* [PATCH v8 3/8] powerpc/vdso: Remove unused \tmp param in __get_datapage()
From: Christophe Leroy @ 2020-04-28 13:16 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, nathanl
Cc: linux-arch, arnd, linux-kernel, luto, tglx, vincenzo.frascino,
linuxppc-dev
In-Reply-To: <cover.1588079622.git.christophe.leroy@c-s.fr>
The \tmp param is not used anymore, remove it.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v7: New patch, splitted out of preceding patch
---
arch/powerpc/include/asm/vdso_datapage.h | 2 +-
arch/powerpc/kernel/vdso32/cacheflush.S | 2 +-
arch/powerpc/kernel/vdso32/datapage.S | 4 ++--
arch/powerpc/kernel/vdso32/gettimeofday.S | 8 ++++----
arch/powerpc/kernel/vdso64/cacheflush.S | 2 +-
arch/powerpc/kernel/vdso64/datapage.S | 4 ++--
arch/powerpc/kernel/vdso64/gettimeofday.S | 8 ++++----
7 files changed, 15 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index 11886467dfdf..f3d7e4e2a45b 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -116,7 +116,7 @@ extern struct vdso_data *vdso_data;
#else /* __ASSEMBLY__ */
-.macro get_datapage ptr, tmp
+.macro get_datapage ptr
bcl 20, 31, .+4
999:
mflr \ptr
diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S
index 3440ddf21c8b..017843bf5382 100644
--- a/arch/powerpc/kernel/vdso32/cacheflush.S
+++ b/arch/powerpc/kernel/vdso32/cacheflush.S
@@ -27,7 +27,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache)
#ifdef CONFIG_PPC64
mflr r12
.cfi_register lr,r12
- get_datapage r10, r0
+ get_datapage r10
mtlr r12
#endif
diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S
index 5513a4f8253e..0513a2eabec8 100644
--- a/arch/powerpc/kernel/vdso32/datapage.S
+++ b/arch/powerpc/kernel/vdso32/datapage.S
@@ -28,7 +28,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
mflr r12
.cfi_register lr,r12
mr. r4,r3
- get_datapage r3, r0
+ get_datapage r3
mtlr r12
addi r3,r3,CFG_SYSCALL_MAP32
beqlr
@@ -49,7 +49,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
.cfi_startproc
mflr r12
.cfi_register lr,r12
- get_datapage r3, r0
+ get_datapage r3
lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3)
lwz r3,CFG_TB_TICKS_PER_SEC(r3)
mtlr r12
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index a3951567118a..0bbdce0f2a9c 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -34,7 +34,7 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
mr. r10,r3 /* r10 saves tv */
mr r11,r4 /* r11 saves tz */
- get_datapage r9, r0
+ get_datapage r9
beq 3f
LOAD_REG_IMMEDIATE(r7, 1000000) /* load up USEC_PER_SEC */
bl __do_get_tspec@local /* get sec/usec from tb & kernel */
@@ -79,7 +79,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
mflr r12 /* r12 saves lr */
.cfi_register lr,r12
mr r11,r4 /* r11 saves tp */
- get_datapage r9, r0
+ get_datapage r9
LOAD_REG_IMMEDIATE(r7, NSEC_PER_SEC) /* load up NSEC_PER_SEC */
beq cr5, .Lcoarse_clocks
.Lprecise_clocks:
@@ -206,7 +206,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
mflr r12
.cfi_register lr,r12
- get_datapage r3, r0
+ get_datapage r3
lwz r5, CLOCK_HRTIMER_RES(r3)
mtlr r12
1: li r3,0
@@ -240,7 +240,7 @@ V_FUNCTION_BEGIN(__kernel_time)
.cfi_register lr,r12
mr r11,r3 /* r11 holds t */
- get_datapage r9, r0
+ get_datapage r9
lwz r3,STAMP_XTIME_SEC+LOPART(r9)
diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S
index cab14324242b..61985de5758f 100644
--- a/arch/powerpc/kernel/vdso64/cacheflush.S
+++ b/arch/powerpc/kernel/vdso64/cacheflush.S
@@ -25,7 +25,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache)
.cfi_startproc
mflr r12
.cfi_register lr,r12
- get_datapage r10, r0
+ get_datapage r10
mtlr r12
lwz r7,CFG_DCACHE_BLOCKSZ(r10)
diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S
index 03bb72c440dc..00760dc69d68 100644
--- a/arch/powerpc/kernel/vdso64/datapage.S
+++ b/arch/powerpc/kernel/vdso64/datapage.S
@@ -28,7 +28,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
mflr r12
.cfi_register lr,r12
mr r4,r3
- get_datapage r3, r0
+ get_datapage r3
mtlr r12
addi r3,r3,CFG_SYSCALL_MAP64
cmpldi cr0,r4,0
@@ -50,7 +50,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
.cfi_startproc
mflr r12
.cfi_register lr,r12
- get_datapage r3, r0
+ get_datapage r3
ld r3,CFG_TB_TICKS_PER_SEC(r3)
