From 592091c0e21655bfbdf68741dd5a920c2ac2bbe6 Mon Sep 17 00:00:00 2001
From: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Date: Tue, 31 Aug 2010 09:13:33 +0900
Subject: therm_throt.c: Trivial printk message fix for a unsuitable
abbreviation of 'thermal'
In unexpected_thermal_interrupt(), "LVT TMR interrupt" is used
in error message.
I don't think TMR is a suitable abbreviation for thermal.
1.TMR has been used in IA32 Architectures Software Developer's
Manual, and is the abbreviation for Trigger Mode Register.
2.There is not an standard abbreviation "TMR" defined for thermal
in IA32 Architectures Software Developer's Manual.
3.Though we could understand it as Thermal Monitor Register, it is
easy to be misunderstood as a *TIMER* interrupt also.
I think this patch will fix it.
Signed-off-by: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Reviewed-by: Jean Delvare <khali@linux-fr.org>
Cc: Brown Len <len.brown@intel.com>
Cc: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
LKML-Reference: <4C7C492D.5020704@np.css.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/therm_throt.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index c2a8b26d4fea..1d0f743c9d6e 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -348,7 +348,7 @@ static void intel_thermal_interrupt(void)
static void unexpected_thermal_interrupt(void)
{
- printk(KERN_ERR "CPU%d: Unexpected LVT TMR interrupt!\n",
+ printk(KERN_ERR "CPU%d: Unexpected LVT thermal interrupt!\n",
smp_processor_id());
add_taint(TAINT_MACHINE_CHECK);
}
--
cgit v1.2.2
From 6038f373a3dc1f1c26496e60b6c40b164716f07e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Sun, 15 Aug 2010 18:52:59 +0200
Subject: llseek: automatically add .llseek fop
All file_operations should get a .llseek operation so we can make
nonseekable_open the default for future file operations without a
.llseek pointer.
The three cases that we can automatically detect are no_llseek, seq_lseek
and default_llseek. For cases where we can we can automatically prove that
the file offset is always ignored, we use noop_llseek, which maintains
the current behavior of not returning an error from a seek.
New drivers should normally not use noop_llseek but instead use no_llseek
and call nonseekable_open at open time. Existing drivers can be converted
to do the same when the maintainer knows for certain that no user code
relies on calling seek on the device file.
The generated code is often incorrectly indented and right now contains
comments that clarify for each added line why a specific variant was
chosen. In the version that gets submitted upstream, the comments will
be gone and I will manually fix the indentation, because there does not
seem to be a way to do that using coccinelle.
Some amount of new code is currently sitting in linux-next that should get
the same modifications, which I will do at the end of the merge window.
Many thanks to Julia Lawall for helping me learn to write a semantic
patch that does all this.
===== begin semantic patch =====
// This adds an llseek= method to all file operations,
// as a preparation for making no_llseek the default.
//
// The rules are
// - use no_llseek explicitly if we do nonseekable_open
// - use seq_lseek for sequential files
// - use default_llseek if we know we access f_pos
// - use noop_llseek if we know we don't access f_pos,
// but we still want to allow users to call lseek
//
@ open1 exists @
identifier nested_open;
@@
nested_open(...)
{
<+...
nonseekable_open(...)
...+>
}
@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}
@ read disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ read_no_fpos disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
... when != off
}
@ write @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ write_no_fpos @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
... when != off
}
@ fops0 @
identifier fops;
@@
struct file_operations fops = {
...
};
@ has_llseek depends on fops0 @
identifier fops0.fops;
identifier llseek_f;
@@
struct file_operations fops = {
...
.llseek = llseek_f,
...
};
@ has_read depends on fops0 @
identifier fops0.fops;
identifier read_f;
@@
struct file_operations fops = {
...
.read = read_f,
...
};
@ has_write depends on fops0 @
identifier fops0.fops;
identifier write_f;
@@
struct file_operations fops = {
...
.write = write_f,
...
};
@ has_open depends on fops0 @
identifier fops0.fops;
identifier open_f;
@@
struct file_operations fops = {
...
.open = open_f,
...
};
// use no_llseek if we call nonseekable_open
////////////////////////////////////////////
@ nonseekable1 depends on !has_llseek && has_open @
identifier fops0.fops;
identifier nso ~= "nonseekable_open";
@@
struct file_operations fops = {
... .open = nso, ...
+.llseek = no_llseek, /* nonseekable */
};
@ nonseekable2 depends on !has_llseek @
identifier fops0.fops;
identifier open.open_f;
@@
struct file_operations fops = {
... .open = open_f, ...
+.llseek = no_llseek, /* open uses nonseekable */
};
// use seq_lseek for sequential files
/////////////////////////////////////
@ seq depends on !has_llseek @
identifier fops0.fops;
identifier sr ~= "seq_read";
@@
struct file_operations fops = {
... .read = sr, ...
+.llseek = seq_lseek, /* we have seq_read */
};
// use default_llseek if there is a readdir
///////////////////////////////////////////
@ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier readdir_e;
@@
// any other fop is used that changes pos
struct file_operations fops = {
... .readdir = readdir_e, ...
+.llseek = default_llseek, /* readdir is present */
};
// use default_llseek if at least one of read/write touches f_pos
/////////////////////////////////////////////////////////////////
@ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read.read_f;
@@
// read fops use offset
struct file_operations fops = {
... .read = read_f, ...
+.llseek = default_llseek, /* read accesses f_pos */
};
@ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write.write_f;
@@
// write fops use offset
struct file_operations fops = {
... .write = write_f, ...
+ .llseek = default_llseek, /* write accesses f_pos */
};
// Use noop_llseek if neither read nor write accesses f_pos
///////////////////////////////////////////////////////////
@ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
identifier write_no_fpos.write_f;
@@
// write fops use offset
struct file_operations fops = {
...
.write = write_f,
.read = read_f,
...
+.llseek = noop_llseek, /* read and write both use no f_pos */
};
@ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write_no_fpos.write_f;
@@
struct file_operations fops = {
... .write = write_f, ...
+.llseek = noop_llseek, /* write uses no f_pos */
};
@ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
@@
struct file_operations fops = {
... .read = read_f, ...
+.llseek = noop_llseek, /* read uses no f_pos */
};
@ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
@@
struct file_operations fops = {
...
