Hi Linus,
First batch of x86 fixes.
The following changes since commit ad41a1e0cab07c5125456e8d38e5b1ab148d04aa:
Merge branch 'io_remap_pfn_range' of git://http://www.jni.nu/cris (2010-08-12 10:17:19 -0700)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git x86/urgent
Eric W. Biederman (1):
x86, apic: Map the local apic when parsing the MP table.
Luca Barbieri (2):
x86, asm: Refactor atomic64_386_32.S to support old binutils and be cleaner
x86, asm: Use a lower case name for the end macro in atomic64_386_32.S
Namhyung Kim (1):
x86: Document __phys_reloc_hide() usage in __pa_symbol()
arch/x86/include/asm/page.h | 7 +
arch/x86/kernel/apic/apic.c | 2 +-
arch/x86/kernel/mpparse.c | 16 +++
arch/x86/lib/atomic64_386_32.S | 238 ++++++++++++++++++++++------------------
4 files changed, 154 insertions(+), 109 deletions(-)
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index 625c3f0..8ca8283 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -37,6 +37,13 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
#define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x))
/* __pa_symbol should be used for C visible symbols.
This seems to be the official gcc blessed way to do such arithmetic. */
+/*
+ * We need __phys_reloc_hide() here because gcc may assume that there is no
+ * overflow during __pa() calculation and can optimize it unexpectedly.
+ * Newer versions of gcc provide -fno-strict-overflow switch to handle this
+ * case properly. Once all supported versions of gcc understand it, we can
+ * remove this Voodoo magic stuff. (i.e. once gcc3.x is deprecated)
+ */
#define __pa_symbol(x) __pa(__phys_reloc_hide((unsigned long)(x)))
#define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET))
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 980508c..e3b534c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1606,7 +1606,7 @@ void __init init_apic_mappings(void)
* acpi lapic path already maps that address in
* acpi_register_lapic_address()
*/
- if (!acpi_lapic)
+ if (!acpi_lapic && !smp_found_config)
set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index d86dbf7..d7b6f7f 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -274,6 +274,18 @@ static void __init smp_dump_mptable(struct mpc_table *mpc, unsigned char *mpt)
void __init default_smp_read_mpc_oem(struct mpc_table *mpc) { }
+static void __init smp_register_lapic_address(unsigned long address)
+{
+ mp_lapic_addr = address;
+
+ set_fixmap_nocache(FIX_APIC_BASE, address);
+ if (boot_cpu_physical_apicid == -1U) {
+ boot_cpu_physical_apicid = read_apic_id();
+ apic_version[boot_cpu_physical_apicid] =
+ GET_APIC_VERSION(apic_read(APIC_LVR));
+ }
+}
+
static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
{
char str[16];
@@ -295,6 +307,10 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
if (early)
return 1;
+ /* Initialize the lapic mapping */
+ if (!acpi_lapic)
+ smp_register_lapic_address(mpc->lapic);
+
if (mpc->oemptr)
x86_init.mpparse.smp_read_mpc_oem(mpc);
diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S
index 4a5979a..2cda60a 100644
--- a/arch/x86/lib/atomic64_386_32.S
+++ b/arch/x86/lib/atomic64_386_32.S
@@ -25,150 +25,172 @@
CFI_ADJUST_CFA_OFFSET -4
.endm
-.macro BEGIN func reg
-$v = \reg
-
-ENTRY(atomic64_\func\()_386)
- CFI_STARTPROC
- LOCK $v
-
-.macro RETURN
- UNLOCK $v
+#define BEGIN(op) \
+.macro endp; \
+ CFI_ENDPROC; \
+ENDPROC(atomic64_##op##_386); \
