From c1e7c3ae59b065bf7ff24a05cb609b2f9e314db6 Mon Sep 17 00:00:00 2001
From: Phillip Lougher <phillip@lougher.demon.co.uk>
Date: Mon, 14 Dec 2009 21:45:19 +0000
Subject: [PATCH 01/16] bzip2/lzma/gzip: pre-boot malloc doesn't return NULL on
failure
The trivial malloc implementation used in the pre-boot environment by the
decompressors returns a bad pointer on failure (falling through after
calling error). This is doubly wrong - the callers expect malloc to
return NULL on failure, second the error function is intended to be
used by the decompressors to propagate errors to *their* callers. The
decompressors have no access to any state set by the error function.
Signed-off-by: Phillip Lougher <phillip@lougher.demon.co.uk>
LKML-Reference: <4b26b1ef.hIInb2AYPMtImAJO%phillip@lougher.demon.co.uk>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
include/linux/decompress/mm.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/linux/decompress/mm.h b/include/linux/decompress/mm.h
index 12ff8c3f1d05..5032b9a31ae7 100644
--- a/include/linux/decompress/mm.h
+++ b/include/linux/decompress/mm.h
@@ -25,7 +25,7 @@ static void *malloc(int size)
void *p;
if (size < 0)
- error("Malloc error");
+ return NULL;
if (!malloc_ptr)
malloc_ptr = free_mem_ptr;
@@ -35,7 +35,7 @@ static void *malloc(int size)
malloc_ptr += size;
if (free_mem_end_ptr && malloc_ptr >= free_mem_end_ptr)
- error("Out of memory");
+ return NULL;
malloc_count++;
return p;
From d4529862cae4de19fda8d4bbcbddc60f3e48a4cf Mon Sep 17 00:00:00 2001
From: Phillip Lougher <phillip@lougher.demon.co.uk>
Date: Mon, 14 Dec 2009 21:45:19 +0000
Subject: [PATCH 02/16] bzip2: Add missing checks for malloc returning NULL
Signed-off-by: Phillip Lougher <phillip@lougher.demon.co.uk>
LKML-Reference: <4b26b1ef.ln20bM9Mn4gzB21L%phillip@lougher.demon.co.uk>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
lib/decompress_bunzip2.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index 76074209f9a2..a4e971dee102 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -637,6 +637,8 @@ static int INIT start_bunzip(struct bunzip_data **bdp, void *inbuf, int len,
/* Allocate bunzip_data. Most fields initialize to zero. */
bd = *bdp = malloc(i);
+ if (!bd)
+ return RETVAL_OUT_OF_MEMORY;
memset(bd, 0, sizeof(struct bunzip_data));
/* Setup input buffer */
bd->inbuf = inbuf;
@@ -664,6 +666,8 @@ static int INIT start_bunzip(struct bunzip_data **bdp, void *inbuf, int len,
bd->dbufSize = 100000*(i-BZh0);
bd->dbuf = large_malloc(bd->dbufSize * sizeof(int));
+ if (!bd->dbuf)
+ return RETVAL_OUT_OF_MEMORY;
return RETVAL_OK;
}
@@ -686,7 +690,7 @@ STATIC int INIT bunzip2(unsigned char *buf, int len,
if (!outbuf) {
error("Could not allocate output bufer");
- return -1;
+ return RETVAL_OUT_OF_MEMORY;
}
if (buf)
inbuf = buf;
@@ -694,6 +698,7 @@ STATIC int INIT bunzip2(unsigned char *buf, int len,
inbuf = malloc(BZIP2_IOBUF_SIZE);
if (!inbuf) {
error("Could not allocate input bufer");
+ i = RETVAL_OUT_OF_MEMORY;
goto exit_0;
}
i = start_bunzip(&bd, inbuf, len, fill);
@@ -720,11 +725,14 @@ STATIC int INIT bunzip2(unsigned char *buf, int len,
} else if (i == RETVAL_UNEXPECTED_OUTPUT_EOF) {
error("Compressed file ends unexpectedly");
}
+ if (!bd)
+ goto exit_1;
if (bd->dbuf)
large_free(bd->dbuf);
if (pos)
*pos = bd->inbufPos;
free(bd);
+exit_1:
if (!buf)
free(inbuf);
exit_0:
From 54291362d2a5738e1b0495df2abcb9e6b0563a3f Mon Sep 17 00:00:00 2001
From: Phillip Lougher <phillip@lougher.demon.co.uk>
Date: Mon, 14 Dec 2009 21:45:19 +0000
Subject: [PATCH 03/16] initramfs: add missing decompressor error check
The decompressors return error by calling a supplied error function, and/or
by returning an error return value. The initramfs code, however, fails to
check the exit code returned by the decompressor, and only checks the error
status set by calling the error function.
This patch adds a return code check and calls the error function.
Signed-off-by: Phillip Lougher <phillip@lougher.demon.co.uk>
LKML-Reference: <4b26b1ef.0+ZWxT6886olqcSc%phillip@lougher.demon.co.uk>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
init/initramfs.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/init/initramfs.c b/init/initramfs.c
index 4c00edc59689..b37d34beb90b 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -413,7 +413,7 @@ static unsigned my_inptr; /* index of next byte to be processed in inbuf */
static char * __init unpack_to_rootfs(char *buf, unsigned len)
{
- int written;
+ int written, res;
decompress_fn decompress;
const char *compress_name;
static __initdata char msg_buf[64];
@@ -445,10 +445,12 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len)
}
this_header = 0;
decompress = decompress_method(buf, len, &compress_name);
- if (decompress)
- decompress(buf, len, NULL, flush_buffer, NULL,
+ if (decompress) {
+ res = decompress(buf, len, NULL, flush_buffer, NULL,
&my_inptr, error);
- else if (compress_name) {
+ if (res)
+ error("decompressor failed");
+ } else if (compress_name) {
if (!message) {
snprintf(msg_buf, sizeof msg_buf,
"compression method %s not configured",
From 0b962d473af32ec334df271b54ff4973cb2b4c73 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@zytor.com>
Date: Tue, 15 Dec 2009 15:13:07 -0800
Subject: [PATCH 04/16] x86, msr/cpuid: Register enough minors for the MSR and
CPUID drivers
register_chrdev() hardcodes registering 256 minors, presumably to
avoid breaking old drivers. However, we need to register enough
minors so that we have all possible CPUs.
checkpatch warns on this patch, but the patch is correct: NR_CPUS here
is a static *upper bound* on the *maximum CPU index* (not *number of
CPUs!*) and that is what we want.
