track_pfn_vma_copy(struct vm_area_struct *vma);
extern void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
diff --git a/mm/memory.c b/mm/memory.c
index d3ee2ea5615..22bfa7a47a0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1511,6 +1511,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn)
{
int ret;
+ pgprot_t pgprot = vma->vm_page_prot;
/*
* Technically, architectures with pte_special can avoid all these
* restrictions (same for remap_pfn_range). However we would like
@@ -1525,10 +1526,10 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
if (addr < vma->vm_start || addr >= vma->vm_end)
return -EFAULT;
- if (track_pfn_vma_new(vma, vma->vm_page_prot, pfn, PAGE_SIZE))
+ if (track_pfn_vma_new(vma, &pgprot, pfn, PAGE_SIZE))
return -EINVAL;
- ret = insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+ ret = insert_pfn(vma, addr, pfn, pgprot);
if (ret)
untrack_pfn_vma(vma, pfn, PAGE_SIZE);
@@ -1671,7 +1672,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
- err = track_pfn_vma_new(vma, prot, pfn, PAGE_ALIGN(size));
+ err = track_pfn_vma_new(vma, &prot, pfn, PAGE_ALIGN(size));
if (err) {
/*
* To indicate that track_pfn related cleanup is not
--
cgit v1.2.3-70-g09d2
From cdecff6864a1cd352a41d44a65e7451b8ef5cee2 Mon Sep 17 00:00:00 2001
From: "venkatesh.pallipadi@intel.com" <venkatesh.pallipadi@intel.com>
Date: Fri, 9 Jan 2009 16:13:12 -0800
Subject: x86 PAT: return compatible mapping to remap_pfn_range callers
Impact: avoid warning message, potentially solve 3D performance regression
Change x86 PAT code to return compatible memtype if the exact memtype that
was requested in remap_pfn_rage and friends is not available due to some
conflict.
This is done by returning the compatible type in pgprot parameter of
track_pfn_vma_new(), and the caller uses that memtype for page table.
Note that track_pfn_vma_copy() which is basically called during fork gets the
prot from existing page table and should not have any conflict. Hence we use
strict memtype check there and do not allow compatible memtypes.
This patch fixes the bug reported here:
http://marc.info/?l=linux-kernel&m=123108883716357&w=2
Specifically the error message:
X:5010 map pfn expected mapping type write-back for d0000000-d0101000,
got write-combining
Should go away.
Reported-and-bisected-by: Kevin Winchester <kjwinchester@gmail.com>
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/mm/pat.c | 43 ++++++++++++++++++++++++++++---------------
1 file changed, 28 insertions(+), 15 deletions(-)
(limited to 'arch/x86/mm')
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index f88ac80530c..8b08fb95527 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -601,12 +601,13 @@ void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
* Reserved non RAM regions only and after successful reserve_memtype,
* this func also keeps identity mapping (if any) in sync with this new prot.
*/
-static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t vma_prot)
+static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
+ int strict_prot)
{
int is_ram = 0;
int id_sz, ret;
unsigned long flags;
- unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK);
+ unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
is_ram = pagerange_is_ram(paddr, paddr + size);
@@ -625,15 +626,24 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t vma_prot)
return ret;
if (flags != want_flags) {
- free_memtype(paddr, paddr + size);
- printk(KERN_ERR
- "%s:%d map pfn expected mapping type %s for %Lx-%Lx, got %s\n",
- current->comm, current->pid,
- cattr_name(want_flags),
- (unsigned long long)paddr,
- (unsigned long long)(paddr + size),
- cattr_name(flags));
- return -EINVAL;
+ if (strict_prot || !is_new_memtype_allowed(want_flags, flags)) {
+ free_memtype(paddr, paddr + size);
+ printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
+ " for %Lx-%Lx, got %s\n",
+ current->comm, current->pid,
+ cattr_name(want_flags),
+ (unsigned long long)paddr,
+ (unsigned long long)(paddr + size),
+ cattr_name(flags));
+ return -EINVAL;
+ }
+ /*
+ * We allow returning different type than the one requested in
+ * non strict case.
