hello,
Resend these two patches for bug fixing:
The bug is that when memory hotplug-adding happens for a large enough area that a new PGD entry is
needed for the direct mapping, the PGDs of other processes would not get updated. This leads to some
CPUs oopsing when they have to access the unmapped areas, e.g. onlining CPUs on the new added node.
Thanks!
---
From 04d9fc860db40f15ad629f8b341ff84b83a00a8d Mon Sep 17 00:00:00 2001
From: Haicheng Li <[email protected]>
Date: Wed, 19 May 2010 17:42:14 +0800
Subject: [PATCH] x86, mem-hotplug: separate x86_64 vmalloc_sync_all() into separate functions
No behavior change here.
Move some of vmalloc_sync_all() code into a new function
sync_global_pgds() that will be useful for memory hotplug.
Signed-off-by: Haicheng Li <[email protected]>
Reviewed-by: Wu Fengguang <[email protected]>
CC: Andi Kleen <[email protected]>
---
arch/x86/include/asm/pgtable_64.h | 2 ++
arch/x86/mm/fault.c | 24 +-----------------------
arch/x86/mm/init_64.c | 30 ++++++++++++++++++++++++++++++
3 files changed, 33 insertions(+), 23 deletions(-)
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 181be52..317026d 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -102,6 +102,8 @@ static inline void native_pgd_clear(pgd_t *pgd)
native_set_pgd(pgd, native_make_pgd(0));
}
+extern void sync_global_pgds(unsigned long start, unsigned long end);
+
/*
* Conversion functions: convert a page and protection to a page entry,
* and a page entry and page directory to the page they refer to.
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index f627779..7ae0897 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -326,29 +326,7 @@ out:
void vmalloc_sync_all(void)
{
- unsigned long address;
-
- for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
- address += PGDIR_SIZE) {
-
- const pgd_t *pgd_ref = pgd_offset_k(address);
- unsigned long flags;
- struct page *page;
-
- if (pgd_none(*pgd_ref))
- continue;
-
- spin_lock_irqsave(&pgd_lock, flags);
- list_for_each_entry(page, &pgd_list, lru) {
- pgd_t *pgd;
- pgd = (pgd_t *)page_address(page) + pgd_index(address);
- if (pgd_none(*pgd))
- set_pgd(pgd, *pgd_ref);
- else
- BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
- }
- spin_unlock_irqrestore(&pgd_lock, flags);
- }
+ sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
}
/*
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index ee41bba..b0c3df0 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -98,6 +98,36 @@ static int __init nonx32_setup(char *str)
__setup("noexec32=", nonx32_setup);
/*
+ * When memory was added/removed make sure all the processes MM have
+ * suitable PGD entries in the local PGD level page.
+ */
+void sync_global_pgds(unsigned long start, unsigned long end)
+{
+ unsigned long address;
+
+ for (address = start; address <= end; address += PGDIR_SIZE) {
+ const pgd_t *pgd_ref = pgd_offset_k(address);
+ unsigned long flags;
+ struct page *page;
+
+ if (pgd_none(*pgd_ref))
+ continue;
+
+ spin_lock_irqsave(&pgd_lock, flags);
+ list_for_each_entry(page, &pgd_list, lru) {
+ pgd_t *pgd;
+ pgd = (pgd_t *)page_address(page) + pgd_index(address);
+ if (pgd_none(*pgd))
+ set_pgd(pgd, *pgd_ref);
+ else
+ BUG_ON(pgd_page_vaddr(*pgd)
+ != pgd_page_vaddr(*pgd_ref));
+ }
+ spin_unlock_irqrestore(&pgd_lock, flags);
+ }
+}
+
+/*
* NOTE: This function is marked __ref because it calls __init function
* (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
*/
--
1.5.6.1
x86, mem-hotplug: update all PGDs for direct mapping and vmemmap mapping changes on 64bit.