Reported-and-tested-by: Russ Anderson <rja@sgi.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
LKML-Reference: <tip-*@git.kernel.org>
---
arch/x86/kernel/cpuid.c | 5 +++--
arch/x86/kernel/msr.c | 4 ++--
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 7ef24a796992..cb27fd6136c9 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -187,7 +187,8 @@ static int __init cpuid_init(void)
int i, err = 0;
i = 0;
- if (register_chrdev(CPUID_MAJOR, "cpu/cpuid", &cpuid_fops)) {
+ if (__register_chrdev(CPUID_MAJOR, 0, NR_CPUS,
+ "cpu/cpuid", &cpuid_fops)) {
printk(KERN_ERR "cpuid: unable to get major %d for cpuid\n",
CPUID_MAJOR);
err = -EBUSY;
@@ -216,7 +217,7 @@ out_class:
}
class_destroy(cpuid_class);
out_chrdev:
- unregister_chrdev(CPUID_MAJOR, "cpu/cpuid");
+ __unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
out:
return err;
}
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 572b07eee3f4..4bd93c9b2b27 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -246,7 +246,7 @@ static int __init msr_init(void)
int i, err = 0;
i = 0;
- if (register_chrdev(MSR_MAJOR, "cpu/msr", &msr_fops)) {
+ if (__register_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr", &msr_fops)) {
printk(KERN_ERR "msr: unable to get major %d for msr\n",
MSR_MAJOR);
err = -EBUSY;
@@ -274,7 +274,7 @@ out_class:
msr_device_destroy(i);
class_destroy(msr_class);
out_chrdev:
- unregister_chrdev(MSR_MAJOR, "cpu/msr");
+ __unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
out:
return err;
}
From 5df974009fe513c664303de24725ea0f8b47f12e Mon Sep 17 00:00:00 2001
From: Sheng Yang <sheng@linux.intel.com>
Date: Wed, 16 Dec 2009 13:48:04 +0800
Subject: [PATCH 05/16] x86: Add IA32_TSC_AUX MSR and use it
Clean up write_tsc() and write_tscp_aux() by replacing
hardcoded values.
No change in functionality.
Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
LKML-Reference: <1260942485-19156-4-git-send-email-sheng@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/include/asm/msr-index.h | 1 +
arch/x86/include/asm/msr.h | 4 ++--
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4ffe09b2ad75..ac98d2914ebf 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -12,6 +12,7 @@
#define MSR_FS_BASE 0xc0000100 /* 64bit FS base */
#define MSR_GS_BASE 0xc0000101 /* 64bit GS base */
#define MSR_KERNEL_GS_BASE 0xc0000102 /* SwapGS GS shadow */
+#define MSR_TSC_AUX 0xc0000103 /* Auxiliary TSC */
/* EFER bits: */
#define _EFER_SCE 0 /* SYSCALL/SYSRET */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 2d228fc9b4b7..cf985aa00660 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -240,9 +240,9 @@ do { \
#define checking_wrmsrl(msr, val) wrmsr_safe((msr), (u32)(val), \
(u32)((val) >> 32))
-#define write_tsc(val1, val2) wrmsr(0x10, (val1), (val2))
+#define write_tsc(val1, val2) wrmsr(MSR_IA32_TSC, (val1), (val2))
-#define write_rdtscp_aux(val) wrmsr(0xc0000103, (val), 0)
+#define write_rdtscp_aux(val) wrmsr(MSR_TSC_AUX, (val), 0)
struct msr *msrs_alloc(void);
void msrs_free(struct msr *msrs);
From 9d260ebc09a0ad6b5c73e17676df42c7bc75ff64 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <herrmann.der.user@googlemail.com>
Date: Wed, 16 Dec 2009 15:43:55 +0100
Subject: [PATCH 06/16] x86, amd: Get multi-node CPU info from NodeId MSR
instead of PCI config space
Use NodeId MSR to get NodeId and number of nodes per processor.
Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
LKML-Reference: <20091216144355.GB28798@alberich.amd.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
arch/x86/include/asm/cpufeature.h | 1 +
arch/x86/include/asm/msr-index.h | 1 +
arch/x86/kernel/cpu/amd.c | 53 +++++++++----------------------
3 files changed, 17 insertions(+), 38 deletions(-)
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 613700f27a4a..637e1ec963c3 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -153,6 +153,7 @@
#define X86_FEATURE_SSE5 (6*32+11) /* SSE-5 */
#define X86_FEATURE_SKINIT (6*32+12) /* SKINIT/STGI instructions */
#define X86_FEATURE_WDT (6*32+13) /* Watchdog timer */
+#define X86_FEATURE_NODEID_MSR (6*32+19) /* NodeId MSR */
/*
* Auxiliary flags: Linux defined - For features scattered in various
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index ac98d2914ebf..1cd58cdbc03f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -124,6 +124,7 @@
#define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
#define FAM10H_MMIO_CONF_BASE_MASK 0xfffffff
#define FAM10H_MMIO_CONF_BASE_SHIFT 20
+#define MSR_FAM10H_NODE_ID 0xc001100c
/* K8 MSRs */
#define MSR_K8_TOP_MEM1 0xc001001a
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 8dc3ea145c97..e485825130d2 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -254,59 +254,36 @@ static int __cpuinit nearby_node(int apicid)
/*
* Fixup core topology information for AMD multi-node processors.
- * Assumption 1: Number of cores in each internal node is the same.
- * Assumption 2: Mixed systems with both single-node and dual-node
- * processors are not supported.
+ * Assumption: Number of cores in each internal node is the same.