mtlr r12
crclr cr0*4+so
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index e54c4ce4d356..275f031d0bf1 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -26,7 +26,7 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
mr r11,r3 /* r11 holds tv */
mr r10,r4 /* r10 holds tz */
- get_datapage r3, r0
+ get_datapage r3
cmpldi r11,0 /* check if tv is NULL */
beq 2f
lis r7,1000000@ha /* load up USEC_PER_SEC */
@@ -71,7 +71,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
mflr r12 /* r12 saves lr */
.cfi_register lr,r12
mr r11,r4 /* r11 saves tp */
- get_datapage r3, r0
+ get_datapage r3
lis r7,NSEC_PER_SEC@h /* want nanoseconds */
ori r7,r7,NSEC_PER_SEC@l
beq cr5,70f
@@ -188,7 +188,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
mflr r12
.cfi_register lr,r12
- get_datapage r3, r0
+ get_datapage r3
lwz r5, CLOCK_HRTIMER_RES(r3)
mtlr r12
li r3,0
@@ -221,7 +221,7 @@ V_FUNCTION_BEGIN(__kernel_time)
.cfi_register lr,r12
mr r11,r3 /* r11 holds t */
- get_datapage r3, r0
+ get_datapage r3
ld r4,STAMP_XTIME_SEC(r3)
--
2.25.0
^ permalink raw reply related
* [PATCH v8 4/8] powerpc/processor: Move cpu_relax() into asm/vdso/processor.h
From: Christophe Leroy @ 2020-04-28 13:16 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, nathanl
Cc: linux-arch, arnd, linux-kernel, luto, tglx, vincenzo.frascino,
linuxppc-dev
In-Reply-To: <cover.1588079622.git.christophe.leroy@c-s.fr>
cpu_relax() need to be in asm/vdso/processor.h to be used by
the C VDSO generic library.
Move it there.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/processor.h | 10 ++--------
arch/powerpc/include/asm/vdso/processor.h | 23 +++++++++++++++++++++++
2 files changed, 25 insertions(+), 8 deletions(-)
create mode 100644 arch/powerpc/include/asm/vdso/processor.h
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index bfa336fbcfeb..8390503c44a2 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -6,6 +6,8 @@
* Copyright (C) 2001 PPC 64 Team, IBM Corp
*/
+#include <vdso/processor.h>
+
#include <asm/reg.h>
#ifdef CONFIG_VSX
@@ -63,14 +65,6 @@ extern int _chrp_type;
#endif /* defined(__KERNEL__) && defined(CONFIG_PPC32) */
-/* Macros for adjusting thread priority (hardware multi-threading) */
-#define HMT_very_low() asm volatile("or 31,31,31 # very low priority")
-#define HMT_low() asm volatile("or 1,1,1 # low priority")
-#define HMT_medium_low() asm volatile("or 6,6,6 # medium low priority")
-#define HMT_medium() asm volatile("or 2,2,2 # medium priority")
-#define HMT_medium_high() asm volatile("or 5,5,5 # medium high priority")
-#define HMT_high() asm volatile("or 3,3,3 # high priority")
-
#ifdef __KERNEL__
#ifdef CONFIG_PPC64
diff --git a/arch/powerpc/include/asm/vdso/processor.h b/arch/powerpc/include/asm/vdso/processor.h
new file mode 100644
index 000000000000..39b9beace9ca
--- /dev/null
+++ b/arch/powerpc/include/asm/vdso/processor.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_VDSO_PROCESSOR_H
+#define __ASM_VDSO_PROCESSOR_H
+
+#ifndef __ASSEMBLY__
+
+/* Macros for adjusting thread priority (hardware multi-threading) */
+#define HMT_very_low() asm volatile("or 31, 31, 31 # very low priority")
+#define HMT_low() asm volatile("or 1, 1, 1 # low priority")
+#define HMT_medium_low() asm volatile("or 6, 6, 6 # medium low priority")
+#define HMT_medium() asm volatile("or 2, 2, 2 # medium priority")
+#define HMT_medium_high() asm volatile("or 5, 5, 5 # medium high priority")
+#define HMT_high() asm volatile("or 3, 3, 3 # high priority")
+
+#ifdef CONFIG_PPC64
+#define cpu_relax() do { HMT_low(); HMT_medium(); barrier(); } while (0)
+#else
+#define cpu_relax() barrier()
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_PROCESSOR_H */
--
2.25.0
^ permalink raw reply related
* [PATCH v8 1/8] powerpc/vdso64: Switch from __get_datapage() to get_datapage inline macro
From: Christophe Leroy @ 2020-04-28 13:16 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, nathanl
Cc: linux-arch, arnd, linux-kernel, luto, tglx, vincenzo.frascino,
linuxppc-dev
In-Reply-To: <cover.1588079622.git.christophe.leroy@c-s.fr>
On the same way as already done on PPC32, drop __get_datapage()
function and use get_datapage inline macro instead.