When memory hotplug-adding happens for a large enough area
that a new PGD entry is needed for the direct mapping, the PGDs
of other processes would not get updated. This leads to some CPUs
oopsing like below when they have to access the unmapped areas.
[ 1139.243192] BUG: soft lockup - CPU#0 stuck for 61s! [bash:6534]
[ 1139.243195] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc
dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc
lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib
i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore
[ 1139.243229] irq event stamp: 8538759
[ 1139.243230] hardirqs last enabled at (8538759): [<ffffffff8100c3fc>] restore_args+0x0/0x30
[ 1139.243236] hardirqs last disabled at (8538757): [<ffffffff810422df>] __do_softirq+0x106/0x146
[ 1139.243240] softirqs last enabled at (8538758): [<ffffffff81042310>] __do_softirq+0x137/0x146
[ 1139.243245] softirqs last disabled at (8538743): [<ffffffff8100cb5c>] call_softirq+0x1c/0x34
[ 1139.243249] CPU 0:
[ 1139.243250] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc
dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc
lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib
i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore
[ 1139.243284] Pid: 6534, comm: bash Tainted: G M 2.6.32-haicheng-cpuhp #7 QSSC-S4R
[ 1139.243287] RIP: 0010:[<ffffffff810ace35>] [<ffffffff810ace35>] alloc_arraycache+0x35/0x69
[ 1139.243292] RSP: 0018:ffff8802799f9d78 EFLAGS: 00010286
[ 1139.243295] RAX: ffff8884ffc00000 RBX: ffff8802799f9d98 RCX: 0000000000000000
[ 1139.243297] RDX: 0000000000190018 RSI: 0000000000000001 RDI: ffff8884ffc00010
[ 1139.243300] RBP: ffffffff8100c34e R08: 0000000000000002 R09: 0000000000000000
[ 1139.243303] R10: ffffffff8246dda0 R11: 000000d08246dda0 R12: ffff8802599bfff0
[ 1139.243305] R13: ffff88027904c040 R14: ffff8802799f8000 R15: 0000000000000001
[ 1139.243308] FS: 00007fe81bfe86e0(0000) GS:ffff88000d800000(0000) knlGS:0000000000000000
[ 1139.243311] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1139.243313] CR2: ffff8884ffc00000 CR3: 000000026cf2d000 CR4: 00000000000006f0
[ 1139.243316] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 1139.243318] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[ 1139.243321] Call Trace:
[ 1139.243324] [<ffffffff810ace29>] ? alloc_arraycache+0x29/0x69
[ 1139.243328] [<ffffffff8135004e>] ? cpuup_callback+0x1b0/0x32a
[ 1139.243333] [<ffffffff8105385d>] ? notifier_call_chain+0x33/0x5b
[ 1139.243337] [<ffffffff810538a4>] ? __raw_notifier_call_chain+0x9/0xb
[ 1139.243340] [<ffffffff8134ecfc>] ? cpu_up+0xb3/0x152
[ 1139.243344] [<ffffffff813388ce>] ? store_online+0x4d/0x75
[ 1139.243348] [<ffffffff811e53f3>] ? sysdev_store+0x1b/0x1d
[ 1139.243351] [<ffffffff8110589f>] ? sysfs_write_file+0xe5/0x121
[ 1139.243355] [<ffffffff810b539d>] ? vfs_write+0xae/0x14a
[ 1139.243358] [<ffffffff810b587f>] ? sys_write+0x47/0x6f
[ 1139.243362] [<ffffffff8100b9ab>] ? system_call_fastpath+0x16/0x1b
This patch makes sure to always replicate new direct mapping PGD entries
to the PGDs of all processes, as well as ensures corresponding vmemmap
mapping gets synced.
V1: initial code by Andi Kleen.
V2: fix several issues found in testing.
V3: as suggested by Wu Fengguang, reuse common code of vmalloc_sync_all().