+.purgem endp; \
+.endm; \
+ENTRY(atomic64_##op##_386); \
+ CFI_STARTPROC; \
+ LOCK v;
+
+#define ENDP endp
+
+#define RET \
+ UNLOCK v; \
ret
-.endm
-
-.macro END_
- CFI_ENDPROC
-ENDPROC(atomic64_\func\()_386)
-.purgem RETURN
-.purgem END_
-.purgem END
-.endm
-
-.macro END
-RETURN
-END_
-.endm
-.endm
-BEGIN read %ecx
- movl ($v), %eax
- movl 4($v), %edx
-END
-
-BEGIN set %esi
- movl %ebx, ($v)
- movl %ecx, 4($v)
-END
-
-BEGIN xchg %esi
- movl ($v), %eax
- movl 4($v), %edx
- movl %ebx, ($v)
- movl %ecx, 4($v)
-END
-
-BEGIN add %ecx
- addl %eax, ($v)
- adcl %edx, 4($v)
-END
-
-BEGIN add_return %ecx
- addl ($v), %eax
- adcl 4($v), %edx
- movl %eax, ($v)
- movl %edx, 4($v)
-END
-
-BEGIN sub %ecx
- subl %eax, ($v)
- sbbl %edx, 4($v)
-END
-
-BEGIN sub_return %ecx
+#define RET_ENDP \
+ RET; \
+ ENDP
+
+#define v %ecx
+BEGIN(read)
+ movl (v), %eax
+ movl 4(v), %edx
+RET_ENDP
+#undef v
+
+#define v %esi
+BEGIN(set)
+ movl %ebx, (v)
+ movl %ecx, 4(v)
+RET_ENDP
+#undef v
+
+#define v %esi
+BEGIN(xchg)
+ movl (v), %eax
+ movl 4(v), %edx
+ movl %ebx, (v)
+ movl %ecx, 4(v)
+RET_ENDP
+#undef v
+
+#define v %ecx
+BEGIN(add)
+ addl %eax, (v)
+ adcl %edx, 4(v)
+RET_ENDP
+#undef v
+
+#define v %ecx
+BEGIN(add_return)
+ addl (v), %eax
+ adcl 4(v), %edx
+ movl %eax, (v)
+ movl %edx, 4(v)
+RET_ENDP
+#undef v
+
+#define v %ecx
+BEGIN(sub)
+ subl %eax, (v)
+ sbbl %edx, 4(v)
+RET_ENDP
+#undef v
+
+#define v %ecx
+BEGIN(sub_return)
negl %edx
negl %eax
sbbl $0, %edx
- addl ($v), %eax
- adcl 4($v), %edx
- movl %eax, ($v)
- movl %edx, 4($v)
-END
-
-BEGIN inc %esi
- addl $1, ($v)
- adcl $0, 4($v)
-END
-
-BEGIN inc_return %esi
- movl ($v), %eax
- movl 4($v), %edx
+ addl (v), %eax
+ adcl 4(v), %edx
+ movl %eax, (v)
+ movl %edx, 4(v)
+RET_ENDP
+#undef v
+
+#define v %esi
+BEGIN(inc)
+ addl $1, (v)
+ adcl $0, 4(v)
+RET_ENDP
+#undef v
+
+#define v %esi
+BEGIN(inc_return)
+ movl (v), %eax
+ movl 4(v), %edx
addl $1, %eax
adcl $0, %edx
- movl %eax, ($v)
- movl %edx, 4($v)
-END
-
-BEGIN dec %esi
- subl $1, ($v)
- sbbl $0, 4($v)
-END
-
-BEGIN dec_return %esi
- movl ($v), %eax
- movl 4($v), %edx
+ movl %eax, (v)
+ movl %edx, 4(v)
+RET_ENDP
+#undef v
+
+#define v %esi
+BEGIN(dec)
+ subl $1, (v)
+ sbbl $0, 4(v)
+RET_ENDP
+#undef v
+
+#define v %esi
+BEGIN(dec_return)
+ movl (v), %eax
+ movl 4(v), %edx
subl $1, %eax
sbbl $0, %edx
- movl %eax, ($v)
- movl %edx, 4($v)
-END
+ movl %eax, (v)
+ movl %edx, 4(v)
+RET_ENDP
+#undef v
-BEGIN add_unless %ecx
+#define v %ecx
+BEGIN(add_unless)
addl %eax, %esi
adcl %edx, %edi
- addl ($v), %eax
- adcl 4($v), %edx
+ addl (v), %eax
+ adcl 4(v), %edx
cmpl %eax, %esi
je 3f
1:
- movl %eax, ($v)
- movl %edx, 4($v)
+ movl %eax, (v)
+ movl %edx, 4(v)
movl $1, %eax
2:
-RETURN
+ RET
3:
cmpl %edx, %edi
jne 1b
xorl %eax, %eax
jmp 2b
-END_
+ENDP
+#undef v
-BEGIN inc_not_zero %esi
- movl ($v), %eax
- movl 4($v), %edx
+#define v %esi
+BEGIN(inc_not_zero)
+ movl (v), %eax
+ movl 4(v), %edx
testl %eax, %eax
je 3f
1:
addl $1, %eax
adcl $0, %edx
- movl %eax, ($v)
- movl %edx, 4($v)
+ movl %eax, (v)
+ movl %edx, 4(v)
movl $1, %eax
2:
-RETURN
+ RET
3:
testl %edx, %edx
jne 1b
jmp 2b
-END_
+ENDP
+#undef v
-BEGIN dec_if_positive %esi
- movl ($v), %eax
- movl 4($v), %edx
+#define v %esi
+BEGIN(dec_if_positive)
+ movl (v), %eax
+ movl 4(v), %edx
subl $1, %eax
sbbl $0, %edx
js 1f
- movl %eax, ($v)
- movl %edx, 4($v)
+ movl %eax, (v)
+ movl %edx, 4(v)
1:
-END
+RET_ENDP
+#undef v
Eureka!