+.llseek = noop_llseek, /* no read or write fn */
};
===== End semantic patch =====
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Julia Lawall <julia@diku.dk>
Cc: Christoph Hellwig <hch@infradead.org>
---
arch/x86/kernel/cpu/mcheck/mce-severity.c | 1 +
arch/x86/kernel/cpu/mcheck/mce.c | 1 +
2 files changed, 2 insertions(+)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 8a85dd1b1aa1..1e8d66c1336a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -192,6 +192,7 @@ static const struct file_operations severities_coverage_fops = {
.release = seq_release,
.read = seq_read,
.write = severities_coverage_write,
+ .llseek = seq_lseek,
};
static int __init severities_debugfs_init(void)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index ed41562909fe..7a35b72d7c03 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1665,6 +1665,7 @@ struct file_operations mce_chrdev_ops = {
.read = mce_read,
.poll = mce_poll,
.unlocked_ioctl = mce_ioctl,
+ .llseek = no_llseek,
};
EXPORT_SYMBOL_GPL(mce_chrdev_ops);
--
cgit v1.2.2
From 27afdf2008da0b8878a73e32e4eb12381b84e224 Mon Sep 17 00:00:00 2001
From: Robert Richter <robert.richter@amd.com>
Date: Wed, 6 Oct 2010 12:27:54 +0200
Subject: apic, x86: Use BIOS settings for IBS and MCE threshold interrupt LVT
offsets
We want the BIOS to setup the EILVT APIC registers. The offsets
were hardcoded and BIOS settings were overwritten by the OS.
Now, the subsystems for MCE threshold and IBS determine the LVT
offset from the registers the BIOS has setup. If the BIOS setup
is buggy on a family 10h system, a workaround enables IBS. If
the OS determines an invalid register setup, a "[Firmware Bug]:
" error message is reported.
We need this change also for upcomming cpu families.
Signed-off-by: Robert Richter <robert.richter@amd.com>
LKML-Reference: <1286360874-1471-3-git-send-email-robert.richter@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/mce_amd.c | 27 ++++++++++++++++++++++++---
1 file changed, 24 insertions(+), 3 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 39aaee5c1ab2..80c482382d5c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -131,7 +131,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
u32 low = 0, high = 0, address = 0;
unsigned int bank, block;
struct thresh_restart tr;
- u8 lvt_off;
+ int lvt_off = -1;
+ u8 offset;
for (bank = 0; bank < NR_BANKS; ++bank) {
for (block = 0; block < NR_BLOCKS; ++block) {
@@ -162,8 +163,28 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
if (shared_bank[bank] && c->cpu_core_id)
break;
#endif
- lvt_off = setup_APIC_eilvt_mce(THRESHOLD_APIC_VECTOR,
- APIC_EILVT_MSG_FIX, 0);
+ offset = (high & MASK_LVTOFF_HI) >> 20;
+ if (lvt_off < 0) {
+ if (setup_APIC_eilvt(offset,
+ THRESHOLD_APIC_VECTOR,
+ APIC_EILVT_MSG_FIX, 0)) {
+ pr_err(FW_BUG "cpu %d, failed to "
+ "setup threshold interrupt "
+ "for bank %d, block %d "
+ "(MSR%08X=0x%x%08x)",
+ smp_processor_id(), bank, block,
+ address, high, low);
+ continue;
+ }
+ lvt_off = offset;
+ } else if (lvt_off != offset) {
+ pr_err(FW_BUG "cpu %d, invalid threshold "
+ "interrupt offset %d for bank %d,"
+ "block %d (MSR%08X=0x%x%08x)",
+ smp_processor_id(), lvt_off, bank,
+ block, address, high, low);
+ continue;
+ }
high &= ~MASK_LVTOFF_HI;
high |= lvt_off << 20;
--
cgit v1.2.2
From 9c37c9d89773ee9da9f6af28ee37d931bd045711 Mon Sep 17 00:00:00 2001
From: Robert Richter <robert.richter@amd.com>
Date: Mon, 25 Oct 2010 16:03:35 +0200
Subject: mce, amd: Implement mce_threshold_block_init() helper function
This patch adds a helper function for the initial setup of an
mce threshold block. The LVT offset is passed as argument. Also
making variable threshold_defaults local as it is only used in
function mce_amd_feature_init(). Function
threshold_restart_bank() is extended to setup the LVT offset,
the change is backward compatible. Thus, now there is only a
single wrmsrl() to setup the block.
Signed-off-by: Robert Richter <robert.richter@amd.com>
Acked-by: Borislav Petkov <borislav.petkov@amd.com>
LKML-Reference: <1288015419-29543-2-git-send-email-robert.richter@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/mce_amd.c | 48 ++++++++++++++++++++++--------------
1 file changed, 29 insertions(+), 19 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 80c482382d5c..f438318ee800 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -59,12 +59,6 @@ struct threshold_block {
struct list_head miscj;
};
-/* defaults used early on boot */
-static struct threshold_block threshold_defaults = {
- .interrupt_enable = 0,
- .threshold_limit = THRESHOLD_MAX,
-};
-
struct threshold_bank {
struct kobject *kobj;
struct threshold_block *blocks;
@@ -89,6 +83,8 @@ static void amd_threshold_interrupt(void);
struct thresh_restart {
struct threshold_block *b;
int reset;
+ int set_lvt_off;
+ int lvt_off;
u16 old_limit;
};
@@ -116,6 +112,12 @@ static void threshold_restart_bank(void *_tr)
(new_count & THRESHOLD_MAX);
}
+ if (tr->set_lvt_off) {
+ /* set new lvt offset */
+ mci_misc_hi &= ~MASK_LVTOFF_HI;
+ mci_misc_hi |= tr->lvt_off << 20;
+ }
+
tr->b->interrupt_enable ?
(mci_misc_hi = (mci_misc_hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) :
(mci_misc_hi &= ~MASK_INT_TYPE_HI);
@@ -124,13 +126,25 @@ static void threshold_restart_bank(void *_tr)
wrmsr(tr->b->address, mci_misc_lo, mci_misc_hi);
}
+static void mce_threshold_block_init(struct threshold_block *b, int offset)
+{
+ struct thresh_restart tr = {
+ .b = b,
+ .set_lvt_off = 1,
+ .lvt_off = offset,
+ };
+
+ b->threshold_limit = THRESHOLD_MAX;
+ threshold_restart_bank(&tr);
+};
+
/* cpu init entry point, called from mce.c with preempt off */
void mce_amd_feature_init(struct cpuinfo_x86 *c)
{
+ struct threshold_block b;
unsigned int cpu = smp_processor_id();
u32 low = 0, high = 0, address = 0;
unsigned int bank, block;
- struct thresh_restart tr;
int lvt_off = -1;
u8 offset;
@@ -186,16 +200,13 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
continue;
}
- high &= ~MASK_LVTOFF_HI;
- high |= lvt_off << 20;
- wrmsr(address, low, high);
-
- threshold_defaults.address = address;
- tr.b = &threshold_defaults;
- tr.reset = 0;
- tr.old_limit = 0;
- threshold_restart_bank(&tr);
+ memset(&b, 0, sizeof(b));
+ b.cpu = cpu;
+ b.bank = bank;
+ b.block = block;
+ b.address = address;
+ mce_threshold_block_init(&b, offset);
mce_threshold_vector = amd_threshold_interrupt;
}
}
@@ -298,9 +309,8 @@ store_interrupt_enable(struct threshold_block *b, const char *buf, size_t size)
b->interrupt_enable = !!new;
+ memset(&tr, 0, sizeof(tr));
tr.b = b;
- tr.reset = 0;
- tr.old_limit = 0;
smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
@@ -321,10 +331,10 @@ store_threshold_limit(struct threshold_block *b, const char *buf, size_t size)
if (new < 1)
new = 1;
+ memset(&tr, 0, sizeof(tr));
tr.old_limit = b->threshold_limit;
b->threshold_limit = new;
tr.b = b;
- tr.reset = 0;
smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
--
cgit v1.2.2
From 7203a0494084541575bac6dfc4e153f9e28869b8 Mon Sep 17 00:00:00 2001
From: Robert Richter <robert.richter@amd.com>
Date: Mon, 25 Oct 2010 16:03:36 +0200
Subject: mce, amd: Shorten local variables mci_misc_{hi,lo}
Shorten this variables to make later changes more readable.