Signed-off-by: Andi Kleen <[email protected]>
Signed-off-by: Haicheng Li <[email protected]>
Reviewed-by: Wu Fengguang <[email protected]>
---
arch/x86/mm/init_64.c | 8 +++++++-
1 files changed, 7 insertions(+), 1 deletions(-)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b0c3df0..fa72b4b 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -564,11 +564,13 @@ kernel_physical_mapping_init(unsigned long start,
unsigned long end,
unsigned long page_size_mask)
{
-
+ int pgd_changed = 0;
unsigned long next, last_map_addr = end;
+ unsigned long addr;
start = (unsigned long)__va(start);
end = (unsigned long)__va(end);
+ addr = start;
for (; start < end; start = next) {
pgd_t *pgd = pgd_offset_k(start);
@@ -593,7 +595,10 @@ kernel_physical_mapping_init(unsigned long start,
spin_lock(&init_mm.page_table_lock);
pgd_populate(&init_mm, pgd, __va(pud_phys));
spin_unlock(&init_mm.page_table_lock);
+ pgd_changed = 1;
}
+ if (pgd_changed)
+ sync_global_pgds(addr, end);
__flush_tlb_all();
return last_map_addr;
@@ -1033,6 +1038,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
}
}
+ sync_global_pgds((unsigned long)start_page, end);
return 0;
}
--
1.5.6.1
Haicheng Li <[email protected]> writes:
> hello,
>
> Resend these two patches for bug fixing:
>
> The bug is that when memory hotplug-adding happens for a large enough area that a new PGD entry is
> needed for the direct mapping, the PGDs of other processes would not get updated. This leads to some
> CPUs oopsing when they have to access the unmapped areas, e.g. onlining CPUs on the new added node.
The patches look good to me. Can we please move forward with this?
Reviewed-by: Andi Kleen <[email protected]>
-Andi
--
[email protected] -- Speaking for myself only.
On 08/25/2010 12:45 AM, Andi Kleen wrote:
> Haicheng Li <[email protected]> writes:
>
>> hello,
>>
>> Resend these two patches for bug fixing:
>>
>> The bug is that when memory hotplug-adding happens for a large enough area that a new PGD entry is
>> needed for the direct mapping, the PGDs of other processes would not get updated. This leads to some
>> CPUs oopsing when they have to access the unmapped areas, e.g. onlining CPUs on the new added node.
>
> The patches look good to me. Can we please move forward with this?
>
> Reviewed-by: Andi Kleen <[email protected]>
>
The patches are mangled so they don't apply even with patch -l --
Haicheng, could you send me another copy, as an attachment if necessary?
-hpa
On 08/25/2010 12:14 PM, H. Peter Anvin wrote:
>
> The patches are mangled so they don't apply even with patch -l --
> Haicheng, could you send me another copy, as an attachment if necessary?
>
Never mind, I fixed them up by hand.
-hpa
Commit-ID: 7b61b1ccb1a84c3391360ac94c908bfbbb35299c
Gitweb: http://git.kernel.org/tip/7b61b1ccb1a84c3391360ac94c908bfbbb35299c
Author: Haicheng Li <[email protected]>
AuthorDate: Wed, 19 May 2010 17:42:14 +0800
Committer: H. Peter Anvin <[email protected]>
CommitDate: Wed, 25 Aug 2010 13:47:14 -0700
x86, mm: Separate x86_64 vmalloc_sync_all() into separate functions
No behavior change.
Move some of vmalloc_sync_all() code into a new function
sync_global_pgds() that will be useful for memory hotplug.