See commit ec0895f08f99 ("powerpc/vdso32: inline __get_datapage()")
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/kernel/vdso64/cacheflush.S | 9 ++++----
arch/powerpc/kernel/vdso64/datapage.S | 28 +++--------------------
arch/powerpc/kernel/vdso64/gettimeofday.S | 8 +++----
3 files changed, 11 insertions(+), 34 deletions(-)
diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S
index 526f5ba2593e..cab14324242b 100644
--- a/arch/powerpc/kernel/vdso64/cacheflush.S
+++ b/arch/powerpc/kernel/vdso64/cacheflush.S
@@ -8,6 +8,7 @@
#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
#include <asm/asm-offsets.h>
.text
@@ -24,14 +25,12 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache)
.cfi_startproc
mflr r12
.cfi_register lr,r12
- mr r11,r3
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r10, r0
mtlr r12
- mr r10,r3
lwz r7,CFG_DCACHE_BLOCKSZ(r10)
addi r5,r7,-1
- andc r6,r11,r5 /* round low to line bdy */
+ andc r6,r3,r5 /* round low to line bdy */
subf r8,r6,r4 /* compute length */
add r8,r8,r5 /* ensure we get enough */
lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10)
@@ -48,7 +47,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache)
lwz r7,CFG_ICACHE_BLOCKSZ(r10)
addi r5,r7,-1
- andc r6,r11,r5 /* round low to line bdy */
+ andc r6,r3,r5 /* round low to line bdy */
subf r8,r6,r4 /* compute length */
add r8,r8,r5
lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10)
diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S
index dc84f5ae3802..067247d3efb9 100644
--- a/arch/powerpc/kernel/vdso64/datapage.S
+++ b/arch/powerpc/kernel/vdso64/datapage.S
@@ -10,35 +10,13 @@
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
.text
.global __kernel_datapage_offset;
__kernel_datapage_offset:
.long 0
-V_FUNCTION_BEGIN(__get_datapage)
- .cfi_startproc
- /* We don't want that exposed or overridable as we want other objects
- * to be able to bl directly to here
- */
- .protected __get_datapage
- .hidden __get_datapage
-
- mflr r0
- .cfi_register lr,r0
-
- bcl 20,31,data_page_branch
-data_page_branch:
- mflr r3
- mtlr r0
- addi r3, r3, __kernel_datapage_offset-data_page_branch
- lwz r0,0(r3)
- .cfi_restore lr
- add r3,r0,r3
- blr
- .cfi_endproc
-V_FUNCTION_END(__get_datapage)
-
/*
* void *__kernel_get_syscall_map(unsigned int *syscall_count) ;
*
@@ -53,7 +31,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
mflr r12
.cfi_register lr,r12
mr r4,r3
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r3, r0
mtlr r12
addi r3,r3,CFG_SYSCALL_MAP64
cmpldi cr0,r4,0
@@ -75,7 +53,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
.cfi_startproc
mflr r12
.cfi_register lr,r12
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r3, r0
ld r3,CFG_TB_TICKS_PER_SEC(r3)
mtlr r12
crclr cr0*4+so
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index 1c9a04703250..e54c4ce4d356 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -26,7 +26,7 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
mr r11,r3 /* r11 holds tv */
mr r10,r4 /* r10 holds tz */
- bl V_LOCAL_FUNC(__get_datapage) /* get data page */
+ get_datapage r3, r0
cmpldi r11,0 /* check if tv is NULL */
beq 2f
lis r7,1000000@ha /* load up USEC_PER_SEC */
@@ -71,7 +71,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
mflr r12 /* r12 saves lr */
.cfi_register lr,r12
mr r11,r4 /* r11 saves tp */
- bl V_LOCAL_FUNC(__get_datapage) /* get data page */
+ get_datapage r3, r0
lis r7,NSEC_PER_SEC@h /* want nanoseconds */
ori r7,r7,NSEC_PER_SEC@l
beq cr5,70f
@@ -188,7 +188,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
mflr r12
.cfi_register lr,r12
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r3, r0
lwz r5, CLOCK_HRTIMER_RES(r3)
mtlr r12
li r3,0
@@ -221,7 +221,7 @@ V_FUNCTION_BEGIN(__kernel_time)
.cfi_register lr,r12
mr r11,r3 /* r11 holds t */
- bl V_LOCAL_FUNC(__get_datapage)
+ get_datapage r3, r0
ld r4,STAMP_XTIME_SEC(r3)
--
2.25.0
^ permalink raw reply related
* [PATCH v8 2/8] powerpc/vdso: Remove __kernel_datapage_offset and simplify __get_datapage()
From: Christophe Leroy @ 2020-04-28 13:16 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, nathanl
Cc: linux-arch, arnd, linux-kernel, luto, tglx, vincenzo.frascino,
linuxppc-dev
In-Reply-To: <cover.1588079622.git.christophe.leroy@c-s.fr>
The VDSO datapage and the text pages are always located immediately
next to each other, so it can be hardcoded without an indirection
through __kernel_datapage_offset
In order to ease things, move the data page in front like other
arches, that way there is no need to know the size of the library
to locate the data page.