Signed-off-by: Robert Richter <robert.richter@amd.com>
Acked-by: Borislav Petkov <borislav.petkov@amd.com>
LKML-Reference: <1288015419-29543-3-git-send-email-robert.richter@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/mce_amd.c | 26 +++++++++++++-------------
1 file changed, 13 insertions(+), 13 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index f438318ee800..eb771b9fc0cb 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -93,37 +93,37 @@ struct thresh_restart {
static void threshold_restart_bank(void *_tr)
{
struct thresh_restart *tr = _tr;
- u32 mci_misc_hi, mci_misc_lo;
+ u32 hi, lo;
- rdmsr(tr->b->address, mci_misc_lo, mci_misc_hi);
+ rdmsr(tr->b->address, lo, hi);
- if (tr->b->threshold_limit < (mci_misc_hi & THRESHOLD_MAX))
+ if (tr->b->threshold_limit < (hi & THRESHOLD_MAX))
tr->reset = 1; /* limit cannot be lower than err count */
if (tr->reset) { /* reset err count and overflow bit */
- mci_misc_hi =
- (mci_misc_hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
+ hi =
+ (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
(THRESHOLD_MAX - tr->b->threshold_limit);
} else if (tr->old_limit) { /* change limit w/o reset */
- int new_count = (mci_misc_hi & THRESHOLD_MAX) +
+ int new_count = (hi & THRESHOLD_MAX) +
(tr->old_limit - tr->b->threshold_limit);
- mci_misc_hi = (mci_misc_hi & ~MASK_ERR_COUNT_HI) |
+ hi = (hi & ~MASK_ERR_COUNT_HI) |
(new_count & THRESHOLD_MAX);
}
if (tr->set_lvt_off) {
/* set new lvt offset */
- mci_misc_hi &= ~MASK_LVTOFF_HI;
- mci_misc_hi |= tr->lvt_off << 20;
+ hi &= ~MASK_LVTOFF_HI;
+ hi |= tr->lvt_off << 20;
}
tr->b->interrupt_enable ?
- (mci_misc_hi = (mci_misc_hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) :
- (mci_misc_hi &= ~MASK_INT_TYPE_HI);
+ (hi = (hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) :
+ (hi &= ~MASK_INT_TYPE_HI);
- mci_misc_hi |= MASK_COUNT_EN_HI;
- wrmsr(tr->b->address, mci_misc_lo, mci_misc_hi);
+ hi |= MASK_COUNT_EN_HI;
+ wrmsr(tr->b->address, lo, hi);
}
static void mce_threshold_block_init(struct threshold_block *b, int offset)
--
cgit v1.2.2
From bbaff08dca3c34d0fb6b4c4051354184e33e3df8 Mon Sep 17 00:00:00 2001
From: Robert Richter <robert.richter@amd.com>
Date: Mon, 25 Oct 2010 16:03:37 +0200
Subject: mce, amd: Add helper functions to setup APIC
This patch reworks and cleans up mce_amd_feature_init() by
introducing helper functions to setup and check the LVT offset.
It also fixes line endings in pr_err() calls.
Signed-off-by: Robert Richter <robert.richter@amd.com>
Acked-by: Borislav Petkov <borislav.petkov@amd.com>
LKML-Reference: <1288015419-29543-4-git-send-email-robert.richter@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/mce_amd.c | 67 ++++++++++++++++++++----------------
1 file changed, 38 insertions(+), 29 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index eb771b9fc0cb..e316684f9ed7 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -31,8 +31,6 @@
#include <asm/mce.h>
#include <asm/msr.h>
-#define PFX "mce_threshold: "
-#define VERSION "version 1.1.1"
#define NR_BANKS 6
#define NR_BLOCKS 9
#define THRESHOLD_MAX 0xFFF
@@ -88,6 +86,27 @@ struct thresh_restart {
u16 old_limit;
};
+static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
+{
+ int msr = (hi & MASK_LVTOFF_HI) >> 20;
+
+ if (apic < 0) {
+ pr_err(FW_BUG "cpu %d, failed to setup threshold interrupt "
+ "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu,
+ b->bank, b->block, b->address, hi, lo);
+ return 0;
+ }
+
+ if (apic != msr) {
+ pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d "
+ "for bank %d, block %d (MSR%08X=0x%x%08x)\n",
+ b->cpu, apic, b->bank, b->block, b->address, hi, lo);
+ return 0;
+ }
+
+ return 1;
+};
+
/* must be called with correct cpu affinity */
/* Called via smp_call_function_single() */
static void threshold_restart_bank(void *_tr)
@@ -113,9 +132,11 @@ static void threshold_restart_bank(void *_tr)
}
if (tr->set_lvt_off) {
- /* set new lvt offset */
- hi &= ~MASK_LVTOFF_HI;
- hi |= tr->lvt_off << 20;
+ if (lvt_off_valid(tr->b, tr->lvt_off, lo, hi)) {
+ /* set new lvt offset */
+ hi &= ~MASK_LVTOFF_HI;
+ hi |= tr->lvt_off << 20;
+ }
}
tr->b->interrupt_enable ?
@@ -138,6 +159,15 @@ static void mce_threshold_block_init(struct threshold_block *b, int offset)
threshold_restart_bank(&tr);
};
+static int setup_APIC_mce(int reserved, int new)
+{
+ if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR,
+ APIC_EILVT_MSG_FIX, 0))
+ return new;
+
+ return reserved;
+}
+
/* cpu init entry point, called from mce.c with preempt off */
void mce_amd_feature_init(struct cpuinfo_x86 *c)
{
@@ -145,8 +175,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
unsigned int cpu = smp_processor_id();
u32 low = 0, high = 0, address = 0;
unsigned int bank, block;
- int lvt_off = -1;
- u8 offset;
+ int offset = -1;
for (bank = 0; bank < NR_BANKS; ++bank) {
for (block = 0; block < NR_BLOCKS; ++block) {
@@ -177,28 +206,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
if (shared_bank[bank] && c->cpu_core_id)
break;
#endif
- offset = (high & MASK_LVTOFF_HI) >> 20;
- if (lvt_off < 0) {
- if (setup_APIC_eilvt(offset,
- THRESHOLD_APIC_VECTOR,
- APIC_EILVT_MSG_FIX, 0)) {
- pr_err(FW_BUG "cpu %d, failed to "
- "setup threshold interrupt "
- "for bank %d, block %d "
- "(MSR%08X=0x%x%08x)",
- smp_processor_id(), bank, block,
- address, high, low);
- continue;
- }
- lvt_off = offset;
- } else if (lvt_off != offset) {
- pr_err(FW_BUG "cpu %d, invalid threshold "
- "interrupt offset %d for bank %d,"
- "block %d (MSR%08X=0x%x%08x)",
- smp_processor_id(), lvt_off, bank,
- block, address, high, low);
- continue;
- }
+ offset = setup_APIC_mce(offset,
+ (high & MASK_LVTOFF_HI) >> 20);
memset(&b, 0, sizeof(b));
b.cpu = cpu;
--
cgit v1.2.2
From 0a17941e71f089b128514f7b5b486e20072ca7dc Mon Sep 17 00:00:00 2001
From: Robert Richter <robert.richter@amd.com>
Date: Mon, 25 Oct 2010 16:03:38 +0200
Subject: mce, amd: Remove goto in threshold_create_device()
Removing the goto in threshold_create_device().