*/
#ifdef CONFIG_X86_HT
static void __cpuinit amd_fixup_dcm(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_PCI
- u32 t, cpn;
- u8 n, n_id;
+ unsigned long long value;
+ u32 nodes, cores_per_node;
int cpu = smp_processor_id();
+ if (!cpu_has(c, X86_FEATURE_NODEID_MSR))
+ return;
+
/* fixup topology information only once for a core */
if (cpu_has(c, X86_FEATURE_AMD_DCM))
return;
- /* check for multi-node processor on boot cpu */
- t = read_pci_config(0, 24, 3, 0xe8);
- if (!(t & (1 << 29)))
+ rdmsrl(MSR_FAM10H_NODE_ID, value);
+
+ nodes = ((value >> 3) & 7) + 1;
+ if (nodes == 1)
return;
set_cpu_cap(c, X86_FEATURE_AMD_DCM);
+ cores_per_node = c->x86_max_cores / nodes;
- /* cores per node: each internal node has half the number of cores */
- cpn = c->x86_max_cores >> 1;
+ /* store NodeID, use llc_shared_map to store sibling info */
+ per_cpu(cpu_llc_id, cpu) = value & 7;
- /* even-numbered NB_id of this dual-node processor */
- n = c->phys_proc_id << 1;
-
- /*
- * determine internal node id and assign cores fifty-fifty to
- * each node of the dual-node processor
- */
- t = read_pci_config(0, 24 + n, 3, 0xe8);
- n = (t>>30) & 0x3;
- if (n == 0) {
- if (c->cpu_core_id < cpn)
- n_id = 0;
- else
- n_id = 1;
- } else {
- if (c->cpu_core_id < cpn)
- n_id = 1;
- else
- n_id = 0;
- }
-
- /* compute entire NodeID, use llc_shared_map to store sibling info */
- per_cpu(cpu_llc_id, cpu) = (c->phys_proc_id << 1) + n_id;
-
- /* fixup core id to be in range from 0 to cpn */
- c->cpu_core_id = c->cpu_core_id % cpn;
-#endif
+ /* fixup core id to be in range from 0 to (cores_per_node - 1) */
+ c->cpu_core_id = c->cpu_core_id % cores_per_node;
}
#endif
From 6ede31e03084ee084bcee073ef3d1136f68d0906 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <petkovbb@googlemail.com>
Date: Thu, 17 Dec 2009 00:16:25 +0100
Subject: [PATCH 07/16] x86, msr: msrs_alloc/free for CONFIG_SMP=n
Randy Dunlap reported the following build error:
"When CONFIG_SMP=n, CONFIG_X86_MSR=m:
ERROR: "msrs_free" [drivers/edac/amd64_edac_mod.ko] undefined!
ERROR: "msrs_alloc" [drivers/edac/amd64_edac_mod.ko] undefined!"
This is due to the fact that <arch/x86/lib/msr.c> is conditioned on
CONFIG_SMP and in the UP case we have only the stubs in the header.
Fork off SMP functionality into a new file (msr-smp.c) and build
msrs_{alloc,free} unconditionally.
Reported-by: Randy Dunlap <randy.dunlap@oracle.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Borislav Petkov <petkovbb@gmail.com>
LKML-Reference: <20091216231625.GD27228@liondog.tnic>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
arch/x86/include/asm/msr.h | 12 +++
arch/x86/lib/Makefile | 4 +-
arch/x86/lib/msr-smp.c | 204 +++++++++++++++++++++++++++++++++++
arch/x86/lib/msr.c | 213 -------------------------------------
4 files changed, 218 insertions(+), 215 deletions(-)
create mode 100644 arch/x86/lib/msr-smp.c
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index cf985aa00660..c5bc4c2d33f5 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -27,6 +27,18 @@ struct msr {
};
};
+struct msr_info {
+ u32 msr_no;
+ struct msr reg;
+ struct msr *msrs;
+ int err;
+};
+
+struct msr_regs_info {
+ u32 *regs;
+ int err;
+};
+
static inline unsigned long long native_read_tscp(unsigned int *aux)
{
unsigned long low, high;
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index a2d6472895fb..706be8bf967b 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -14,7 +14,7 @@ $(obj)/inat.o: $(obj)/inat-tables.c
clean-files := inat-tables.c
-obj-$(CONFIG_SMP) := msr.o
+obj-$(CONFIG_SMP) += msr-smp.o
lib-y := delay.o
lib-y += thunk_$(BITS).o
@@ -22,7 +22,7 @@ lib-y += usercopy_$(BITS).o getuser.o putuser.o
lib-y += memcpy_$(BITS).o
lib-y += insn.o inat.o
-obj-y += msr-reg.o msr-reg-export.o
+obj-y += msr.o msr-reg.o msr-reg-export.o
ifeq ($(CONFIG_X86_32),y)
obj-y += atomic64_32.o
diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c
new file mode 100644
index 000000000000..a6b1b86d2253
--- /dev/null
+++ b/arch/x86/lib/msr-smp.c
@@ -0,0 +1,204 @@
+#include <linux/module.h>
+#include <linux/preempt.h>
+#include <linux/smp.h>
+#include <asm/msr.h>
+
+static void __rdmsr_on_cpu(void *info)
+{
+ struct msr_info *rv = info;
+ struct msr *reg;
+ int this_cpu = raw_smp_processor_id();
+
+ if (rv->msrs)
+ reg = per_cpu_ptr(rv->msrs, this_cpu);
+ else
+ reg = &rv->reg;
+
+ rdmsr(rv->msr_no, reg->l, reg->h);
+}
+
+static void __wrmsr_on_cpu(void *info)
+{
+ struct msr_info *rv = info;
+ struct msr *reg;
+ int this_cpu = raw_smp_processor_id();
+
+ if (rv->msrs)
+ reg = per_cpu_ptr(rv->msrs, this_cpu);
+ else
+ reg = &rv->reg;
+
+ wrmsr(rv->msr_no, reg->l, reg->h);
+}
+
+int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+ int err;
+ struct msr_info rv;
+
+ memset(&rv, 0, sizeof(rv));
+
+ rv.msr_no = msr_no;
+ err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1);
+ *l = rv.reg.l;
+ *h = rv.reg.h;
+
+ return err;
+}
+EXPORT_SYMBOL(rdmsr_on_cpu);
+
+int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+ int err;
+ struct msr_info rv;
+
+ memset(&rv, 0, sizeof(rv));
+
+ rv.msr_no = msr_no;
+ rv.reg.l = l;
+ rv.reg.h = h;
+ err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1);
+
+ return err;
+}
+EXPORT_SYMBOL(wrmsr_on_cpu);
+
+static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no,
+ struct msr *msrs,
+ void (*msr_func) (void *info))
+{
+ struct msr_info rv;
+ int this_cpu;
+
+ memset(&rv, 0, sizeof(rv));
+
+ rv.msrs = msrs;
+ rv.msr_no = msr_no;
+
+ this_cpu = get_cpu();
+
+ if (cpumask_test_cpu(this_cpu, mask))
+ msr_func(&rv);
+
+ smp_call_function_many(mask, msr_func, &rv, 1);
+ put_cpu();
+}
+
+/* rdmsr on a bunch of CPUs
+ *
+ * @mask: which CPUs
+ * @msr_no: which MSR
+ * @msrs: array of MSR values
+ *
+ */
+void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
+{
+ __rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu);
+}
+EXPORT_SYMBOL(rdmsr_on_cpus);
+
+/*
+ * wrmsr on a bunch of CPUs
+ *
+ * @mask: which CPUs
+ * @msr_no: which MSR
+ * @msrs: array of MSR values
+ *
+ */
+void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
+{
+ __rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu);
+}
+EXPORT_SYMBOL(wrmsr_on_cpus);
+
+/* These "safe" variants are slower and should be used when the target MSR
+ may not actually exist. */
+static void __rdmsr_safe_on_cpu(void *info)
+{
+ struct msr_info *rv = info;
+
+ rv->err = rdmsr_safe(rv->msr_no, &rv->reg.l, &rv->reg.h);
+}
+
+static void __wrmsr_safe_on_cpu(void *info)
+{
+ struct msr_info *rv = info;
+
+ rv->err = wrmsr_safe(rv->msr_no, rv->reg.l, rv->reg.h);
+}
+
+int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+ int err;
+ struct msr_info rv;
+
+ memset(&rv, 0, sizeof(rv));
+
+ rv.msr_no = msr_no;
+ err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1);
+ *l = rv.reg.l;
+ *h = rv.reg.h;
+
+ return err ? err : rv.err;
+}
+EXPORT_SYMBOL(rdmsr_safe_on_cpu);
+
+int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+ int err;
+ struct msr_info rv;
+
+ memset(&rv, 0, sizeof(rv));
+
+ rv.msr_no = msr_no;
+ rv.reg.l = l;
+ rv.reg.h = h;
+ err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1);
+
+ return err ? err : rv.err;
+}
+EXPORT_SYMBOL(wrmsr_safe_on_cpu);
+
+/*
+ * These variants are significantly slower, but allows control over
+ * the entire 32-bit GPR set.