+ */
+ *vma_prot = __pgprot((pgprot_val(*vma_prot) &
+ (~_PAGE_CACHE_MASK)) |
+ flags);
}
/* Need to keep identity mapping in sync */
@@ -689,6 +699,7 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
unsigned long vma_start = vma->vm_start;
unsigned long vma_end = vma->vm_end;
unsigned long vma_size = vma_end - vma_start;
+ pgprot_t pgprot;
if (!pat_enabled)
return 0;
@@ -702,7 +713,8 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
WARN_ON_ONCE(1);
return -EINVAL;
}
- return reserve_pfn_range(paddr, vma_size, __pgprot(prot));
+ pgprot = __pgprot(prot);
+ return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
}
/* reserve entire vma page by page, using pfn and prot from pte */
@@ -710,7 +722,8 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
continue;
- retval = reserve_pfn_range(paddr, PAGE_SIZE, __pgprot(prot));
+ pgprot = __pgprot(prot);
+ retval = reserve_pfn_range(paddr, PAGE_SIZE, &pgprot, 1);
if (retval)
goto cleanup_ret;
}
@@ -758,14 +771,14 @@ int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
if (is_linear_pfn_mapping(vma)) {
/* reserve the whole chunk starting from vm_pgoff */
paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
- return reserve_pfn_range(paddr, vma_size, *prot);
+ return reserve_pfn_range(paddr, vma_size, prot, 0);
}
/* reserve page by page using pfn and size */
base_paddr = (resource_size_t)pfn << PAGE_SHIFT;
for (i = 0; i < size; i += PAGE_SIZE) {
paddr = base_paddr + i;
- retval = reserve_pfn_range(paddr, PAGE_SIZE, *prot);
+ retval = reserve_pfn_range(paddr, PAGE_SIZE, prot, 0);
if (retval)
goto cleanup_ret;
}
--
cgit v1.2.3-70-g09d2
From 58dab916dfb57328d50deb0aa9b3fc92efa248ff Mon Sep 17 00:00:00 2001
From: "venkatesh.pallipadi@intel.com" <venkatesh.pallipadi@intel.com>
Date: Fri, 9 Jan 2009 16:13:14 -0800
Subject: x86 PAT: remove CPA WARN_ON for zero pte
Impact: reduce scope of debug check - avoid warnings
The logic to find whether identity map exists or not using
high_memory or max_low_pfn_mapped/max_pfn_mapped are not complete
as the memory withing the range may not be mapped if there is a
unusable hole in e820.
Specifically, on my test system I started seeing these warnings with
tools like hwinfo, acpidump trying to map ACPI region.
[ 27.400018] ------------[ cut here ]------------
[ 27.400344] WARNING: at /home/venkip/src/linus/linux-2.6/arch/x86/mm/pageattr.c:560 __change_page_attr_set_clr+0xf3/0x8b8()
[ 27.400821] Hardware name: X7DB8
[ 27.401070] CPA: called for zero pte. vaddr = ffff8800cff6a000 cpa->vaddr = ffff8800cff6a000
[ 27.401569] Modules linked in:
[ 27.401882] Pid: 4913, comm: dmidecode Not tainted 2.6.28-05716-gfe0bdec #586
[ 27.402141] Call Trace:
[ 27.402488] [<ffffffff80237c21>] warn_slowpath+0xd3/0x10f
[ 27.402749] [<ffffffff80274ade>] ? find_get_page+0xb3/0xc9
[ 27.403028] [<ffffffff80274a2b>] ? find_get_page+0x0/0xc9
[ 27.403333] [<ffffffff80226425>] __change_page_attr_set_clr+0xf3/0x8b8
[ 27.403628] [<ffffffff8028ec99>] ? __purge_vmap_area_lazy+0x192/0x1a1
[ 27.403883] [<ffffffff8028eb52>] ? __purge_vmap_area_lazy+0x4b/0x1a1
[ 27.404172] [<ffffffff80290268>] ? vm_unmap_aliases+0x1ab/0x1bb
[ 27.404512] [<ffffffff80290105>] ? vm_unmap_aliases+0x48/0x1bb
[ 27.404766] [<ffffffff80226d28>] change_page_attr_set_clr+0x13e/0x2e6
[ 27.405026] [<ffffffff80698fa7>] ? _spin_unlock+0x26/0x2a
[ 27.405292] [<ffffffff80227e6a>] ? reserve_memtype+0x19b/0x4e3
[ 27.405590] [<ffffffff80226ffd>] _set_memory_wb+0x22/0x24
[ 27.405844] [<ffffffff80225d28>] ioremap_change_attr+0x26/0x28
[ 27.406097] [<ffffffff80228355>] reserve_pfn_range+0x1a3/0x235
[ 27.406427] [<ffffffff80228430>] track_pfn_vma_new+0x49/0xb3
[ 27.406686] [<ffffffff80286c46>] remap_pfn_range+0x94/0x32c
[ 27.406940] [<ffffffff8022878d>] ? phys_mem_access_prot_allowed+0xb5/0x1a8
[ 27.407209] [<ffffffff803e9bf4>] mmap_mem+0x75/0x9d
[ 27.407523] [<ffffffff8028b3b4>] mmap_region+0x2cf/0x53e
[ 27.407776] [<ffffffff8028b8cc>] do_mmap_pgoff+0x2a9/0x30d
[ 27.408034] [<ffffffff8020f4a4>] sys_mmap+0x92/0xce
[ 27.408339] [<ffffffff8020b65b>] system_call_fastpath+0x16/0x1b
[ 27.408614] ---[ end trace 4b16ad70c09a602d ]---
[ 27.408871] dmidecode:4913 reserve_pfn_range ioremap_change_attr failed write-back for cff6a000-cff6b000
This is wih track_pfn_vma_new trying to keep identity map in sync.