Signed-off-by: Haicheng Li <[email protected]>
LKML-Reference: <[email protected]>
Reviewed-by: Wu Fengguang <[email protected]>
Reviewed-by: Andi Kleen <[email protected]>
Signed-off-by: H. Peter Anvin <[email protected]>
Commit-ID: f4a9f26dd0041423da94bb22dfed742540915487
Gitweb: http://git.kernel.org/tip/f4a9f26dd0041423da94bb22dfed742540915487
Author: Haicheng Li <[email protected]>
AuthorDate: Fri, 20 Aug 2010 17:50:16 +0800
Committer: H. Peter Anvin <[email protected]>
CommitDate: Wed, 25 Aug 2010 14:01:03 -0700
x86-64, mem: Update all PGDs for direct mapping and vmemmap mapping changes
When memory hotplug-adding happens for a large enough area
that a new PGD entry is needed for the direct mapping, the PGDs
of other processes would not get updated. This leads to some CPUs
oopsing like below when they have to access the unmapped areas.
[ 1139.243192] BUG: soft lockup - CPU#0 stuck for 61s! [bash:6534]
[ 1139.243195] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc
dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc
lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib
i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore
[ 1139.243229] irq event stamp: 8538759
[ 1139.243230] hardirqs last enabled at (8538759): [<ffffffff8100c3fc>] restore_args+0x0/0x30
[ 1139.243236] hardirqs last disabled at (8538757): [<ffffffff810422df>] __do_softirq+0x106/0x146
[ 1139.243240] softirqs last enabled at (8538758): [<ffffffff81042310>] __do_softirq+0x137/0x146
[ 1139.243245] softirqs last disabled at (8538743): [<ffffffff8100cb5c>] call_softirq+0x1c/0x34
[ 1139.243249] CPU 0:
[ 1139.243250] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc
dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc
lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib
i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore
[ 1139.243284] Pid: 6534, comm: bash Tainted: G M 2.6.32-haicheng-cpuhp #7 QSSC-S4R
[ 1139.243287] RIP: 0010:[<ffffffff810ace35>] [<ffffffff810ace35>] alloc_arraycache+0x35/0x69
[ 1139.243292] RSP: 0018:ffff8802799f9d78 EFLAGS: 00010286
[ 1139.243295] RAX: ffff8884ffc00000 RBX: ffff8802799f9d98 RCX: 0000000000000000
[ 1139.243297] RDX: 0000000000190018 RSI: 0000000000000001 RDI: ffff8884ffc00010
[ 1139.243300] RBP: ffffffff8100c34e R08: 0000000000000002 R09: 0000000000000000
[ 1139.243303] R10: ffffffff8246dda0 R11: 000000d08246dda0 R12: ffff8802599bfff0
[ 1139.243305] R13: ffff88027904c040 R14: ffff8802799f8000 R15: 0000000000000001
[ 1139.243308] FS: 00007fe81bfe86e0(0000) GS:ffff88000d800000(0000) knlGS:0000000000000000
[ 1139.243311] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1139.243313] CR2: ffff8884ffc00000 CR3: 000000026cf2d000 CR4: 00000000000006f0
[ 1139.243316] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 1139.243318] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[ 1139.243321] Call Trace:
[ 1139.243324] [<ffffffff810ace29>] ? alloc_arraycache+0x29/0x69
[ 1139.243328] [<ffffffff8135004e>] ? cpuup_callback+0x1b0/0x32a
[ 1139.243333] [<ffffffff8105385d>] ? notifier_call_chain+0x33/0x5b
[ 1139.243337] [<ffffffff810538a4>] ? __raw_notifier_call_chain+0x9/0xb
[ 1139.243340] [<ffffffff8134ecfc>] ? cpu_up+0xb3/0x152
[ 1139.243344] [<ffffffff813388ce>] ? store_online+0x4d/0x75
[ 1139.243348] [<ffffffff811e53f3>] ? sysdev_store+0x1b/0x1d
[ 1139.243351] [<ffffffff8110589f>] ? sysfs_write_file+0xe5/0x121
[ 1139.243355] [<ffffffff810b539d>] ? vfs_write+0xae/0x14a
[ 1139.243358] [<ffffffff810b587f>] ? sys_write+0x47/0x6f
[ 1139.243362] [<ffffffff8100b9ab>] ? system_call_fastpath+0x16/0x1b
This patch makes sure to always replicate new direct mapping PGD entries
to the PGDs of all processes, as well as ensures corresponding vmemmap
mapping gets synced.