+ */
+static void __rdmsr_safe_regs_on_cpu(void *info)
+{
+ struct msr_regs_info *rv = info;
+
+ rv->err = rdmsr_safe_regs(rv->regs);
+}
+
+static void __wrmsr_safe_regs_on_cpu(void *info)
+{
+ struct msr_regs_info *rv = info;
+
+ rv->err = wrmsr_safe_regs(rv->regs);
+}
+
+int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs)
+{
+ int err;
+ struct msr_regs_info rv;
+
+ rv.regs = regs;
+ rv.err = -EIO;
+ err = smp_call_function_single(cpu, __rdmsr_safe_regs_on_cpu, &rv, 1);
+
+ return err ? err : rv.err;
+}
+EXPORT_SYMBOL(rdmsr_safe_regs_on_cpu);
+
+int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs)
+{
+ int err;
+ struct msr_regs_info rv;
+
+ rv.regs = regs;
+ rv.err = -EIO;
+ err = smp_call_function_single(cpu, __wrmsr_safe_regs_on_cpu, &rv, 1);
+
+ return err ? err : rv.err;
+}
+EXPORT_SYMBOL(wrmsr_safe_regs_on_cpu);
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 872834177937..8f8eebdca7d4 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -1,123 +1,7 @@
#include <linux/module.h>
#include <linux/preempt.h>
-#include <linux/smp.h>
#include <asm/msr.h>
-struct msr_info {
- u32 msr_no;
- struct msr reg;
- struct msr *msrs;
- int err;
-};
-
-static void __rdmsr_on_cpu(void *info)
-{
- struct msr_info *rv = info;
- struct msr *reg;
- int this_cpu = raw_smp_processor_id();
-
- if (rv->msrs)
- reg = per_cpu_ptr(rv->msrs, this_cpu);
- else
- reg = &rv->reg;
-
- rdmsr(rv->msr_no, reg->l, reg->h);
-}
-
-static void __wrmsr_on_cpu(void *info)
-{
- struct msr_info *rv = info;
- struct msr *reg;
- int this_cpu = raw_smp_processor_id();
-
- if (rv->msrs)
- reg = per_cpu_ptr(rv->msrs, this_cpu);
- else
- reg = &rv->reg;
-
- wrmsr(rv->msr_no, reg->l, reg->h);
-}
-
-int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
-{
- int err;
- struct msr_info rv;
-
- memset(&rv, 0, sizeof(rv));
-
- rv.msr_no = msr_no;
- err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1);
- *l = rv.reg.l;
- *h = rv.reg.h;
-
- return err;
-}
-EXPORT_SYMBOL(rdmsr_on_cpu);
-
-int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
-{
- int err;
- struct msr_info rv;
-
- memset(&rv, 0, sizeof(rv));
-
- rv.msr_no = msr_no;
- rv.reg.l = l;
- rv.reg.h = h;
- err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1);
-
- return err;
-}
-EXPORT_SYMBOL(wrmsr_on_cpu);
-
-static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no,
- struct msr *msrs,
- void (*msr_func) (void *info))
-{
- struct msr_info rv;
- int this_cpu;
-
- memset(&rv, 0, sizeof(rv));
-
- rv.msrs = msrs;
- rv.msr_no = msr_no;
-
- this_cpu = get_cpu();
-
- if (cpumask_test_cpu(this_cpu, mask))
- msr_func(&rv);
-
- smp_call_function_many(mask, msr_func, &rv, 1);
- put_cpu();
-}
-
-/* rdmsr on a bunch of CPUs
- *
- * @mask: which CPUs
- * @msr_no: which MSR
- * @msrs: array of MSR values
- *
- */
-void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
-{
- __rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu);
-}
-EXPORT_SYMBOL(rdmsr_on_cpus);
-
-/*
- * wrmsr on a bunch of CPUs
- *
- * @mask: which CPUs
- * @msr_no: which MSR
- * @msrs: array of MSR values
- *
- */
-void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
-{
- __rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu);
-}
-EXPORT_SYMBOL(wrmsr_on_cpus);
-
struct msr *msrs_alloc(void)
{
struct msr *msrs = NULL;
@@ -137,100 +21,3 @@ void msrs_free(struct msr *msrs)
free_percpu(msrs);
}
EXPORT_SYMBOL(msrs_free);
-
-/* These "safe" variants are slower and should be used when the target MSR
- may not actually exist. */
-static void __rdmsr_safe_on_cpu(void *info)
-{
- struct msr_info *rv = info;
-
- rv->err = rdmsr_safe(rv->msr_no, &rv->reg.l, &rv->reg.h);
-}
-
-static void __wrmsr_safe_on_cpu(void *info)
-{
- struct msr_info *rv = info;
-
- rv->err = wrmsr_safe(rv->msr_no, rv->reg.l, rv->reg.h);
-}
-
-int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
-{
- int err;
- struct msr_info rv;
-
- memset(&rv, 0, sizeof(rv));
-
- rv.msr_no = msr_no;
- err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1);
- *l = rv.reg.l;
- *h = rv.reg.h;
-
- return err ? err : rv.err;
-}
-EXPORT_SYMBOL(rdmsr_safe_on_cpu);
-
-int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
-{
- int err;
- struct msr_info rv;
-
- memset(&rv, 0, sizeof(rv));
-
- rv.msr_no = msr_no;
- rv.reg.l = l;
- rv.reg.h = h;
- err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1);
-
- return err ? err : rv.err;
-}
-EXPORT_SYMBOL(wrmsr_safe_on_cpu);
-
-/*
- * These variants are significantly slower, but allows control over
- * the entire 32-bit GPR set.