Signed-off-by: Robert Richter <robert.richter@amd.com>
Acked-by: Borislav Petkov <borislav.petkov@amd.com>
LKML-Reference: <1288015419-29543-5-git-send-email-robert.richter@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/mce_amd.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index e316684f9ed7..5bf2fac52aca 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -622,9 +622,9 @@ static __cpuinit int threshold_create_device(unsigned int cpu)
continue;
err = threshold_create_bank(cpu, bank);
if (err)
- goto out;
+ return err;
}
-out:
+
return err;
}
--
cgit v1.2.2
From 0a3aee0da4402aa19b66e458038533c896fb80c6 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Sat, 18 Dec 2010 16:28:55 +0100
Subject: x86: Use this_cpu_ops to optimize code
Go through x86 code and replace __get_cpu_var and get_cpu_var
instances that refer to a scalar and are not used for address
determinations.
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
arch/x86/kernel/cpu/mcheck/mce.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 7a35b72d7c03..0c746af6c5eb 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -326,7 +326,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
static int msr_to_offset(u32 msr)
{
- unsigned bank = __get_cpu_var(injectm.bank);
+ unsigned bank = __this_cpu_read(injectm.bank);
if (msr == rip_msr)
return offsetof(struct mce, ip);
@@ -346,7 +346,7 @@ static u64 mce_rdmsrl(u32 msr)
{
u64 v;
- if (__get_cpu_var(injectm).finished) {
+ if (__this_cpu_read(injectm.finished)) {
int offset = msr_to_offset(msr);
if (offset < 0)
@@ -369,7 +369,7 @@ static u64 mce_rdmsrl(u32 msr)
static void mce_wrmsrl(u32 msr, u64 v)
{
- if (__get_cpu_var(injectm).finished) {
+ if (__this_cpu_read(injectm.finished)) {
int offset = msr_to_offset(msr);
if (offset >= 0)
--
cgit v1.2.2
From 7b543a5334ff4ea2e3ad3b777fc23cdb8072a988 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Sat, 18 Dec 2010 16:30:05 +0100
Subject: x86: Replace uses of current_cpu_data with this_cpu ops
Replace all uses of current_cpu_data with this_cpu operations on the
per cpu structure cpu_info. The scala accesses are replaced with the
matching this_cpu ops which results in smaller and more efficient
code.
In the long run, it might be a good idea to remove cpu_data() macro
too and use per_cpu macro directly.
tj: updated description
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
arch/x86/kernel/cpu/mcheck/mce.c | 14 +++++++-------
arch/x86/kernel/cpu/mcheck/mce_intel.c | 2 +-
2 files changed, 8 insertions(+), 8 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 0c746af6c5eb..d916183b7f9c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1159,7 +1159,7 @@ static void mce_start_timer(unsigned long data)
WARN_ON(smp_processor_id() != data);
- if (mce_available(¤t_cpu_data)) {
+ if (mce_available(__this_cpu_ptr(&cpu_info))) {
machine_check_poll(MCP_TIMESTAMP,
&__get_cpu_var(mce_poll_banks));
}
@@ -1767,7 +1767,7 @@ static int mce_shutdown(struct sys_device *dev)
static int mce_resume(struct sys_device *dev)
{
__mcheck_cpu_init_generic();
- __mcheck_cpu_init_vendor(¤t_cpu_data);
+ __mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info));
return 0;
}
@@ -1775,7 +1775,7 @@ static int mce_resume(struct sys_device *dev)
static void mce_cpu_restart(void *data)
{
del_timer_sync(&__get_cpu_var(mce_timer));
- if (!mce_available(¤t_cpu_data))
+ if (!mce_available(__this_cpu_ptr(&cpu_info)))
return;
__mcheck_cpu_init_generic();
__mcheck_cpu_init_timer();
@@ -1790,7 +1790,7 @@ static void mce_restart(void)
/* Toggle features for corrected errors */
static void mce_disable_ce(void *all)
{
- if (!mce_available(¤t_cpu_data))
+ if (!mce_available(__this_cpu_ptr(&cpu_info)))
return;
if (all)
del_timer_sync(&__get_cpu_var(mce_timer));
@@ -1799,7 +1799,7 @@ static void mce_disable_ce(void *all)
static void mce_enable_ce(void *all)
{
- if (!mce_available(¤t_cpu_data))
+ if (!mce_available(__this_cpu_ptr(&cpu_info)))
return;
cmci_reenable();
cmci_recheck();
@@ -2022,7 +2022,7 @@ static void __cpuinit mce_disable_cpu(void *h)
unsigned long action = *(unsigned long *)h;
int i;
- if (!mce_available(¤t_cpu_data))
+ if (!mce_available(__this_cpu_ptr(&cpu_info)))
return;
if (!(action & CPU_TASKS_FROZEN))
@@ -2040,7 +2040,7 @@ static void __cpuinit mce_reenable_cpu(void *h)
unsigned long action = *(unsigned long *)h;
int i;
- if (!mce_available(¤t_cpu_data))
+ if (!mce_available(__this_cpu_ptr(&cpu_info)))
return;
if (!(action & CPU_TASKS_FROZEN))
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 6fcd0936194f..8694ef56459d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -130,7 +130,7 @@ void cmci_recheck(void)
unsigned long flags;
int banks;
- if (!mce_available(¤t_cpu_data) || !cmci_supported(&banks))
+ if (!mce_available(__this_cpu_ptr(&cpu_info)) || !cmci_supported(&banks))
return;
local_irq_save(flags);
machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
--
cgit v1.2.2
From 9e76a97efd31a08cb19d0ba12013b8fb4ad3e474 Mon Sep 17 00:00:00 2001
From: "R, Durgadoss" <durgadoss.r@intel.com>
Date: Mon, 3 Jan 2011 17:22:04 +0530
Subject: x86, hwmon: Add core threshold notification to therm_throt.c
This patch adds code to therm_throt.c to notify core thermal threshold
events. These thresholds are supported by the IA32_THERM_INTERRUPT register.