V1: initial code by Andi Kleen.
V2: fix several issues found in testing.
V3: as suggested by Wu Fengguang, reuse common code of vmalloc_sync_all().
[ hpa: changed pgd_change from int to bool ]
Originally-by: Andi Kleen <[email protected]>
Signed-off-by: Haicheng Li <[email protected]>
LKML-Reference: <[email protected]>
Reviewed-by: Wu Fengguang <[email protected]>
Reviewed-by: Andi Kleen <[email protected]>
Signed-off-by: H. Peter Anvin <[email protected]>
---
arch/x86/mm/init_64.c | 9 ++++++++-
1 files changed, 8 insertions(+), 1 deletions(-)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9a66746..de852ad 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -534,8 +534,9 @@ kernel_physical_mapping_init(unsigned long start,
unsigned long end,
unsigned long page_size_mask)
{
-
+ bool pgd_changed = false;
unsigned long next, last_map_addr = end;
+ unsigned long addr;
start = (unsigned long)__va(start);
end = (unsigned long)__va(end);
@@ -563,7 +564,12 @@ kernel_physical_mapping_init(unsigned long start,
spin_lock(&init_mm.page_table_lock);
pgd_populate(&init_mm, pgd, __va(pud_phys));
spin_unlock(&init_mm.page_table_lock);
+ pgd_changed = true;
}
+
+ if (pgd_changed)
+ sync_global_pgds(addr, end);
+
__flush_tlb_all();
return last_map_addr;
@@ -1003,6 +1009,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
}
}
+ sync_global_pgds((unsigned long)start_page, end);
return 0;
}
Commit-ID: 9b861528a8012e7bc4d1f7bae07395b225331477
Gitweb: http://git.kernel.org/tip/9b861528a8012e7bc4d1f7bae07395b225331477
Author: Haicheng Li <[email protected]>
AuthorDate: Fri, 20 Aug 2010 17:50:16 +0800
Committer: H. Peter Anvin <[email protected]>
CommitDate: Thu, 26 Aug 2010 14:02:33 -0700
x86-64, mem: Update all PGDs for direct mapping and vmemmap mapping changes
When memory hotplug-adding happens for a large enough area
that a new PGD entry is needed for the direct mapping, the PGDs
of other processes would not get updated. This leads to some CPUs
oopsing like below when they have to access the unmapped areas.
[ 1139.243192] BUG: soft lockup - CPU#0 stuck for 61s! [bash:6534]
[ 1139.243195] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc
dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc
lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib
i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore
[ 1139.243229] irq event stamp: 8538759
[ 1139.243230] hardirqs last enabled at (8538759): [<ffffffff8100c3fc>] restore_args+0x0/0x30
[ 1139.243236] hardirqs last disabled at (8538757): [<ffffffff810422df>] __do_softirq+0x106/0x146
[ 1139.243240] softirqs last enabled at (8538758): [<ffffffff81042310>] __do_softirq+0x137/0x146
[ 1139.243245] softirqs last disabled at (8538743): [<ffffffff8100cb5c>] call_softirq+0x1c/0x34
[ 1139.243249] CPU 0:
[ 1139.243250] Modules linked in: ipv6 autofs4 rfcomm l2cap crc16 bluetooth rfkill binfmt_misc
dm_mirror dm_region_hash dm_log dm_multipath dm_mod video output sbs sbshc fan battery ac parport_pc
lp parport joydev usbhid processor thermal thermal_sys container button rtc_cmos rtc_core rtc_lib
i2c_i801 i2c_core pcspkr uhci_hcd ohci_hcd ehci_hcd usbcore
[ 1139.243284] Pid: 6534, comm: bash Tainted: G M 2.6.32-haicheng-cpuhp #7 QSSC-S4R
[ 1139.243287] RIP: 0010:[<ffffffff810ace35>] [<ffffffff810ace35>] alloc_arraycache+0x35/0x69
[ 1139.243292] RSP: 0018:ffff8802799f9d78 EFLAGS: 00010286
[ 1139.243295] RAX: ffff8884ffc00000 RBX: ffff8802799f9d98 RCX: 0000000000000000