- */
-struct msr_regs_info {
- u32 *regs;
- int err;
-};
-
-static void __rdmsr_safe_regs_on_cpu(void *info)
-{
- struct msr_regs_info *rv = info;
-
- rv->err = rdmsr_safe_regs(rv->regs);
-}
-
-static void __wrmsr_safe_regs_on_cpu(void *info)
-{
- struct msr_regs_info *rv = info;
-
- rv->err = wrmsr_safe_regs(rv->regs);
-}
-
-int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs)
-{
- int err;
- struct msr_regs_info rv;
-
- rv.regs = regs;
- rv.err = -EIO;
- err = smp_call_function_single(cpu, __rdmsr_safe_regs_on_cpu, &rv, 1);
-
- return err ? err : rv.err;
-}
-EXPORT_SYMBOL(rdmsr_safe_regs_on_cpu);
-
-int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs)
-{
- int err;
- struct msr_regs_info rv;
-
- rv.regs = regs;
- rv.err = -EIO;
- err = smp_call_function_single(cpu, __wrmsr_safe_regs_on_cpu, &rv, 1);
-
- return err ? err : rv.err;
-}
-EXPORT_SYMBOL(wrmsr_safe_regs_on_cpu);
From 45a94d7cd45ed991914011919e7d40eb6d2546d1 Mon Sep 17 00:00:00 2001
From: Suresh Siddha <suresh.b.siddha@intel.com>
Date: Wed, 16 Dec 2009 16:25:42 -0800
Subject: [PATCH 08/16] x86, cpuid: Add "volatile" to asm in native_cpuid()
xsave_cntxt_init() does something like:
cpuid(0xd, ..); // find out what features FP/SSE/.. etc are supported
xsetbv(); // enable the features known to OS
cpuid(0xd, ..); // find out the size of the context for features enabled
Depending on what features get enabled in xsetbv(), value of the
cpuid.eax=0xd.ecx=0.ebx changes correspondingly (representing the
size of the context that is enabled).
As we don't have volatile keyword for native_cpuid(), gcc 4.1.2
optimizes away the second cpuid and the kernel continues to use
the cpuid information obtained before xsetbv(), ultimately leading to kernel
crash on processors supporting more state than the legacy FP/SSE.
Add "volatile" for native_cpuid().
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
LKML-Reference: <1261009542.2745.55.camel@sbs-t61.sc.intel.com>
Cc: stable@kernel.org
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
arch/x86/include/asm/processor.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6f8ec1c37e0a..fc801bab1b3b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -181,7 +181,7 @@ static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
unsigned int *ecx, unsigned int *edx)
{
/* ecx is often an input as well as an output. */
- asm("cpuid"
+ asm volatile("cpuid"
: "=a" (*eax),
"=b" (*ebx),
"=c" (*ecx),
From 329962503692b42d8088f31584e42d52db179d52 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Tue, 15 Dec 2009 17:59:02 -0800
Subject: [PATCH 09/16] x86: Fix checking of SRAT when node 0 ram is not from 0
Found one system that boot from socket1 instead of socket0, SRAT get rejected...
[ 0.000000] SRAT: Node 1 PXM 0 0-a0000
[ 0.000000] SRAT: Node 1 PXM 0 100000-80000000
[ 0.000000] SRAT: Node 1 PXM 0 100000000-2080000000
[ 0.000000] SRAT: Node 0 PXM 1 2080000000-4080000000
[ 0.000000] SRAT: Node 2 PXM 2 4080000000-6080000000
[ 0.000000] SRAT: Node 3 PXM 3 6080000000-8080000000
[ 0.000000] SRAT: Node 4 PXM 4 8080000000-a080000000
[ 0.000000] SRAT: Node 5 PXM 5 a080000000-c080000000
[ 0.000000] SRAT: Node 6 PXM 6 c080000000-e080000000
[ 0.000000] SRAT: Node 7 PXM 7 e080000000-10080000000
...
[ 0.000000] NUMA: Allocated memnodemap from 500000 - 701040
[ 0.000000] NUMA: Using 20 for the hash shift.
[ 0.000000] Adding active range (0, 0x2080000, 0x4080000) 0 entries of 3200 used
[ 0.000000] Adding active range (1, 0x0, 0x96) 1 entries of 3200 used
[ 0.000000] Adding active range (1, 0x100, 0x7f750) 2 entries of 3200 used
[ 0.000000] Adding active range (1, 0x100000, 0x2080000) 3 entries of 3200 used
[ 0.000000] Adding active range (2, 0x4080000, 0x6080000) 4 entries of 3200 used
[ 0.000000] Adding active range (3, 0x6080000, 0x8080000) 5 entries of 3200 used
[ 0.000000] Adding active range (4, 0x8080000, 0xa080000) 6 entries of 3200 used
[ 0.000000] Adding active range (5, 0xa080000, 0xc080000) 7 entries of 3200 used
[ 0.000000] Adding active range (6, 0xc080000, 0xe080000) 8 entries of 3200 used
[ 0.000000] Adding active range (7, 0xe080000, 0x10080000) 9 entries of 3200 used
[ 0.000000] SRAT: PXMs only cover 917504MB of your 1048566MB e820 RAM. Not used.
[ 0.000000] SRAT: SRAT not used.
the early_node_map is not sorted because node0 with non zero start come first.
so try to sort it right away after all regions are registered.
also fixs refression by 8716273c (x86: Export srat physical topology)
-v2: make it more solid to handle cross node case like node0 [0,4g), [8,12g) and node1 [4g, 8g), [12g, 16g)
-v3: update comments.