The status/log for the same is monitored using the IA32_THERM_STATUS register.
The necessary #defines are in msr-index.h. A call back is added to mce.h, to
further notify the thermal stack, about the threshold events.
Signed-off-by: Durgadoss R <durgadoss.r@intel.com>
LKML-Reference: <D6D887BA8C9DFF48B5233887EF04654105C1251710@bgsmsx502.gar.corp.intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
arch/x86/kernel/cpu/mcheck/therm_throt.c | 40 ++++++++++++++++++++++++++++++++
1 file changed, 40 insertions(+)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 4b683267eca5..e12246ff5aa6 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -53,8 +53,13 @@ struct thermal_state {
struct _thermal_state core_power_limit;
struct _thermal_state package_throttle;
struct _thermal_state package_power_limit;
+ struct _thermal_state core_thresh0;
+ struct _thermal_state core_thresh1;
};
+/* Callback to handle core threshold interrupts */
+int (*platform_thermal_notify)(__u64 msr_val);
+
static DEFINE_PER_CPU(struct thermal_state, thermal_state);
static atomic_t therm_throt_en = ATOMIC_INIT(0);
@@ -200,6 +205,22 @@ static int therm_throt_process(bool new_event, int event, int level)
return 0;
}
+static int thresh_event_valid(int event)
+{
+ struct _thermal_state *state;
+ unsigned int this_cpu = smp_processor_id();
+ struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu);
+ u64 now = get_jiffies_64();
+
+ state = (event == 0) ? &pstate->core_thresh0 : &pstate->core_thresh1;
+
+ if (time_before64(now, state->next_check))
+ return 0;
+
+ state->next_check = now + CHECK_INTERVAL;
+ return 1;
+}
+
#ifdef CONFIG_SYSFS
/* Add/Remove thermal_throttle interface for CPU device: */
static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev,
@@ -313,6 +334,22 @@ device_initcall(thermal_throttle_init_device);
#define PACKAGE_THROTTLED ((__u64)2 << 62)
#define PACKAGE_POWER_LIMIT ((__u64)3 << 62)
+static void notify_thresholds(__u64 msr_val)
+{
+ /* check whether the interrupt handler is defined;
+ * otherwise simply return
+ */
+ if (!platform_thermal_notify)
+ return;
+
+ /* lower threshold reached */
+ if ((msr_val & THERM_LOG_THRESHOLD0) && thresh_event_valid(0))
+ platform_thermal_notify(msr_val);
+ /* higher threshold reached */
+ if ((msr_val & THERM_LOG_THRESHOLD1) && thresh_event_valid(1))
+ platform_thermal_notify(msr_val);
+}
+
/* Thermal transition interrupt handler */
static void intel_thermal_interrupt(void)
{
@@ -321,6 +358,9 @@ static void intel_thermal_interrupt(void)
rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
+ /* Check for violation of core thermal thresholds*/
+ notify_thresholds(msr_val);
+
if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
THERMAL_THROTTLING_EVENT,
CORE_LEVEL) != 0)
--
cgit v1.2.2
From 166d751479c6d4e5b17dfc1f204a9c4397c9b3f1 Mon Sep 17 00:00:00 2001
From: Don Zickus <dzickus@redhat.com>
Date: Thu, 6 Jan 2011 16:18:49 -0500
Subject: x86, NMI: Add priorities to handlers
In order to consolidate the NMI die_chain events, we need to setup the priorities
for the die notifiers.
I started by defining a bunch of common priorities that can be used by the
notifier blocks. Then I modified the notifier blocks to use the newly created
priorities.
Now that the priorities are straightened out, it should be easier to remove the
event DIE_NMI_IPI.
Signed-off-by: Don Zickus <dzickus@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1294348732-15030-4-git-send-email-dzickus@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/mce-inject.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index e7dbde7bfedb..59546c1219f9 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -95,7 +95,7 @@ static int mce_raise_notify(struct notifier_block *self,
static struct notifier_block mce_raise_nb = {
.notifier_call = mce_raise_notify,
- .priority = 1000,
+ .priority = NMI_LOCAL_NORMAL_PRIOR,
};
/* Inject mce on current CPU */
--
cgit v1.2.2
From c410b8307702c1e1f35be3fd868ad18e4ba0410f Mon Sep 17 00:00:00 2001
From: Don Zickus <dzickus@redhat.com>
Date: Thu, 6 Jan 2011 16:18:50 -0500
Subject: x86, NMI: Remove DIE_NMI_IPI
With priorities in place and no one really understanding the difference between
DIE_NMI and DIE_NMI_IPI, just remove DIE_NMI_IPI and convert everyone to DIE_NMI.
This also simplifies default_do_nmi() a little bit. Instead of calling the
die_notifier in both the if and else part, just pull it out and call it before
the if-statement. This has the side benefit of avoiding a call to the ioport
to see if there is an external NMI sitting around until after the (more frequent)
internal NMIs are dealt with.
Patch-Inspired-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Don Zickus <dzickus@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1294348732-15030-5-git-send-email-dzickus@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/mce-inject.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 59546c1219f9..a77971979564 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -25,6 +25,7 @@
#include <linux/gfp.h>
#include <asm/mce.h>
#include <asm/apic.h>
+#include <asm/nmi.h>
/* Update fake mce registers on current CPU. */
static void inject_mce(struct mce *m)
@@ -83,7 +84,7 @@ static int mce_raise_notify(struct notifier_block *self,
struct die_args *args = (struct die_args *)data;
int cpu = smp_processor_id();
struct mce *m = &__get_cpu_var(injectm);
- if (val != DIE_NMI_IPI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
+ if (val != DIE_NMI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
return NOTIFY_DONE;
cpumask_clear_cpu(cpu, mce_inject_cpumask);
if (m->inject_flags & MCJ_EXCEPTION)
--
cgit v1.2.2
From f21bbec9ffcaf73e99938209e52b757d93f9133b Mon Sep 17 00:00:00 2001
From: Fenghua Yu <fenghua.yu@intel.com>
Date: Thu, 20 Jan 2011 20:12:40 -0800
Subject: x86, mcheck, therm_throt.c: Export symbol platform_thermal_notify to
allow coretemp to handler intr
In therm_throt.c, commit
9e76a97efd31a08cb19d0ba12013b8fb4ad3e474 patch doesn't export
the symbol platform_thermal_notify.
Other drivers (e.g. drivers/hwmon/coretemp.c) can not find the
symbol platform_thermal_notify when defining threshould
interrupt handler.
Please apply this patch to allow threshold interrupt handler in
coretemp.