Before:
clock-getres-realtime-coarse: vdso: 714 nsec/call
clock-gettime-realtime-coarse: vdso: 792 nsec/call
clock-gettime-realtime: vdso: 1243 nsec/call
After:
clock-getres-realtime-coarse: vdso: 699 nsec/call
clock-gettime-realtime-coarse: vdso: 784 nsec/call
clock-gettime-realtime: vdso: 1231 nsec/call
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v7:
- Moved the removal of the tmp param of __get_datapage()
in a subsequent patch
- Included the addition of the offset param to __get_datapage()
in the further preparatory patch
---
arch/powerpc/include/asm/vdso_datapage.h | 8 ++--
arch/powerpc/kernel/vdso.c | 53 ++++--------------------
arch/powerpc/kernel/vdso32/datapage.S | 3 --
arch/powerpc/kernel/vdso32/vdso32.lds.S | 7 +---
arch/powerpc/kernel/vdso64/datapage.S | 3 --
arch/powerpc/kernel/vdso64/vdso64.lds.S | 7 +---
6 files changed, 16 insertions(+), 65 deletions(-)
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index b9ef6cf50ea5..11886467dfdf 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -118,10 +118,12 @@ extern struct vdso_data *vdso_data;
.macro get_datapage ptr, tmp
bcl 20, 31, .+4
+999:
mflr \ptr
- addi \ptr, \ptr, (__kernel_datapage_offset - (.-4))@l
- lwz \tmp, 0(\ptr)
- add \ptr, \tmp, \ptr
+#if CONFIG_PPC_PAGE_SHIFT > 14
+ addis \ptr, \ptr, (_vdso_datapage - 999b)@ha
+#endif
+ addi \ptr, \ptr, (_vdso_datapage - 999b)@l
.endm
#endif /* __ASSEMBLY__ */
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index f38f26e844b6..d33fa22ddbed 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -190,7 +190,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
* install_special_mapping or the perf counter mmap tracking code
* will fail to recognise it as a vDSO (since arch_vma_name fails).
*/
- current->mm->context.vdso_base = vdso_base;
+ current->mm->context.vdso_base = vdso_base + PAGE_SIZE;
/*
* our vma flags don't have VM_WRITE so by default, the process isn't
@@ -482,42 +482,6 @@ static __init void vdso_setup_trampolines(struct lib32_elfinfo *v32,
vdso32_rt_sigtramp = find_function32(v32, "__kernel_sigtramp_rt32");
}
-static __init int vdso_fixup_datapage(struct lib32_elfinfo *v32,
- struct lib64_elfinfo *v64)
-{
-#ifdef CONFIG_VDSO32
- Elf32_Sym *sym32;
-#endif
-#ifdef CONFIG_PPC64
- Elf64_Sym *sym64;
-
- sym64 = find_symbol64(v64, "__kernel_datapage_offset");
- if (sym64 == NULL) {
- printk(KERN_ERR "vDSO64: Can't find symbol "
- "__kernel_datapage_offset !\n");
- return -1;
- }
- *((int *)(vdso64_kbase + sym64->st_value - VDSO64_LBASE)) =
- (vdso64_pages << PAGE_SHIFT) -
- (sym64->st_value - VDSO64_LBASE);
-#endif /* CONFIG_PPC64 */
-
-#ifdef CONFIG_VDSO32
- sym32 = find_symbol32(v32, "__kernel_datapage_offset");
- if (sym32 == NULL) {
- printk(KERN_ERR "vDSO32: Can't find symbol "
- "__kernel_datapage_offset !\n");
- return -1;
- }
- *((int *)(vdso32_kbase + (sym32->st_value - VDSO32_LBASE))) =
- (vdso32_pages << PAGE_SHIFT) -
- (sym32->st_value - VDSO32_LBASE);
-#endif
-
- return 0;
-}
-
-
static __init int vdso_fixup_features(struct lib32_elfinfo *v32,
struct lib64_elfinfo *v64)
{
@@ -618,9 +582,6 @@ static __init int vdso_setup(void)
if (vdso_do_find_sections(&v32, &v64))
return -1;
- if (vdso_fixup_datapage(&v32, &v64))
- return -1;
-
if (vdso_fixup_features(&v32, &v64))
return -1;
@@ -761,26 +722,26 @@ static int __init vdso_init(void)
vdso32_pagelist = kcalloc(vdso32_pages + 2, sizeof(struct page *),
GFP_KERNEL);
BUG_ON(vdso32_pagelist == NULL);
+ vdso32_pagelist[0] = virt_to_page(vdso_data);
for (i = 0; i < vdso32_pages; i++) {
struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE);
get_page(pg);
- vdso32_pagelist[i] = pg;
+ vdso32_pagelist[i + 1] = pg;
}
- vdso32_pagelist[i++] = virt_to_page(vdso_data);
- vdso32_pagelist[i] = NULL;
+ vdso32_pagelist[i + 1] = NULL;
#endif
#ifdef CONFIG_PPC64
vdso64_pagelist = kcalloc(vdso64_pages + 2, sizeof(struct page *),
GFP_KERNEL);
BUG_ON(vdso64_pagelist == NULL);
+ vdso64_pagelist[0] = virt_to_page(vdso_data);
for (i = 0; i < vdso64_pages; i++) {
struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE);
get_page(pg);
- vdso64_pagelist[i] = pg;
+ vdso64_pagelist[i + 1] = pg;
}
- vdso64_pagelist[i++] = virt_to_page(vdso_data);