Reported-and-tested-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <4B2579D2.3010201@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
arch/x86/mm/srat_32.c | 2 ++
arch/x86/mm/srat_64.c | 4 +++-
include/linux/mm.h | 3 +++
mm/page_alloc.c | 4 ++--
4 files changed, 10 insertions(+), 3 deletions(-)
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 6f8aa33031c7..9324f13492d5 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -267,6 +267,8 @@ int __init get_memcfg_from_srat(void)
e820_register_active_regions(chunk->nid, chunk->start_pfn,
min(chunk->end_pfn, max_pfn));
}
+ /* for out of order entries in SRAT */
+ sort_node_map();
for_each_online_node(nid) {
unsigned long start = node_start_pfn[nid];
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index d89075489664..a27124185fc1 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -317,7 +317,7 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
unsigned long s = nodes[i].start >> PAGE_SHIFT;
unsigned long e = nodes[i].end >> PAGE_SHIFT;
pxmram += e - s;
- pxmram -= absent_pages_in_range(s, e);
+ pxmram -= __absent_pages_in_range(i, s, e);
if ((long)pxmram < 0)
pxmram = 0;
}
@@ -373,6 +373,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
for_each_node_mask(i, nodes_parsed)
e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
nodes[i].end >> PAGE_SHIFT);
+ /* for out of order entries in SRAT */
+ sort_node_map();
if (!nodes_cover_memory(nodes)) {
bad_srat();
return -1;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 24c395694f4d..20a2036f3a94 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1022,6 +1022,9 @@ extern void add_active_range(unsigned int nid, unsigned long start_pfn,
extern void remove_active_range(unsigned int nid, unsigned long start_pfn,
unsigned long end_pfn);
extern void remove_all_active_ranges(void);
+void sort_node_map(void);
+unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn,
+ unsigned long end_pfn);
extern unsigned long absent_pages_in_range(unsigned long start_pfn,
unsigned long end_pfn);
extern void get_pfn_range_for_nid(unsigned int nid,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2bc2ac63f41e..873c86308b4e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3573,7 +3573,7 @@ static unsigned long __meminit zone_spanned_pages_in_node(int nid,
* Return the number of holes in a range on a node. If nid is MAX_NUMNODES,
* then all holes in the requested range will be accounted for.
*/
-static unsigned long __meminit __absent_pages_in_range(int nid,
+unsigned long __meminit __absent_pages_in_range(int nid,
unsigned long range_start_pfn,
unsigned long range_end_pfn)
{
@@ -4102,7 +4102,7 @@ static int __init cmp_node_active_region(const void *a, const void *b)
}
/* sort the node_map by start_pfn */
-static void __init sort_node_map(void)
+void __init sort_node_map(void)
{
sort(early_node_map, (size_t)nr_nodemap_entries,
sizeof(struct node_active_region),
From 6a1e008a0915f502eb026fb995ea3e49d5b017f7 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Tue, 15 Dec 2009 17:59:03 -0800
Subject: [PATCH 10/16] x86: Increase MAX_EARLY_RES; insufficient on 32-bit
NUMA
Due to recent changes wakeup and mptable, we run out of early
reservations on 32-bit NUMA. Thus, adjust the available number.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <4B22D754.2020706@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
arch/x86/kernel/e820.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index f50447d961c0..05ed7ab2ca48 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -724,7 +724,7 @@ core_initcall(e820_mark_nvs_memory);
/*
* Early reserved memory areas.
*/
-#define MAX_EARLY_RES 20
+#define MAX_EARLY_RES 32
struct early_res {
u64 start, end;
From c051346b7db27aaf674b8f3b4955240580b2a58a Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@zytor.com>
Date: Thu, 17 Dec 2009 06:56:11 -0800
Subject: [PATCH 11/16] Makefile: set LC_CTYPE, LC_COLLATE, LC_NUMERIC to C
There are a number of common Unix constructs like character ranges in
grep/sed/awk which don't work as expected with LC_COLLATE set to other
than C. Similarly, set LC_CTYPE and LC_NUMERIC to C to avoid other
nasty surprises.
In order to make sure these actually take effect we also have to
clear LC_ALL.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Acked-by: Michal Marek <mmarek@sues.cz>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: Roland Dreier <rdreier@cisco.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
LKML-Reference: <4B2A1761.4070904@suse.cz>
---
Makefile | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/Makefile b/Makefile
index 33d4732a6c4a..6e39af1d8bc4 100644
--- a/Makefile
+++ b/Makefile
@@ -16,6 +16,13 @@ NAME = Man-Eating Seals of Antiquity
# o print "Entering directory ...";
MAKEFLAGS += -rR --no-print-directory
+# Avoid funny character set dependencies
+LC_ALL=
+LC_CTYPE=C
+LC_COLLATE=C
+LC_NUMERIC=C
+export LC_ALL LC_CTYPE LC_COLLATE LC_NUMERIC
+
# We are using a recursive build, so we need to do a little thinking
# to get the ordering right.
#
From 4beb3d6d144c41525541cce2b611858b2645c725 Mon Sep 17 00:00:00 2001
From: Roland Dreier <rdreier@cisco.com>
Date: Wed, 16 Dec 2009 17:39:48 -0800
Subject: [PATCH 12/16] x86: Don't use POSIX character classes in
gen-insn-attr-x86.awk
Not all awk implementations (including the default awk in Ubuntu 9.10)
support POSIX character classes. Since x86-opcode-map.txt is plain
ASCII, we can just use explicit ranges for lower case, alphabetic, and
alphanumeric characters instead.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
LKML-Reference: <adabphy750b.fsf@roland-alpha.cisco.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
arch/x86/tools/gen-insn-attr-x86.awk | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index 7a6850683c34..eaf11f52fc0b 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -6,8 +6,6 @@
# Awk implementation sanity check
function check_awk_implement() {
- if (!match("abc", "[[:lower:]]+"))
- return "Your awk doesn't support charactor-class."
if (sprintf("%x", 0) != "0")
return "Your awk has a printf-format problem."
return ""
@@ -44,12 +42,12 @@ BEGIN {
delete gtable
delete atable
- opnd_expr = "^[[:alpha:]/]"
+ opnd_expr = "^[A-Za-z/]"
ext_expr = "^\\("
sep_expr = "^\\|$"
- group_expr = "^Grp[[:alnum:]]+"
+ group_expr = "^Grp[0-9A-Za-z]+"
- imm_expr = "^[IJAO][[:lower:]]"
+ imm_expr = "^[IJAO][a-z]"
imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)"
@@ -62,7 +60,7 @@ BEGIN {
imm_flag["Ob"] = "INAT_MOFFSET"
imm_flag["Ov"] = "INAT_MOFFSET"
- modrm_expr = "^([CDEGMNPQRSUVW/][[:lower:]]+|NTA|T[012])"
+ modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
force64_expr = "\\([df]64\\)"
rex_expr = "^REX(\\.[XRWB]+)*"
fpu_expr = "^ESC" # TODO
From 6c56ccecf05fafe100ab4ea94f6fccbf5ff00db7 Mon Sep 17 00:00:00 2001
From: "Pallipadi, Venkatesh" <venkatesh.pallipadi@intel.com>
Date: Thu, 17 Dec 2009 12:27:02 -0800
Subject: [PATCH 13/16] x86: Reenable TSC sync check at boot, even with
NONSTOP_TSC
Commit 83ce4009 did the following change
If the TSC is constant and non-stop, also set it reliable.