This seems to solve my problem! My Dual P3-500MHZ is now booting with
that patch.
Good work guys!!!!
Thank you very much,
David C. Hill
----- Original Message -----
From: "H. Peter Anvin" <[email protected]>
To: "Linus Torvalds" <[email protected]>
Cc: <[email protected]>; "David Hill" <[email protected]>; "Dieter
Stussy" <[email protected]>; "Eric W. Biederman"
<[email protected]>; "H. Peter Anvin" <[email protected]>; "H. Peter
Anvin" <[email protected]>; "Ingo Molnar" <[email protected]>; "Linux Kernel Mailing
List" <[email protected]>; "Luca Barbieri"
<[email protected]>; "Namhyung Kim" <[email protected]>; "Thomas
Gleixner" <[email protected]>; "Tvrtko Ursulin" <[email protected]>
Sent: Thursday, August 12, 2010 3:08 PM
Subject: [GIT PULL] x86/urgent for 2.6.36-rc1
> Hi Linus,
>
> First batch of x86 fixes.
>
> The following changes since commit
> ad41a1e0cab07c5125456e8d38e5b1ab148d04aa:
>
> Merge branch 'io_remap_pfn_range' of git://http://www.jni.nu/cris (2010-08-12
> 10:17:19 -0700)
>
> are available in the git repository at:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git
> x86/urgent
>
> Eric W. Biederman (1):
> x86, apic: Map the local apic when parsing the MP table.
>
> Luca Barbieri (2):
> x86, asm: Refactor atomic64_386_32.S to support old binutils and be
> cleaner
> x86, asm: Use a lower case name for the end macro in
> atomic64_386_32.S
>
> Namhyung Kim (1):
> x86: Document __phys_reloc_hide() usage in __pa_symbol()
>
> arch/x86/include/asm/page.h | 7 +
> arch/x86/kernel/apic/apic.c | 2 +-
> arch/x86/kernel/mpparse.c | 16 +++
> arch/x86/lib/atomic64_386_32.S | 238
> ++++++++++++++++++++++------------------
> 4 files changed, 154 insertions(+), 109 deletions(-)
>
> diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
> index 625c3f0..8ca8283 100644
> --- a/arch/x86/include/asm/page.h
> +++ b/arch/x86/include/asm/page.h
> @@ -37,6 +37,13 @@ static inline void copy_user_page(void *to, void *from,
> unsigned long vaddr,
> #define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x))
> /* __pa_symbol should be used for C visible symbols.
> This seems to be the official gcc blessed way to do such arithmetic. */
> +/*
> + * We need __phys_reloc_hide() here because gcc may assume that there is
> no
> + * overflow during __pa() calculation and can optimize it unexpectedly.