- vdso64_pagelist[i] = NULL;
+ vdso64_pagelist[i + 1] = NULL;
#endif /* CONFIG_PPC64 */
get_page(virt_to_page(vdso_data));
diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S
index 217bb630f8f9..5513a4f8253e 100644
--- a/arch/powerpc/kernel/vdso32/datapage.S
+++ b/arch/powerpc/kernel/vdso32/datapage.S
@@ -13,9 +13,6 @@
#include <asm/vdso_datapage.h>
.text
- .global __kernel_datapage_offset;
-__kernel_datapage_offset:
- .long 0
/*
* void *__kernel_get_syscall_map(unsigned int *syscall_count) ;
diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
index 5206c2eb2a1d..6cf729612268 100644
--- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
@@ -4,6 +4,7 @@
* library
*/
#include <asm/vdso.h>
+#include <asm/page.h>
#ifdef __LITTLE_ENDIAN__
OUTPUT_FORMAT("elf32-powerpcle", "elf32-powerpcle", "elf32-powerpcle")
@@ -15,6 +16,7 @@ ENTRY(_start)
SECTIONS
{
+ PROVIDE(_vdso_datapage = . - PAGE_SIZE);
. = VDSO32_LBASE + SIZEOF_HEADERS;
.hash : { *(.hash) } :text
@@ -138,11 +140,6 @@ VERSION
{
VDSO_VERSION_STRING {
global:
- /*
- * Has to be there for the kernel to find
- */
- __kernel_datapage_offset;
-
__kernel_get_syscall_map;
#ifndef CONFIG_PPC_BOOK3S_601
__kernel_gettimeofday;
diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S
index 067247d3efb9..03bb72c440dc 100644
--- a/arch/powerpc/kernel/vdso64/datapage.S
+++ b/arch/powerpc/kernel/vdso64/datapage.S
@@ -13,9 +13,6 @@
#include <asm/vdso_datapage.h>
.text
-.global __kernel_datapage_offset;
-__kernel_datapage_offset:
- .long 0
/*
* void *__kernel_get_syscall_map(unsigned int *syscall_count) ;
diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S
index 256fb9720298..f58c7e2e9cbd 100644
--- a/arch/powerpc/kernel/vdso64/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S
@@ -4,6 +4,7 @@
* library
*/
#include <asm/vdso.h>
+#include <asm/page.h>
#ifdef __LITTLE_ENDIAN__
OUTPUT_FORMAT("elf64-powerpcle", "elf64-powerpcle", "elf64-powerpcle")
@@ -15,6 +16,7 @@ ENTRY(_start)
SECTIONS
{
+ PROVIDE(_vdso_datapage = . - PAGE_SIZE);
. = VDSO64_LBASE + SIZEOF_HEADERS;
.hash : { *(.hash) } :text
@@ -138,11 +140,6 @@ VERSION
{
VDSO_VERSION_STRING {
global:
- /*
- * Has to be there for the kernel to find
- */
- __kernel_datapage_offset;
-
__kernel_get_syscall_map;
__kernel_gettimeofday;
__kernel_clock_gettime;
--
2.25.0
^ permalink raw reply related
* Re: [PATCH] tty: hvc: Fix data abort due to race in hvc_open
From: Markus Elfring @ 2020-04-28 12:48 UTC (permalink / raw)
To: Raghavendra Rao Ananta, linuxppc-dev
Cc: Greg Kroah-Hartman, Andrew Melnychenko, linux-kernel, Jiri Slaby
> Hence, serialize hvc_open and check if tty->private_data is NULL before
> proceeding ahead.
How do you think about to add the tag “Fixes” because of adjustments
for the data synchronisation?
…
> +++ b/drivers/tty/hvc/hvc_console.c
…
@@ -384,6 +394,8 @@ static int hvc_open(struct tty_struct *tty, struct file * filp)
…
> +out:
> + mutex_unlock(&hvc_open_mutex);
> return rc;
> }
I suggest to use the label “unlock” instead.
Regards,
Markus
^ permalink raw reply
* [PATCH] powerpc: Drop unneeded cast in task_pt_regs()
From: Michael Ellerman @ 2020-04-28 12:31 UTC (permalink / raw)
To: linuxppc-dev
There's no need to cast in task_pt_regs() as tsk->thread.regs should
already be a struct pt_regs. If someone's using task_pt_regs() on
something that's not a task but happens to have a thread.regs then
we'll deal with them later.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/processor.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index bfa336fbcfeb..8e855c78d780 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -307,7 +307,7 @@ struct thread_struct {
}
#endif
-#define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.regs)
+#define task_pt_regs(tsk) ((tsk)->thread.regs)
unsigned long get_wchan(struct task_struct *p);
--
2.25.1
^ permalink raw reply related
* [PATCH] powerpc/64: Don't initialise init_task->thread.regs
From: Michael Ellerman @ 2020-04-28 12:31 UTC (permalink / raw)
To: linuxppc-dev; +Cc: aneesh.kumar
Aneesh increased the size of struct pt_regs by 16 bytes and started
seeing this WARN_ON:
smp: Bringing up secondary CPUs ...