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Cc: R Durgadoss <durgadoss.r@intel.com>
Cc: khali@linux-fr.org <khali@linux-fr.org>
Cc: lm-sensors@lm-sensors.org <lm-sensors@lm-sensors.org>
Cc: Guenter Roeck <guenter.roeck@ericsson.com>
LKML-Reference: <20110121041239.GB26954@linux-os.sc.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/therm_throt.c | 1 +
1 file changed, 1 insertion(+)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index e12246ff5aa6..6f8c5e9da97f 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -59,6 +59,7 @@ struct thermal_state {
/* Callback to handle core threshold interrupts */
int (*platform_thermal_notify)(__u64 msr_val);
+EXPORT_SYMBOL(platform_thermal_notify);
static DEFINE_PER_CPU(struct thermal_state, thermal_state);
--
cgit v1.2.2
From b3d7336db553d318e7ec042eb50a70d307013339 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Fri, 21 Jan 2011 15:29:44 -0800
Subject: x86: Move llc_shared_map out of cpu_info
cpu_info is already with per_cpu, We can take llc_shared_map out
of cpu_info, and declare it as per_cpu variable directly.
So later referencing could be simple and directly instead of
diving to find cpu_info at first.
Also could make smp_store_cpu_info() much simple to avoid to do
save and restore trick.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Hans Rosenfeld <hans.rosenfeld@amd.com>
Cc: Alok N Kataria <akataria@vmware.com>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: Hans J. Koch <hjk@linutronix.de>
Cc: Tejun Heo <tj@kernel.org>
Cc: Borislav Petkov <borislav.petkov@amd.com>
Cc: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
LKML-Reference: <4D3A16E8.5020608@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/mce_amd.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 5bf2fac52aca..167f97b5596e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -527,15 +527,12 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
int i, err = 0;
struct threshold_bank *b = NULL;
char name[32];
-#ifdef CONFIG_SMP
- struct cpuinfo_x86 *c = &cpu_data(cpu);
-#endif
sprintf(name, "threshold_bank%i", bank);
#ifdef CONFIG_SMP
if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */
- i = cpumask_first(c->llc_shared_map);
+ i = cpumask_first(cpu_llc_shared_mask(cpu));
/* first core not up yet */
if (cpu_data(i).cpu_core_id)
@@ -555,7 +552,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
if (err)
goto out;
- cpumask_copy(b->cpus, c->llc_shared_map);
+ cpumask_copy(b->cpus, cpu_llc_shared_mask(cpu));
per_cpu(threshold_banks, cpu)[bank] = b;
goto out;
--
cgit v1.2.2
From 0d2eb44f631d9d0a826efa3156f157477fdaecf4 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.de.marchi@gmail.com>
Date: Thu, 17 Mar 2011 16:24:16 -0300
Subject: x86: Fix common misspellings
They were generated by 'codespell' and then manually reviewed.
Signed-off-by: Lucas De Marchi <lucas.demarchi@profusion.mobi>
Cc: trivial@kernel.org
LKML-Reference: <1300389856-1099-3-git-send-email-lucas.demarchi@profusion.mobi>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/mce-inject.c | 2 +-
arch/x86/kernel/cpu/mcheck/mce.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index a77971979564..0ed633c5048b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -32,7 +32,7 @@ static void inject_mce(struct mce *m)
{
struct mce *i = &per_cpu(injectm, m->extcpu);
- /* Make sure noone reads partially written injectm */
+ /* Make sure no one reads partially written injectm */
i->finished = 0;
mb();
m->finished = 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index d916183b7f9c..ab1122998dba 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -881,7 +881,7 @@ reset:
* Check if the address reported by the CPU is in a format we can parse.
* It would be possible to add code for most other cases, but all would
* be somewhat complicated (e.g. segment offset would require an instruction
- * parser). So only support physical addresses upto page granuality for now.
+ * parser). So only support physical addresses up to page granuality for now.
*/
static int mce_usable_address(struct mce *m)
{
--
cgit v1.2.2
From 885b976fada5bc6595a9fd3e67e3cb1a3d11f50b Mon Sep 17 00:00:00 2001
From: Huang Ying <ying.huang@intel.com>
Date: Mon, 21 Feb 2011 13:54:41 +0800
Subject: ACPI, APEI, Add ERST record ID cache
APEI ERST firmware interface and implementation has no multiple users
in mind. For example, if there is four records in storage with ID: 1,
2, 3 and 4, if two ERST readers enumerate the records via
GET_NEXT_RECORD_ID as follow,
reader 1 reader 2
1
2
3
4
-1
-1
where -1 signals there is no more record ID.
Reader 1 has no chance to check record 2 and 4, while reader 2 has no
chance to check record 1 and 3. And any other GET_NEXT_RECORD_ID will
return -1, that is, other readers will has no chance to check any
record even they are not cleared by anyone.
This makes raw GET_NEXT_RECORD_ID not suitable for used by multiple
users.
To solve the issue, an in-memory ERST record ID cache is designed and
implemented. When enumerating record ID, the ID returned by
GET_NEXT_RECORD_ID is added into cache in addition to be returned to
caller. So other readers can check the cache to get all record ID
available.
Signed-off-by: Huang Ying <ying.huang@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
arch/x86/kernel/cpu/mcheck/mce-apei.c | 42 ++++++++++++++++++++++-------------
1 file changed, 26 insertions(+), 16 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index 8209472b27a5..83930deec3c6 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -106,24 +106,34 @@ int apei_write_mce(struct mce *m)
ssize_t apei_read_mce(struct mce *m, u64 *record_id)
{
struct cper_mce_record rcd;
- ssize_t len;
-
- len = erst_read_next(&rcd.hdr, sizeof(rcd));
- if (len <= 0)
- return len;
- /* Can not skip other records in storage via ERST unless clear them */
- else if (len != sizeof(rcd) ||
- uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE)) {
- if (printk_ratelimit())
- pr_warning(
- "MCE-APEI: Can not skip the unknown record in ERST");
- return -EIO;
- }
-
+ int rc, pos;
+
+ rc = erst_get_record_id_begin(&pos);
+ if (rc)
+ return rc;
+retry:
+ rc = erst_get_record_id_next(&pos, record_id);
+ if (rc)
+ goto out;
+ /* no more record */
+ if (*record_id == APEI_ERST_INVALID_RECORD_ID)
+ goto out;
+ rc = erst_read(*record_id, &rcd.hdr, sizeof(rcd));
+ /* someone else has cleared the record, try next one */
+ if (rc == -ENOENT)
+ goto retry;
+ else if (rc < 0)
+ goto out;
+ /* try to skip other type records in storage */
+ else if (rc != sizeof(rcd) ||
+ uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE))
+ goto retry;
memcpy(m, &rcd.mce, sizeof(*m));
- *record_id = rcd.hdr.record_id;
+ rc = sizeof(*m);
+out:
+ erst_get_record_id_end();
- return sizeof(*m);
+ return rc;
}
/* Check whether there is record in ERST */
--
cgit v1.2.2
From f3c6ea1b06c71b43f751b36bd99345369fe911af Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Wed, 23 Mar 2011 22:15:54 +0100
Subject: x86: Use syscore_ops instead of sysdev classes and sysdevs
Some subsystems in the x86 tree need to carry out suspend/resume and
shutdown operations with one CPU on-line and interrupts disabled and
they define sysdev classes and sysdevs or sysdev drivers for this
purpose. This leads to unnecessarily complicated code and excessive
memory usage, so switch them to using struct syscore_ops objects for
this purpose instead.