> + * Newer versions of gcc provide -fno-strict-overflow switch to handle
> this
> + * case properly. Once all supported versions of gcc understand it, we
> can
> + * remove this Voodoo magic stuff. (i.e. once gcc3.x is deprecated)
> + */
> #define __pa_symbol(x) __pa(__phys_reloc_hide((unsigned long)(x)))
>
> #define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET))
> diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
> index 980508c..e3b534c 100644
> --- a/arch/x86/kernel/apic/apic.c
> +++ b/arch/x86/kernel/apic/apic.c
> @@ -1606,7 +1606,7 @@ void __init init_apic_mappings(void)
> * acpi lapic path already maps that address in
> * acpi_register_lapic_address()
> */
> - if (!acpi_lapic)
> + if (!acpi_lapic && !smp_found_config)
> set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
>
> apic_printk(APIC_VERBOSE, "mapped APIC to %08lx (%08lx)\n",
> diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
> index d86dbf7..d7b6f7f 100644
> --- a/arch/x86/kernel/mpparse.c
> +++ b/arch/x86/kernel/mpparse.c
> @@ -274,6 +274,18 @@ static void __init smp_dump_mptable(struct mpc_table
> *mpc, unsigned char *mpt)
>
> void __init default_smp_read_mpc_oem(struct mpc_table *mpc) { }
>
> +static void __init smp_register_lapic_address(unsigned long address)
> +{
> + mp_lapic_addr = address;
> +
> + set_fixmap_nocache(FIX_APIC_BASE, address);
> + if (boot_cpu_physical_apicid == -1U) {
> + boot_cpu_physical_apicid = read_apic_id();
> + apic_version[boot_cpu_physical_apicid] =
> + GET_APIC_VERSION(apic_read(APIC_LVR));
> + }
> +}
> +
> static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
> {
> char str[16];
> @@ -295,6 +307,10 @@ static int __init smp_read_mpc(struct mpc_table *mpc,
> unsigned early)
> if (early)
> return 1;
>
> + /* Initialize the lapic mapping */
> + if (!acpi_lapic)
> + smp_register_lapic_address(mpc->lapic);
> +
> if (mpc->oemptr)
> x86_init.mpparse.smp_read_mpc_oem(mpc);
>
> diff --git a/arch/x86/lib/atomic64_386_32.S
> b/arch/x86/lib/atomic64_386_32.S
> index 4a5979a..2cda60a 100644
> --- a/arch/x86/lib/atomic64_386_32.S
> +++ b/arch/x86/lib/atomic64_386_32.S
> @@ -25,150 +25,172 @@
> CFI_ADJUST_CFA_OFFSET -4
> .endm
>
> -.macro BEGIN func reg
> -$v = \reg
> -
> -ENTRY(atomic64_\func\()_386)
> - CFI_STARTPROC
> - LOCK $v
> -
> -.macro RETURN
> - UNLOCK $v
> +#define BEGIN(op) \
> +.macro endp; \
> + CFI_ENDPROC; \
> +ENDPROC(atomic64_##op##_386); \
> +.purgem endp; \
> +.endm; \
> +ENTRY(atomic64_##op##_386); \
> + CFI_STARTPROC; \
> + LOCK v;
> +
> +#define ENDP endp
> +
> +#define RET \
> + UNLOCK v; \
> ret
> -.endm
> -
> -.macro END_
> - CFI_ENDPROC
> -ENDPROC(atomic64_\func\()_386)
> -.purgem RETURN
> -.purgem END_
> -.purgem END
> -.endm
> -
> -.macro END
> -RETURN
> -END_
> -.endm
> -.endm
>
> -BEGIN read %ecx
> - movl ($v), %eax
> - movl 4($v), %edx
> -END
> -
> -BEGIN set %esi
> - movl %ebx, ($v)
> - movl %ecx, 4($v)
> -END
> -
> -BEGIN xchg %esi
> - movl ($v), %eax
> - movl 4($v), %edx
> - movl %ebx, ($v)
> - movl %ecx, 4($v)
> -END
> -
> -BEGIN add %ecx
> - addl %eax, ($v)
> - adcl %edx, 4($v)
> -END
> -
> -BEGIN add_return %ecx
> - addl ($v), %eax
> - adcl 4($v), %edx
> - movl %eax, ($v)
> - movl %edx, 4($v)
> -END
> -
> -BEGIN sub %ecx
> - subl %eax, ($v)
> - sbbl %edx, 4($v)
> -END
> -