But, there seems to be few systems that will end up with TSC warp across
sockets, depending on how the cpus come out of reset. Skipping TSC sync
test on such systems may result in time inconsistency later.
So, reenable TSC sync test even on constant and non-stop TSC systems.
Set, sched_clock_stable to 1 by default and reset it in
mark_tsc_unstable, if TSC sync fails.
This change still gives perf benefit mentioned in 83ce4009 for systems
where TSC is reliable.
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>
LKML-Reference: <20091217202702.GA18015@linux-os.sc.intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
arch/x86/kernel/cpu/intel.c | 1 -
arch/x86/kernel/tsc.c | 1 +
2 files changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 9c31e8b09d2c..879666f4d871 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -70,7 +70,6 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
if (c->x86_power & (1 << 8)) {
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
- set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE);
sched_clock_stable = 1;
}
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index cd982f48e23e..597683aa5ba0 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -763,6 +763,7 @@ void mark_tsc_unstable(char *reason)
{
if (!tsc_unstable) {
tsc_unstable = 1;
+ sched_clock_stable = 0;
printk(KERN_INFO "Marking TSC unstable due to %s\n", reason);
/* Change only the rating, when not registered */
if (clocksource_tsc.mult)
From 8c63450718ea62ee3a70bffde170b4d15fc72d3c Mon Sep 17 00:00:00 2001
From: "akpm@linux-foundation.org" <akpm@linux-foundation.org>
Date: Thu, 17 Dec 2009 15:26:36 -0800
Subject: [PATCH 14/16] x86: Fix objdump version check in
arch/x86/tools/chkobjdump.awk
It says
Warning: objdump version is older than 2.19
Warning: Skipping posttest.
because it used the wrong field from `objdump -v':
akpm:/usr/src/25> /opt/crosstool/gcc-4.0.2-glibc-2.3.6/x86_64-unknown-linux-gnu/bin/x86_64-unknown-linux-gnu-objdump -v
GNU objdump 2.16.1
Copyright 2005 Free Software Foundation, Inc.
This program is free software; you may redistribute it under the terms of
the GNU General Public License. This program has absolutely no warranty.
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <200912172326.nBHNQaQl024796@imap1.linux-foundation.org>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
---
arch/x86/tools/chkobjdump.awk | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/tools/chkobjdump.awk b/arch/x86/tools/chkobjdump.awk
index 0d13cd9fdcff..5bbb5a33f220 100644
--- a/arch/x86/tools/chkobjdump.awk
+++ b/arch/x86/tools/chkobjdump.awk
@@ -9,7 +9,7 @@ BEGIN {
}
/^GNU/ {
- split($4, ver, ".");
+ split($3, ver, ".");
if (ver[1] > od_ver ||
(ver[1] == od_ver && ver[2] >= od_sver)) {
exit 1;
From 06b5dc646b9479b786d77749936f25910cd82a37 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@zytor.com>
Date: Thu, 17 Dec 2009 15:51:37 -0800
Subject: [PATCH 15/16] Makefile: Unexport LC_ALL instead of clearing it
Apparently not all versions of glibc and utilities treat an empty
LC_ALL as nonexistent, causing error messages to be garbled. Instead,
explicitly unexport it from the environment.
Reported-and-tested-by: Masami Hiramatsu <mhiramat@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
LKML-Reference: <4B2AC394.4030108@redhat.com>
Cc: Michal Marek <mmarek@sues.cz>
Cc: Roland Dreier <rdreier@cisco.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
---
Makefile | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/Makefile b/Makefile
index 6e39af1d8bc4..5e92ca58fb6d 100644
--- a/Makefile
+++ b/Makefile
@@ -17,11 +17,11 @@ NAME = Man-Eating Seals of Antiquity
MAKEFLAGS += -rR --no-print-directory
# Avoid funny character set dependencies
-LC_ALL=
+unexport LC_ALL
LC_CTYPE=C
LC_COLLATE=C
LC_NUMERIC=C
-export LC_ALL LC_CTYPE LC_COLLATE LC_NUMERIC
+export LC_CTYPE LC_COLLATE LC_NUMERIC
# We are using a recursive build, so we need to do a little thinking
# to get the ordering right.
From 18374d89e5fe96772102f44f535efb1198d9be08 Mon Sep 17 00:00:00 2001
From: Suresh Siddha <suresh.b.siddha@intel.com>
Date: Thu, 17 Dec 2009 18:29:46 -0800
Subject: [PATCH 16/16] x86, irq: Allow 0xff for /proc/irq/[n]/smp_affinity on
an 8-cpu system
John Blackwood reported:
> on an older Dell PowerEdge 6650 system with 8 cpus (4 are hyper-threaded),
> and 32 bit (x86) kernel, once you change the irq smp_affinity of an irq
> to be less than all cpus in the system, you can never change really the
> irq smp_affinity back to be all cpus in the system (0xff) again,
> even though no error status is returned on the "/bin/echo ff >
> /proc/irq/[n]/smp_affinity" operation.
>
> This is due to that fact that BAD_APICID has the same value as
> all cpus (0xff) on 32bit kernels, and thus the value returned from
> set_desc_affinity() via the cpu_mask_to_apicid_and() function is treated
> as a failure in set_ioapic_affinity_irq_desc(), and no affinity changes
> are made.
set_desc_affinity() is already checking if the incoming cpu mask
intersects with the cpu online mask or not. So there is no need
for the apic op cpu_mask_to_apicid_and() to check again
and return BAD_APICID.
Remove the BAD_APICID return value from cpu_mask_to_apicid_and()
and also fix set_desc_affinity() to return -1 instead of using BAD_APICID
to represent error conditions (as cpu_mask_to_apicid_and() can return
logical or physical apicid values and BAD_APICID is really to represent
bad physical apic id).