Generally, there are three categories of subsystems that use
sysdevs for implementing PM operations: (1) subsystems whose
suspend/resume callbacks ignore their arguments entirely (the
majority), (2) subsystems whose suspend/resume callbacks use their
struct sys_device argument, but don't really need to do that,
because they can be implemented differently in an arguably simpler
way (io_apic.c), and (3) subsystems whose suspend/resume callbacks
use their struct sys_device argument, but the value of that argument
is always the same and could be ignored (microcode_core.c). In all
of these cases the subsystems in question may be readily converted to
using struct syscore_ops objects for power management and shutdown.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/mce.c | 21 ++++++++++++---------
1 file changed, 12 insertions(+), 9 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index ab1122998dba..5a05ef63eb4a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -21,6 +21,7 @@
#include <linux/percpu.h>
#include <linux/string.h>
#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/delay.h>
#include <linux/ctype.h>
#include <linux/sched.h>
@@ -1749,14 +1750,14 @@ static int mce_disable_error_reporting(void)
return 0;
}
-static int mce_suspend(struct sys_device *dev, pm_message_t state)
+static int mce_suspend(void)
{
return mce_disable_error_reporting();
}
-static int mce_shutdown(struct sys_device *dev)
+static void mce_shutdown(void)
{
- return mce_disable_error_reporting();
+ mce_disable_error_reporting();
}
/*
@@ -1764,14 +1765,18 @@ static int mce_shutdown(struct sys_device *dev)
* Only one CPU is active at this time, the others get re-added later using
* CPU hotplug:
*/
-static int mce_resume(struct sys_device *dev)
+static void mce_resume(void)
{
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info));
-
- return 0;
}
+static struct syscore_ops mce_syscore_ops = {
+ .suspend = mce_suspend,
+ .shutdown = mce_shutdown,
+ .resume = mce_resume,
+};
+
static void mce_cpu_restart(void *data)
{
del_timer_sync(&__get_cpu_var(mce_timer));
@@ -1808,9 +1813,6 @@ static void mce_enable_ce(void *all)
}
static struct sysdev_class mce_sysclass = {
- .suspend = mce_suspend,
- .shutdown = mce_shutdown,
- .resume = mce_resume,
.name = "machinecheck",
};
@@ -2139,6 +2141,7 @@ static __init int mcheck_init_device(void)
return err;
}
+ register_syscore_ops(&mce_syscore_ops);
register_hotcpu_notifier(&mce_cpu_notifier);
misc_register(&mce_log_device);
--
cgit v1.2.2
From fe5042138b6fc60edde3b60025078884c2eb71ac Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@linux.com>
Date: Sat, 12 Mar 2011 12:50:46 +0100
Subject: x86: Use this_cpu_has for thermal_interrupt current cpu
It is more effective to use a segment prefix instead of calculating the
address of the current cpu area amd then testing flags.
Signed-off-by: Christoph Lameter <cl@linux.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
arch/x86/kernel/cpu/mcheck/therm_throt.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 6f8c5e9da97f..6b0f4cde7a22 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -355,7 +355,6 @@ static void notify_thresholds(__u64 msr_val)
static void intel_thermal_interrupt(void)
{
__u64 msr_val;
- struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
@@ -367,19 +366,19 @@ static void intel_thermal_interrupt(void)
CORE_LEVEL) != 0)
mce_log_therm_throt_event(CORE_THROTTLED | msr_val);
- if (cpu_has(c, X86_FEATURE_PLN))
+ if (this_cpu_has(X86_FEATURE_PLN))
if (therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
POWER_LIMIT_EVENT,
CORE_LEVEL) != 0)
mce_log_therm_throt_event(CORE_POWER_LIMIT | msr_val);
- if (cpu_has(c, X86_FEATURE_PTS)) {
+ if (this_cpu_has(X86_FEATURE_PTS)) {
rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT,
THERMAL_THROTTLING_EVENT,
PACKAGE_LEVEL) != 0)
mce_log_therm_throt_event(PACKAGE_THROTTLED | msr_val);
- if (cpu_has(c, X86_FEATURE_PLN))
+ if (this_cpu_has(X86_FEATURE_PLN))
if (therm_throt_process(msr_val &
PACKAGE_THERM_STATUS_POWER_LIMIT,
POWER_LIMIT_EVENT,
--
cgit v1.2.2
From a4dd99250dc49031e6a92a895dbcc230a4832083 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 1 Apr 2011 07:15:14 -0700
Subject: rcu: create new rcu_access_index() and use in mce
The MCE subsystem needs to sample an RCU-protected index outside of
any protection for that index. If this was a pointer, we would use
rcu_access_pointer(), but there is no corresponding rcu_access_index().
This commit therefore creates an rcu_access_index() and applies it
to MCE.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Zdenek Kabelac <zkabelac@redhat.com>
---
arch/x86/kernel/cpu/mcheck/mce.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 5a05ef63eb4a..3385ea26f684 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1626,7 +1626,7 @@ out:
static unsigned int mce_poll(struct file *file, poll_table *wait)
{
poll_wait(file, &mce_wait, wait);
- if (rcu_dereference_check_mce(mcelog.next))
+ if (rcu_access_index(mcelog.next))
return POLLIN | POLLRDNORM;
if (!mce_apei_read_done && apei_check_mce())
return POLLIN | POLLRDNORM;
--
cgit v1.2.2
From 7b70bd3441437b7bc04fc9d321e17c8ed0e8f958 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <borislav.petkov@amd.com>
Date: Mon, 18 Apr 2011 16:00:21 +0200
Subject: x86, MCE: Do not taint when handling correctable errors
Correctable errors are considered something rather normal on
modern hardware these days. Even more importantly, correctable
errors mean exactly that - they've been corrected by the
hardware - and there's no need to taint the kernel since
execution hasn't been compromised so far.
Also, drop tainting in the thermal throttling code for a similar
reason: crossing a thermal threshold does not mean corruption.
Signed-off-by: Borislav Petkov <borislav.petkov@amd.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Acked-by: Nagananda Chumbalkar <Nagananda.Chumbalkar@hp.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Russ Anderson <rja@sgi.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1303135222-17118-1-git-send-email-bp@amd64.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/mce.c | 1 -
arch/x86/kernel/cpu/mcheck/therm_throt.c | 3 ---
2 files changed, 4 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 3385ea26f684..68e230327d65 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -590,7 +590,6 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) {
mce_log(&m);
atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, &m);
- add_taint(TAINT_MACHINE_CHECK);
}
/*
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 6f8c5e9da97f..5846a797b970 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -187,8 +187,6 @@ static int therm_throt_process(bool new_event, int event, int level)
this_cpu,
level == CORE_LEVEL ? "Core" : "Package",
state->count);
-
- add_taint(TAINT_MACHINE_CHECK);
return 1;
}
if (old_event) {
@@ -393,7 +391,6 @@ static void unexpected_thermal_interrupt(void)
{
printk(KERN_ERR "CPU%d: Unexpected LVT thermal interrupt!\n",
smp_processor_id());
- add_taint(TAINT_MACHINE_CHECK);
}
static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;
--
cgit v1.2.2
From dffa4b2f62ff28c982144c7033001b1ece4d3532 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <borislav.petkov@amd.com>
Date: Wed, 20 Apr 2011 12:23:49 +0200
Subject: x86, mce: Drop the default decoding notifier
The default notifier doesn't make a lot of sense to call in the
correctable errors case. Drop it and emit the mcelog decoding
hint only in the uncorrectable errors case and when no notifier
is registered. Also, limit issuing the "mcelog --ascii" message
in the rare case when we dump unreported CEs before panicking.