> -BEGIN sub_return %ecx
> +#define RET_ENDP \
> + RET; \
> + ENDP
> +
> +#define v %ecx
> +BEGIN(read)
> + movl (v), %eax
> + movl 4(v), %edx
> +RET_ENDP
> +#undef v
> +
> +#define v %esi
> +BEGIN(set)
> + movl %ebx, (v)
> + movl %ecx, 4(v)
> +RET_ENDP
> +#undef v
> +
> +#define v %esi
> +BEGIN(xchg)
> + movl (v), %eax
> + movl 4(v), %edx
> + movl %ebx, (v)
> + movl %ecx, 4(v)
> +RET_ENDP
> +#undef v
> +
> +#define v %ecx
> +BEGIN(add)
> + addl %eax, (v)
> + adcl %edx, 4(v)
> +RET_ENDP
> +#undef v
> +
> +#define v %ecx
> +BEGIN(add_return)
> + addl (v), %eax
> + adcl 4(v), %edx
> + movl %eax, (v)
> + movl %edx, 4(v)
> +RET_ENDP
> +#undef v
> +
> +#define v %ecx
> +BEGIN(sub)
> + subl %eax, (v)
> + sbbl %edx, 4(v)
> +RET_ENDP
> +#undef v
> +
> +#define v %ecx
> +BEGIN(sub_return)
> negl %edx
> negl %eax
> sbbl $0, %edx
> - addl ($v), %eax
> - adcl 4($v), %edx
> - movl %eax, ($v)
> - movl %edx, 4($v)
> -END
> -
> -BEGIN inc %esi
> - addl $1, ($v)
> - adcl $0, 4($v)
> -END
> -
> -BEGIN inc_return %esi
> - movl ($v), %eax
> - movl 4($v), %edx
> + addl (v), %eax
> + adcl 4(v), %edx
> + movl %eax, (v)
> + movl %edx, 4(v)
> +RET_ENDP
> +#undef v
> +
> +#define v %esi
> +BEGIN(inc)
> + addl $1, (v)
> + adcl $0, 4(v)
> +RET_ENDP
> +#undef v
> +
> +#define v %esi
> +BEGIN(inc_return)
> + movl (v), %eax
> + movl 4(v), %edx
> addl $1, %eax
> adcl $0, %edx
> - movl %eax, ($v)
> - movl %edx, 4($v)
> -END
> -
> -BEGIN dec %esi
> - subl $1, ($v)
> - sbbl $0, 4($v)
> -END
> -
> -BEGIN dec_return %esi
> - movl ($v), %eax
> - movl 4($v), %edx
> + movl %eax, (v)
> + movl %edx, 4(v)
> +RET_ENDP
> +#undef v
> +
> +#define v %esi
> +BEGIN(dec)
> + subl $1, (v)
> + sbbl $0, 4(v)
> +RET_ENDP
> +#undef v
> +
> +#define v %esi
> +BEGIN(dec_return)
> + movl (v), %eax
> + movl 4(v), %edx
> subl $1, %eax
> sbbl $0, %edx
> - movl %eax, ($v)
> - movl %edx, 4($v)
> -END
> + movl %eax, (v)
> + movl %edx, 4(v)
> +RET_ENDP
> +#undef v
>
> -BEGIN add_unless %ecx
> +#define v %ecx
> +BEGIN(add_unless)
> addl %eax, %esi
> adcl %edx, %edi
> - addl ($v), %eax
> - adcl 4($v), %edx
> + addl (v), %eax
> + adcl 4(v), %edx
> cmpl %eax, %esi
> je 3f
> 1:
> - movl %eax, ($v)
> - movl %edx, 4($v)
> + movl %eax, (v)
> + movl %edx, 4(v)
> movl $1, %eax
> 2:
> -RETURN
> + RET
> 3:
> cmpl %edx, %edi
> jne 1b
> xorl %eax, %eax
> jmp 2b
> -END_
> +ENDP
> +#undef v
>
> -BEGIN inc_not_zero %esi
> - movl ($v), %eax
> - movl 4($v), %edx
> +#define v %esi
> +BEGIN(inc_not_zero)
> + movl (v), %eax
> + movl 4(v), %edx
> testl %eax, %eax
> je 3f
> 1:
> addl $1, %eax
> adcl $0, %edx
> - movl %eax, ($v)
> - movl %edx, 4($v)
> + movl %eax, (v)
> + movl %edx, 4(v)
> movl $1, %eax
> 2:
> -RETURN
> + RET
> 3:
> testl %edx, %edx
> jne 1b
> jmp 2b
> -END_
> +ENDP
> +#undef v
>
> -BEGIN dec_if_positive %esi
> - movl ($v), %eax
> - movl 4($v), %edx
> +#define v %esi
> +BEGIN(dec_if_positive)
> + movl (v), %eax
> + movl 4(v), %edx
> subl $1, %eax
> sbbl $0, %edx
> js 1f
> - movl %eax, ($v)
> - movl %edx, 4($v)
> + movl %eax, (v)
> + movl %edx, 4(v)
> 1:
> -END
> +RET_ENDP
> +#undef v
>
> --
> This message has been scanned for viruses and
> dangerous content by MailScanner, and is
> believed to be clean.
>
>
--
This message has been scanned for viruses and
dangerous content by MailScanner, and is
believed to be clean.