------------[ cut here ]------------
WARNING: CPU: 0 PID: 0 at arch/powerpc/kernel/process.c:455 giveup_all+0xb4/0x110
Modules linked in:
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.7.0-rc2-gcc-8.2.0-1.g8f6a41f-default+ #318
NIP: c00000000001a2b4 LR: c00000000001a29c CTR: c0000000031d0000
REGS: c0000000026d3980 TRAP: 0700 Not tainted (5.7.0-rc2-gcc-8.2.0-1.g8f6a41f-default+)
MSR: 800000000282b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE> CR: 48048224 XER: 00000000
CFAR: c000000000019cc8 IRQMASK: 1
GPR00: c00000000001a264 c0000000026d3c20 c0000000026d7200 800000000280b033
GPR04: 0000000000000001 0000000000000000 0000000000000077 30206d7372203164
GPR08: 0000000000002000 0000000002002000 800000000280b033 3230303030303030
GPR12: 0000000000008800 c0000000031d0000 0000000000800050 0000000002000066
GPR16: 000000000309a1a0 000000000309a4b0 000000000309a2d8 000000000309a890
GPR20: 00000000030d0098 c00000000264da40 00000000fd620000 c0000000ff798080
GPR24: c00000000264edf0 c0000001007469f0 00000000fd620000 c0000000020e5e90
GPR28: c00000000264edf0 c00000000264d200 000000001db60000 c00000000264d200
NIP [c00000000001a2b4] giveup_all+0xb4/0x110
LR [c00000000001a29c] giveup_all+0x9c/0x110
Call Trace:
[c0000000026d3c20] [c00000000001a264] giveup_all+0x64/0x110 (unreliable)
[c0000000026d3c90] [c00000000001ae34] __switch_to+0x104/0x480
[c0000000026d3cf0] [c000000000e0b8a0] __schedule+0x320/0x970
[c0000000026d3dd0] [c000000000e0c518] schedule_idle+0x38/0x70
[c0000000026d3df0] [c00000000019c7c8] do_idle+0x248/0x3f0
[c0000000026d3e70] [c00000000019cbb8] cpu_startup_entry+0x38/0x40
[c0000000026d3ea0] [c000000000011bb0] rest_init+0xe0/0xf8
[c0000000026d3ed0] [c000000002004820] start_kernel+0x990/0x9e0
[c0000000026d3f90] [c00000000000c49c] start_here_common+0x1c/0x400
Which was unexpected. The warning is checking the thread.regs->msr
value of the task we are switching from:
usermsr = tsk->thread.regs->msr;
...
WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC)));
ie. if MSR_VSX is set then both of MSR_FP and MSR_VEC are also set.
Dumping tsk->thread.regs->msr we see that it's: 0x1db60000
Which is not a normal looking MSR, in fact the only valid bit is
MSR_VSX, all the other bits are reserved in the current definition of
the MSR.
We can see from the oops that it was swapper/0 that we were switching
from when we hit the warning, ie. init_task. So its thread.regs points
to the base (high addresses) in init_stack.
Dumping the content of init_task->thread.regs, with the members of
pt_regs annotated (the 16 bytes larger version), we see:
0000000000000000 c000000002780080 gpr[0] gpr[1]
0000000000000000 c000000002666008 gpr[2] gpr[3]
c0000000026d3ed0 0000000000000078 gpr[4] gpr[5]
c000000000011b68 c000000002780080 gpr[6] gpr[7]
0000000000000000 0000000000000000 gpr[8] gpr[9]
c0000000026d3f90 0000800000002200 gpr[10] gpr[11]
c000000002004820 c0000000026d7200 gpr[12] gpr[13]
000000001db60000 c0000000010aabe8 gpr[14] gpr[15]
c0000000010aabe8 c0000000010aabe8 gpr[16] gpr[17]
c00000000294d598 0000000000000000 gpr[18] gpr[19]
0000000000000000 0000000000001ff8 gpr[20] gpr[21]
0000000000000000 c00000000206d608 gpr[22] gpr[23]
c00000000278e0cc 0000000000000000 gpr[24] gpr[25]
000000002fff0000 c000000000000000 gpr[26] gpr[27]
0000000002000000 0000000000000028 gpr[28] gpr[29]
000000001db60000 0000000004750000 gpr[30] gpr[31]
0000000002000000 000000001db60000 nip msr
0000000000000000 0000000000000000 orig_r3 ctr
c00000000000c49c 0000000000000000 link xer
0000000000000000 0000000000000000 ccr softe
0000000000000000 0000000000000000 trap dar
0000000000000000 0000000000000000 dsisr result
0000000000000000 0000000000000000 ppr kuap
0000000000000000 0000000000000000 pad[2] pad[3]
This looks suspiciously like stack frames, not a pt_regs. If we look
closely we can see return addresses from the stack trace above,
c000000002004820 (start_kernel) and c00000000000c49c (start_here_common).