While at it, remove unused old x86_mce_decode_callback from the
header.
Signed-off-by: Borislav Petkov <borislav.petkov@amd.com>
Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Nagananda Chumbalkar <Nagananda.Chumbalkar@hp.com>
Cc: Russ Anderson <rja@sgi.com>
Link: http://lkml.kernel.org/r/20110420102349.GB1361@aftab
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/mce.c | 24 +++++++-----------------
1 file changed, 7 insertions(+), 17 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 68e230327d65..ff1ae9b6464d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -105,20 +105,6 @@ static int cpu_missing;
ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
EXPORT_SYMBOL_GPL(x86_mce_decoder_chain);
-static int default_decode_mce(struct notifier_block *nb, unsigned long val,
- void *data)
-{
- pr_emerg(HW_ERR "No human readable MCE decoding support on this CPU type.\n");
- pr_emerg(HW_ERR "Run the message through 'mcelog --ascii' to decode.\n");
-
- return NOTIFY_STOP;
-}
-
-static struct notifier_block mce_dec_nb = {
- .notifier_call = default_decode_mce,
- .priority = -1,
-};
-
/* MCA banks polled by the period polling timer for corrected events */
DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
@@ -212,6 +198,8 @@ void mce_log(struct mce *mce)
static void print_mce(struct mce *m)
{
+ int ret = 0;
+
pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n",
m->extcpu, m->mcgstatus, m->bank, m->status);
@@ -239,7 +227,11 @@ static void print_mce(struct mce *m)
* Print out human-readable details about the MCE error,
* (if the CPU has an implementation for that)
*/
- atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
+ ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
+ if (ret == NOTIFY_STOP)
+ return;
+
+ pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
}
#define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -1721,8 +1713,6 @@ __setup("mce", mcheck_enable);
int __init mcheck_init(void)
{
- atomic_notifier_chain_register(&x86_mce_decoder_chain, &mce_dec_nb);
-
mcheck_intel_therm_init();
return 0;
--
cgit v1.2.2
From d9a5ac9ef306eb5cc874f285185a15c303c50009 Mon Sep 17 00:00:00 2001
From: Julia Lawall <julia@diku.dk>
Date: Fri, 13 May 2011 15:52:09 +0200
Subject: x86, mce, AMD: Fix leaving freed data in a list
b may be added to a list, but is not removed before being freed
in the case of an error. This is done in the corresponding
deallocation function, so the code here has been changed to
follow that.
The sematic match that finds this problem is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@@
expression E,E1,E2;
identifier l;
@@
*list_add(&E->l,E1);
... when != E1
when != list_del(&E->l)
when != list_del_init(&E->l)
when != E = E2
*kfree(E);// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Cc: Borislav Petkov <borislav.petkov@amd.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: <stable@kernel.org>
Link: http://lkml.kernel.org/r/1305294731-12127-1-git-send-email-julia@diku.dk
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/mce_amd.c | 1 +
1 file changed, 1 insertion(+)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 167f97b5596e..bb0adad35143 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -509,6 +509,7 @@ recurse:
out_free:
if (b) {
kobject_put(&b->kobj);
+ list_del(&b->miscj);
kfree(b);
}
return err;
--
cgit v1.2.2
From e503f9e4b092e2349a9477a333543de8f3c7f5d9 Mon Sep 17 00:00:00 2001
From: Youquan Song <youquan.song@intel.com>
Date: Fri, 22 Apr 2011 00:22:43 +0800
Subject: x86, apic: Fix spurious error interrupts triggering on all non-boot
APs
This patch fixes a bug reported by a customer, who found
that many unreasonable error interrupts reported on all
non-boot CPUs (APs) during the system boot stage.
According to Chapter 10 of Intel Software Developer Manual
Volume 3A, Local APIC may signal an illegal vector error when
an LVT entry is set as an illegal vector value (0~15) under
FIXED delivery mode (bits 8-11 is 0), regardless of whether
the mask bit is set or an interrupt actually happen. These
errors are seen as error interrupts.
The initial value of thermal LVT entries on all APs always reads
0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI
sequence to them and LVT registers are reset to 0s except for
the mask bits which are set to 1s when APs receive INIT IPI.
When the BIOS takes over the thermal throttling interrupt,
the LVT thermal deliver mode should be SMI and it is required
from the kernel to keep AP's LVT thermal monitoring register
programmed as such as well.
This issue happens when BIOS does not take over thermal throttling
interrupt, AP's LVT thermal monitor register will be restored to
0x10000 which means vector 0 and fixed deliver mode, so all APs will
signal illegal vector error interrupts.
This patch check if interrupt delivery mode is not fixed mode before
restoring AP's LVT thermal monitor register.
Signed-off-by: Youquan Song <youquan.song@intel.com>
Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>
Acked-by: Yong Wang <yong.y.wang@intel.com>
Cc: hpa@linux.intel.com
Cc: joe@perches.com
Cc: jbaron@redhat.com
Cc: trenn@suse.de
Cc: kent.liu@intel.com
Cc: chaohong.guo@intel.com
Cc: <stable@kernel.org> # As far back as possible
Link: http://lkml.kernel.org/r/1303402963-17738-1-git-send-email-youquan.song@intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/cpu/mcheck/therm_throt.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
(limited to 'arch/x86/kernel/cpu/mcheck')
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 6f8c5e9da97f..0f034460260d 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -446,18 +446,20 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
*/
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
+ h = lvtthmr_init;
/*
* The initial value of thermal LVT entries on all APs always reads
* 0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI
* sequence to them and LVT registers are reset to 0s except for
* the mask bits which are set to 1s when APs receive INIT IPI.
- * Always restore the value that BIOS has programmed on AP based on
- * BSP's info we saved since BIOS is always setting the same value
- * for all threads/cores
+ * If BIOS takes over the thermal interrupt and sets its interrupt
+ * delivery mode to SMI (not fixed), it restores the value that the
+ * BIOS has programmed on AP based on BSP's info we saved since BIOS
+ * is always setting the same value for all threads/cores.
*/
- apic_write(APIC_LVTTHMR, lvtthmr_init);
+ if ((h & APIC_DM_FIXED_MASK) != APIC_DM_FIXED)
+ apic_write(APIC_LVTTHMR, lvtthmr_init);
- h = lvtthmr_init;
if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
printk(KERN_DEBUG
--
cgit v1.2.2