The address cff6a000 is the ACPI region according to e820.
[ 0.000000] BIOS-provided physical RAM map:
[ 0.000000] BIOS-e820: 0000000000000000 - 000000000009c000 (usable)
[ 0.000000] BIOS-e820: 000000000009c000 - 00000000000a0000 (reserved)
[ 0.000000] BIOS-e820: 00000000000cc000 - 00000000000d0000 (reserved)
[ 0.000000] BIOS-e820: 00000000000e4000 - 0000000000100000 (reserved)
[ 0.000000] BIOS-e820: 0000000000100000 - 00000000cff60000 (usable)
[ 0.000000] BIOS-e820: 00000000cff60000 - 00000000cff69000 (ACPI data)
[ 0.000000] BIOS-e820: 00000000cff69000 - 00000000cff80000 (ACPI NVS)
[ 0.000000] BIOS-e820: 00000000cff80000 - 00000000d0000000 (reserved)
[ 0.000000] BIOS-e820: 00000000e0000000 - 00000000f0000000 (reserved)
[ 0.000000] BIOS-e820: 00000000fec00000 - 00000000fec10000 (reserved)
[ 0.000000] BIOS-e820: 00000000fee00000 - 00000000fee01000 (reserved)
[ 0.000000] BIOS-e820: 00000000ff000000 - 0000000100000000 (reserved)
[ 0.000000] BIOS-e820: 0000000100000000 - 0000000230000000 (usable)
And is not mapped as per init_memory_mapping.
[ 0.000000] init_memory_mapping: 0000000000000000-00000000cff60000
[ 0.000000] init_memory_mapping: 0000000100000000-0000000230000000
We can add logic to check for this. But, there can also be other holes in
identity map when we have 1GB of aligned reserved space in e820.
This patch handles it by removing the WARN_ON and returning a specific
error value (EFAULT) to indicate that the address does not have any
identity mapping.
The code that tries to keep identity map in sync can ignore
this error, with other callers of cpa still getting error here.
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/mm/pageattr.c | 10 ++++++----
arch/x86/mm/pat.c | 45 ++++++++++++++++++++++++++++++++-------------
2 files changed, 38 insertions(+), 17 deletions(-)
(limited to 'arch/x86/mm')
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index e89d24815f2..4cf30dee816 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -555,10 +555,12 @@ repeat:
if (!pte_val(old_pte)) {
if (!primary)
return 0;
- WARN(1, KERN_WARNING "CPA: called for zero pte. "
- "vaddr = %lx cpa->vaddr = %lx\n", address,
- *cpa->vaddr);
- return -EINVAL;
+
+ /*
+ * Special error value returned, indicating that the mapping
+ * did not exist at this address.
+ */
+ return -EFAULT;
}
if (level == PG_LEVEL_4K) {
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 8b08fb95527..160c42d3eb8 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -505,6 +505,35 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
}
#endif /* CONFIG_STRICT_DEVMEM */
+/*
+ * Change the memory type for the physial address range in kernel identity
+ * mapping space if that range is a part of identity map.
+ */
+static int kernel_map_sync_memtype(u64 base, unsigned long size,
+ unsigned long flags)
+{
+ unsigned long id_sz;
+ int ret;
+
+ if (!pat_enabled || base >= __pa(high_memory))
+ return 0;
+
+ id_sz = (__pa(high_memory) < base + size) ?
+ __pa(high_memory) - base :
+ size;
+
+ ret = ioremap_change_attr((unsigned long)__va(base), id_sz, flags);
+ /*
+ * -EFAULT return means that the addr was not valid and did not have
+ * any identity mapping. That case is a success for
+ * kernel_map_sync_memtype.