[ 1139.243297] RDX: 0000000000190018 RSI: 0000000000000001 RDI: ffff8884ffc00010
[ 1139.243300] RBP: ffffffff8100c34e R08: 0000000000000002 R09: 0000000000000000
[ 1139.243303] R10: ffffffff8246dda0 R11: 000000d08246dda0 R12: ffff8802599bfff0
[ 1139.243305] R13: ffff88027904c040 R14: ffff8802799f8000 R15: 0000000000000001
[ 1139.243308] FS: 00007fe81bfe86e0(0000) GS:ffff88000d800000(0000) knlGS:0000000000000000
[ 1139.243311] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1139.243313] CR2: ffff8884ffc00000 CR3: 000000026cf2d000 CR4: 00000000000006f0
[ 1139.243316] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 1139.243318] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[ 1139.243321] Call Trace:
[ 1139.243324] [<ffffffff810ace29>] ? alloc_arraycache+0x29/0x69
[ 1139.243328] [<ffffffff8135004e>] ? cpuup_callback+0x1b0/0x32a
[ 1139.243333] [<ffffffff8105385d>] ? notifier_call_chain+0x33/0x5b
[ 1139.243337] [<ffffffff810538a4>] ? __raw_notifier_call_chain+0x9/0xb
[ 1139.243340] [<ffffffff8134ecfc>] ? cpu_up+0xb3/0x152
[ 1139.243344] [<ffffffff813388ce>] ? store_online+0x4d/0x75
[ 1139.243348] [<ffffffff811e53f3>] ? sysdev_store+0x1b/0x1d
[ 1139.243351] [<ffffffff8110589f>] ? sysfs_write_file+0xe5/0x121
[ 1139.243355] [<ffffffff810b539d>] ? vfs_write+0xae/0x14a
[ 1139.243358] [<ffffffff810b587f>] ? sys_write+0x47/0x6f
[ 1139.243362] [<ffffffff8100b9ab>] ? system_call_fastpath+0x16/0x1b
This patch makes sure to always replicate new direct mapping PGD entries
to the PGDs of all processes, as well as ensures corresponding vmemmap
mapping gets synced.
V1: initial code by Andi Kleen.
V2: fix several issues found in testing.
V3: as suggested by Wu Fengguang, reuse common code of vmalloc_sync_all().
[ hpa: changed pgd_change from int to bool ]
Originally-by: Andi Kleen <[email protected]>
Signed-off-by: Haicheng Li <[email protected]>
LKML-Reference: <[email protected]>
Reviewed-by: Wu Fengguang <[email protected]>
Reviewed-by: Andi Kleen <[email protected]>
Signed-off-by: H. Peter Anvin <[email protected]>
---
arch/x86/mm/init_64.c | 9 ++++++++-
1 files changed, 8 insertions(+), 1 deletions(-)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 61a1b4f..64e7bc2 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -564,8 +564,9 @@ kernel_physical_mapping_init(unsigned long start,
unsigned long end,
unsigned long page_size_mask)
{
-
+ bool pgd_changed = false;
unsigned long next, last_map_addr = end;
+ unsigned long addr;
start = (unsigned long)__va(start);
end = (unsigned long)__va(end);
@@ -593,7 +594,12 @@ kernel_physical_mapping_init(unsigned long start,
spin_lock(&init_mm.page_table_lock);
pgd_populate(&init_mm, pgd, __va(pud_phys));
spin_unlock(&init_mm.page_table_lock);
+ pgd_changed = true;
}
+
+ if (pgd_changed)
+ sync_global_pgds(addr, end);
+
__flush_tlb_all();
return last_map_addr;
@@ -1033,6 +1039,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
}
}
+ sync_global_pgds((unsigned long)start_page, end);
return 0;
}
Commit-ID: 6afb5157b9eba4092e2f0f54d24a3806409bdde5
Gitweb: http://git.kernel.org/tip/6afb5157b9eba4092e2f0f54d24a3806409bdde5
Author: Haicheng Li <[email protected]>
AuthorDate: Wed, 19 May 2010 17:42:14 +0800
Committer: H. Peter Anvin <[email protected]>
CommitDate: Thu, 26 Aug 2010 14:02:29 -0700
x86, mm: Separate x86_64 vmalloc_sync_all() into separate functions
No behavior change.