init_task->thread.regs is setup at build time in processor.h:
#define INIT_THREAD { \
.ksp = INIT_SP, \
.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
The early boot code where we setup the initial stack is:
LOAD_REG_ADDR(r3,init_thread_union)
/* set up a stack pointer */
LOAD_REG_IMMEDIATE(r1,THREAD_SIZE)
add r1,r3,r1
li r0,0
stdu r0,-STACK_FRAME_OVERHEAD(r1)
Which creates a stack frame of size 112 bytes (STACK_FRAME_OVERHEAD).
Which is far too small to contain a pt_regs.
So the result is init_task->thread.regs is pointing at some stack
frames on the init stack, not at a pt_regs.
We have gotten away with this for so long because with pt_regs at its
current size the MSR happens to point into the first frame, at a
location that is not written to by the early asm. With the 16 byte
expansion the MSR falls into the second frame, which is used by the
compiler, and collides with a saved register that tends to be
non-zero.
As far as I can see this has been wrong since the original merge of
64-bit ppc support, back in 2002.
Conceptually swapper should have no regs, it never entered from
userspace, and in fact that's what we do on 32-bit. It's also
presumably what the "bogus" comment is referring to.
So I think the right fix is to just not-initialise regs at all. I'm
slightly worried this will break some code that isn't prepared for a
NULL regs, but we'll have to see.
Remove the comment in head_64.S which refers to us setting up the
regs (even though we never did), and is otherwise not really accurate
any more.
Reported-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/processor.h | 1 -
arch/powerpc/kernel/head_64.S | 9 +--------
2 files changed, 1 insertion(+), 9 deletions(-)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 8e855c78d780..5ab202055d5a 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -300,7 +300,6 @@ struct thread_struct {
#else
#define INIT_THREAD { \
.ksp = INIT_SP, \
- .regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
.addr_limit = KERNEL_DS, \
.fpexc_mode = 0, \
.fscr = FSCR_TAR | FSCR_EBB \
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index ddfbd02140d9..0e05a9a47a4b 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -947,15 +947,8 @@ __REF
std r0,0(r4)
#endif
- /* The following gets the stack set up with the regs */
- /* pointing to the real addr of the kernel stack. This is */
- /* all done to support the C function call below which sets */
- /* up the htab. This is done because we have relocated the */
- /* kernel but are still running in real mode. */
-
- LOAD_REG_ADDR(r3,init_thread_union)
-
/* set up a stack pointer */
+ LOAD_REG_ADDR(r3,init_thread_union)
LOAD_REG_IMMEDIATE(r1,THREAD_SIZE)
add r1,r3,r1
li r0,0
--
2.25.1
^ permalink raw reply related
* [RFC PATCH] powerpc/spufs: fix copy_to_user while atomic
From: Jeremy Kerr @ 2020-04-28 12:02 UTC (permalink / raw)
To: Linus Torvalds, Arnd Bergmann, Eric W . Biederman, Andrew Morton,
Alexander Viro, Christoph Hellwig, Michael Ellerman
Cc: linux-fsdevel, linuxppc-dev, linux-kernel
In-Reply-To: <20200427200626.1622060-2-hch@lst.de>
Currently, we may perform a copy_to_user (through
simple_read_from_buffer()) while holding a context's register_lock,
while accessing the context save area.
This change uses a temporary buffers for the context save area data,
which we then pass to simple_read_from_buffer.
Signed-off-by: Jeremy Kerr <jk@ozlabs.org>
---
Christoph - this fixes the copy_to_user while atomic, hopefully with
only minimal distruption to your series.