Reported-by: John Blackwood <john.blackwood@ccur.com>
Root-caused-by: John Blackwood <john.blackwood@ccur.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
LKML-Reference: <1261103386.2535.409.camel@sbs-t61>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
arch/x86/include/asm/hw_irq.h | 3 ++-
arch/x86/kernel/apic/apic_flat_64.c | 5 +----
arch/x86/kernel/apic/bigsmp_32.c | 5 +----
arch/x86/kernel/apic/io_apic.c | 32 ++++++++++++---------------
arch/x86/kernel/apic/x2apic_cluster.c | 5 +----
arch/x86/kernel/apic/x2apic_phys.c | 5 +----
arch/x86/kernel/apic/x2apic_uv_x.c | 5 +----
arch/x86/kernel/uv_irq.c | 3 +--
8 files changed, 22 insertions(+), 41 deletions(-)
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 08c48a81841f..eeac829a0f44 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -103,7 +103,8 @@ extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
extern void send_cleanup_vector(struct irq_cfg *);
struct irq_desc;
-extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *);
+extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *,
+ unsigned int *dest_id);
extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, struct io_apic_irq_attr *irq_attr);
extern void setup_ioapic_dest(void);
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index d0c99abc26c3..eacbd2b31d27 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -306,10 +306,7 @@ physflat_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
if (cpumask_test_cpu(cpu, cpu_online_mask))
break;
}
- if (cpu < nr_cpu_ids)
- return per_cpu(x86_cpu_to_apicid, cpu);
-
- return BAD_APICID;
+ return per_cpu(x86_cpu_to_apicid, cpu);
}
struct apic apic_physflat = {
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 38dcecfa5818..cb804c5091b9 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -131,10 +131,7 @@ static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
if (cpumask_test_cpu(cpu, cpu_online_mask))
break;
}
- if (cpu < nr_cpu_ids)
- return bigsmp_cpu_to_logical_apicid(cpu);
-
- return BAD_APICID;
+ return bigsmp_cpu_to_logical_apicid(cpu);
}
static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index d5d498fbee4b..98ced709e829 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2276,26 +2276,28 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq
/*
* Either sets desc->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
+ * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
* leaves desc->affinity untouched.
*/
unsigned int
-set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
+set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask,
+ unsigned int *dest_id)
{
struct irq_cfg *cfg;
unsigned int irq;
if (!cpumask_intersects(mask, cpu_online_mask))
- return BAD_APICID;
+ return -1;
irq = desc->irq;
cfg = desc->chip_data;
if (assign_irq_vector(irq, cfg, mask))
- return BAD_APICID;
+ return -1;
cpumask_copy(desc->affinity, mask);
- return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
+ *dest_id = apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
+ return 0;
}
static int
@@ -2311,12 +2313,11 @@ set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
cfg = desc->chip_data;
spin_lock_irqsave(&ioapic_lock, flags);
- dest = set_desc_affinity(desc, mask);
- if (dest != BAD_APICID) {
+ ret = set_desc_affinity(desc, mask, &dest);
+ if (!ret) {
/* Only the high 8 bits are valid. */
dest = SET_APIC_LOGICAL_ID(dest);
__target_IO_APIC_irq(irq, dest, cfg);
- ret = 0;
}
spin_unlock_irqrestore(&ioapic_lock, flags);
@@ -3351,8 +3352,7 @@ static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
struct msi_msg msg;
unsigned int dest;
- dest = set_desc_affinity(desc, mask);
- if (dest == BAD_APICID)
+ if (set_desc_affinity(desc, mask, &dest))
return -1;
cfg = desc->chip_data;
@@ -3384,8 +3384,7 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
if (get_irte(irq, &irte))
return -1;
- dest = set_desc_affinity(desc, mask);
- if (dest == BAD_APICID)
+ if (set_desc_affinity(desc, mask, &dest))
return -1;
irte.vector = cfg->vector;
@@ -3567,8 +3566,7 @@ static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
struct msi_msg msg;
unsigned int dest;
- dest = set_desc_affinity(desc, mask);
- if (dest == BAD_APICID)
+ if (set_desc_affinity(desc, mask, &dest))
return -1;
cfg = desc->chip_data;
@@ -3623,8 +3621,7 @@ static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
struct msi_msg msg;
unsigned int dest;
- dest = set_desc_affinity(desc, mask);
- if (dest == BAD_APICID)
+ if (set_desc_affinity(desc, mask, &dest))
return -1;
cfg = desc->chip_data;
@@ -3730,8 +3727,7 @@ static int set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
struct irq_cfg *cfg;
unsigned int dest;
- dest = set_desc_affinity(desc, mask);
- if (dest == BAD_APICID)
+ if (set_desc_affinity(desc, mask, &dest))
return -1;
cfg = desc->chip_data;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index a5371ec36776..cf69c59f4910 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -148,10 +148,7 @@ x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
break;
}
- if (cpu < nr_cpu_ids)
- return per_cpu(x86_cpu_to_logical_apicid, cpu);
-
- return BAD_APICID;
+ return per_cpu(x86_cpu_to_logical_apicid, cpu);
}
static unsigned int x2apic_cluster_phys_get_apic_id(unsigned long x)
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index a8989aadc99a..8972f38c5ced 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -146,10 +146,7 @@ x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
break;
}
- if (cpu < nr_cpu_ids)
- return per_cpu(x86_cpu_to_apicid, cpu);
-
- return BAD_APICID;
+ return per_cpu(x86_cpu_to_apicid, cpu);
}
static unsigned int x2apic_phys_get_apic_id(unsigned long x)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index b684bb303cbf..d56b0efb2057 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -225,10 +225,7 @@ uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
if (cpumask_test_cpu(cpu, cpu_online_mask))
break;
}
- if (cpu < nr_cpu_ids)
- return per_cpu(x86_cpu_to_apicid, cpu);
-
- return BAD_APICID;
+ return per_cpu(x86_cpu_to_apicid, cpu);
}
static unsigned int x2apic_get_apic_id(unsigned long x)
diff --git a/arch/x86/kernel/uv_irq.c b/arch/x86/kernel/uv_irq.c
index 61d805df4c91..ece73d8e3240 100644
--- a/arch/x86/kernel/uv_irq.c
+++ b/arch/x86/kernel/uv_irq.c
@@ -215,8 +215,7 @@ static int uv_set_irq_affinity(unsigned int irq, const struct cpumask *mask)
unsigned long mmr_offset;
unsigned mmr_pnode;
- dest = set_desc_affinity(desc, mask);
- if (dest == BAD_APICID)
+ if (set_desc_affinity(desc, mask, &dest))
return -1;
mmr_value = 0;