+ */
+ if (ret == -EFAULT)
+ ret = 0;
+
+ return ret;
+}
+
int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t *vma_prot)
{
@@ -555,9 +584,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
if (retval < 0)
return 0;
- 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) {
+ if (kernel_map_sync_memtype(offset, size, flags)) {
free_memtype(offset, offset + size);
printk(KERN_INFO
"%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n",
@@ -605,7 +632,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
int strict_prot)
{
int is_ram = 0;
- int id_sz, ret;
+ int ret;
unsigned long flags;
unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
@@ -646,15 +673,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
flags);
}
- /* Need to keep identity mapping in sync */
- if (paddr >= __pa(high_memory))
- return 0;
-
- id_sz = (__pa(high_memory) < paddr + size) ?
- __pa(high_memory) - paddr :
- size;
-
- if (ioremap_change_attr((unsigned long)__va(paddr), id_sz, flags) < 0) {
+ if (kernel_map_sync_memtype(paddr, size, flags)) {
free_memtype(paddr, paddr + size);
printk(KERN_ERR
"%s:%d reserve_pfn_range ioremap_change_attr failed %s "
--
cgit v1.2.3-70-g09d2
From 5cca0cf15a94417f49625ce52e23589eed0a1675 Mon Sep 17 00:00:00 2001
From: Suresh Siddha <suresh.b.siddha@intel.com>
Date: Fri, 9 Jan 2009 14:35:20 -0800
Subject: x86, pat: fix reserve_memtype() for legacy 1MB range
Thierry Vignaud reported:
> http://bugzilla.kernel.org/show_bug.cgi?id=12372
>
> On P4 with an SiS motherboard (video card is a SiS 651)
> X server fails to start with error:
> xf86MapVidMem: Could not mmap framebuffer (0x00000000,0x2000) (Invalid
> argument)
Here X is trying to map first 8KB of memory using /dev/mem. Existing
code treats first 0-4KB of memory as non-RAM and 4KB-8KB as RAM. Recent
code changes don't allow to map memory with different attributes
at the same time.
Fix this by treating the first 1MB legacy region as special and always
track the attribute requests with in this region using linear linked
list (and don't bother if the range is RAM or non-RAM or mixed)
Reported-and-tested-by: Thierry Vignaud <tvignaud@mandriva.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/mm/pat.c | 37 +++++++++++++++++++++++++++----------
1 file changed, 27 insertions(+), 10 deletions(-)
(limited to 'arch/x86/mm')
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 85cbd3cd372..070ee4a3b22 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -333,11 +333,20 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
req_type & _PAGE_CACHE_MASK);
}
- is_range_ram = pagerange_is_ram(start, end);
- if (is_range_ram == 1)
- return reserve_ram_pages_type(start, end, req_type, new_type);
- else if (is_range_ram < 0)
- return -EINVAL;
+ /*
+ * For legacy reasons, some parts of the physical address range in the
+ * legacy 1MB region is treated as non-RAM (even when listed as RAM in
+ * the e820 tables). So we will track the memory attributes of this
+ * legacy 1MB region using the linear memtype_list always.
+ */
+ if (end >= ISA_END_ADDRESS) {
+ is_range_ram = pagerange_is_ram(start, end);
+ if (is_range_ram == 1)
+ return reserve_ram_pages_type(start, end, req_type,
+ new_type);
+ else if (is_range_ram < 0)
+ return -EINVAL;
+ }
new = kmalloc(sizeof(struct memtype), GFP_KERNEL);
if (!new)
@@ -437,11 +446,19 @@ int free_memtype(u64 start, u64 end)
if (is_ISA_range(start, end - 1))
return 0;
- is_range_ram = pagerange_is_ram(start, end);
- if (is_range_ram == 1)
- return free_ram_pages_type(start, end);
- else if (is_range_ram < 0)
- return -EINVAL;
+ /*
+ * For legacy reasons, some parts of the physical address range in the
+ * legacy 1MB region is treated as non-RAM (even when listed as RAM in
+ * the e820 tables). So we will track the memory attributes of this
+ * legacy 1MB region using the linear memtype_list always.
+ */
+ if (end >= ISA_END_ADDRESS) {
+ is_range_ram = pagerange_is_ram(start, end);
+ if (is_range_ram == 1)
+ return free_ram_pages_type(start, end);
+ else if (is_range_ram < 0)
+ return -EINVAL;
+ }
spin_lock(&memtype_lock);
list_for_each_entry(entry, &memtype_list, nd) {
--
cgit v1.2.3-70-g09d2