Move some of vmalloc_sync_all() code into a new function
sync_global_pgds() that will be useful for memory hotplug.
Signed-off-by: Haicheng Li <[email protected]>
LKML-Reference: <[email protected]>
Reviewed-by: Wu Fengguang <[email protected]>
Reviewed-by: Andi Kleen <[email protected]>
Signed-off-by: H. Peter Anvin <[email protected]>
---
arch/x86/include/asm/pgtable_64.h | 2 ++
arch/x86/mm/fault.c | 24 +-----------------------
arch/x86/mm/init_64.c | 30 ++++++++++++++++++++++++++++++
3 files changed, 33 insertions(+), 23 deletions(-)
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 076052c..f96ac9b 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -102,6 +102,8 @@ static inline void native_pgd_clear(pgd_t *pgd)
native_set_pgd(pgd, native_make_pgd(0));
}
+extern void sync_global_pgds(unsigned long start, unsigned long end);
+
/*
* Conversion functions: convert a page and protection to a page entry,
* and a page entry and page directory to the page they refer to.
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 4c4508e..51f7ee7 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -326,29 +326,7 @@ out:
void vmalloc_sync_all(void)
{
- unsigned long address;
-
- for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
- address += PGDIR_SIZE) {
-
- const pgd_t *pgd_ref = pgd_offset_k(address);
- unsigned long flags;
- struct page *page;
-
- if (pgd_none(*pgd_ref))
- continue;
-
- spin_lock_irqsave(&pgd_lock, flags);
- list_for_each_entry(page, &pgd_list, lru) {
- pgd_t *pgd;
- pgd = (pgd_t *)page_address(page) + pgd_index(address);
- if (pgd_none(*pgd))
- set_pgd(pgd, *pgd_ref);
- else
- BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
- }
- spin_unlock_irqrestore(&pgd_lock, flags);
- }
+ sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
}
/*
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9a66746..61a1b4f 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -98,6 +98,36 @@ static int __init nonx32_setup(char *str)
__setup("noexec32=", nonx32_setup);
/*
+ * When memory was added/removed make sure all the processes MM have
+ * suitable PGD entries in the local PGD level page.
+ */
+void sync_global_pgds(unsigned long start, unsigned long end)
+{
+ unsigned long address;
+
+ for (address = start; address <= end; address += PGDIR_SIZE) {
+ const pgd_t *pgd_ref = pgd_offset_k(address);
+ unsigned long flags;
+ struct page *page;
+
+ if (pgd_none(*pgd_ref))
+ continue;
+
+ spin_lock_irqsave(&pgd_lock, flags);
+ list_for_each_entry(page, &pgd_list, lru) {
+ pgd_t *pgd;
+ pgd = (pgd_t *)page_address(page) + pgd_index(address);
+ if (pgd_none(*pgd))
+ set_pgd(pgd, *pgd_ref);
+ else
+ BUG_ON(pgd_page_vaddr(*pgd)
+ != pgd_page_vaddr(*pgd_ref));
+ }
+ spin_unlock_irqrestore(&pgd_lock, flags);
+ }
+}
+
+/*
* NOTE: This function is marked __ref because it calls __init function
* (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
*/