---
arch/powerpc/platforms/cell/spufs/file.c | 110 +++++++++++++++--------
1 file changed, 74 insertions(+), 36 deletions(-)
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index c0f950a3f4e1..c62d77ddaf7d 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -1978,8 +1978,9 @@ static ssize_t __spufs_mbox_info_read(struct spu_context *ctx,
static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf,
size_t len, loff_t *pos)
{
- int ret;
struct spu_context *ctx = file->private_data;
+ u32 stat, data;
+ int ret;
if (!access_ok(buf, len))
return -EFAULT;
@@ -1988,11 +1989,16 @@ static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf,
if (ret)
return ret;
spin_lock(&ctx->csa.register_lock);
- ret = __spufs_mbox_info_read(ctx, buf, len, pos);
+ stat = ctx->csa.prob.mb_stat_R;
+ data = ctx->csa.prob.pu_mb_R;
spin_unlock(&ctx->csa.register_lock);
spu_release_saved(ctx);
- return ret;
+ /* EOF if there's no entry in the mbox */
+ if (!(stat & 0x0000ff))
+ return 0;
+
+ return simple_read_from_buffer(buf, len, pos, &data, sizeof(data));
}
static const struct file_operations spufs_mbox_info_fops = {
@@ -2019,6 +2025,7 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf,
size_t len, loff_t *pos)
{
struct spu_context *ctx = file->private_data;
+ u32 stat, data;
int ret;
if (!access_ok(buf, len))
@@ -2028,11 +2035,16 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf,
if (ret)
return ret;
spin_lock(&ctx->csa.register_lock);
- ret = __spufs_ibox_info_read(ctx, buf, len, pos);
+ stat = ctx->csa.prob.mb_stat_R;
+ data = ctx->csa.priv2.puint_mb_R;
spin_unlock(&ctx->csa.register_lock);
spu_release_saved(ctx);
- return ret;
+ /* EOF if there's no entry in the ibox */
+ if (!(stat & 0xff0000))
+ return 0;
+
+ return simple_read_from_buffer(buf, len, pos, &data, sizeof(data));
}
static const struct file_operations spufs_ibox_info_fops = {
@@ -2041,6 +2053,11 @@ static const struct file_operations spufs_ibox_info_fops = {
.llseek = generic_file_llseek,
};
+static size_t spufs_wbox_info_cnt(struct spu_context *ctx)
+{
+ return (4 - ((ctx->csa.prob.mb_stat_R & 0x00ff00) >> 8)) * sizeof(u32);
+}
+
static ssize_t __spufs_wbox_info_read(struct spu_context *ctx,
char __user *buf, size_t len, loff_t *pos)
{
@@ -2049,7 +2066,7 @@ static ssize_t __spufs_wbox_info_read(struct spu_context *ctx,
u32 wbox_stat;
wbox_stat = ctx->csa.prob.mb_stat_R;
- cnt = 4 - ((wbox_stat & 0x00ff00) >> 8);
+ cnt = spufs_wbox_info_cnt(ctx);
for (i = 0; i < cnt; i++) {
data[i] = ctx->csa.spu_mailbox_data[i];
}
@@ -2062,7 +2079,8 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf,
size_t len, loff_t *pos)
{
struct spu_context *ctx = file->private_data;
- int ret;
+ u32 data[ARRAY_SIZE(ctx->csa.spu_mailbox_data)];
+ int ret, count;
if (!access_ok(buf, len))
return -EFAULT;
@@ -2071,11 +2089,13 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf,
if (ret)
return ret;
spin_lock(&ctx->csa.register_lock);
- ret = __spufs_wbox_info_read(ctx, buf, len, pos);
+ count = spufs_wbox_info_cnt(ctx);
+ memcpy(&data, &ctx->csa.spu_mailbox_data, sizeof(data));
spin_unlock(&ctx->csa.register_lock);
spu_release_saved(ctx);
- return ret;
+ return simple_read_from_buffer(buf, len, pos, &data,
+ count * sizeof(u32));
}
static const struct file_operations spufs_wbox_info_fops = {
@@ -2084,20 +2104,19 @@ static const struct file_operations spufs_wbox_info_fops = {
.llseek = generic_file_llseek,
};
-static ssize_t __spufs_dma_info_read(struct spu_context *ctx,
- char __user *buf, size_t len, loff_t *pos)
+static void ___spufs_dma_info_read(struct spu_context *ctx,
+ struct spu_dma_info *info)
{
- struct spu_dma_info info;
struct mfc_cq_sr *qp, *spuqp;
int i;
- info.dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW;
- info.dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0];
- info.dma_info_status = ctx->csa.spu_chnldata_RW[24];
- info.dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25];
- info.dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27];
+ info->dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW;
+ info->dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0];
+ info->dma_info_status = ctx->csa.spu_chnldata_RW[24];
+ info->dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25];
+ info->dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27];
for (i = 0; i < 16; i++) {
- qp = &info.dma_info_command_data[i];
+ qp = &info->dma_info_command_data[i];
spuqp = &ctx->csa.priv2.spuq[i];
qp->mfc_cq_data0_RW = spuqp->mfc_cq_data0_RW;
@@ -2105,6 +2124,14 @@ static ssize_t __spufs_dma_info_read(struct spu_context *ctx,
qp->mfc_cq_data2_RW = spuqp->mfc_cq_data2_RW;
qp->mfc_cq_data3_RW = spuqp->mfc_cq_data3_RW;
}
+}
+
+static ssize_t __spufs_dma_info_read(struct spu_context *ctx,
+ char __user *buf, size_t len, loff_t *pos)
+{
+ struct spu_dma_info info;
+
+ ___spufs_dma_info_read(ctx, &info);
return simple_read_from_buffer(buf, len, pos, &info,
sizeof info);
@@ -2114,6 +2141,7 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf,
size_t len, loff_t *pos)
{
struct spu_context *ctx = file->private_data;
+ struct spu_dma_info info;
int ret;
if (!access_ok(buf, len))
@@ -2123,11 +2151,12 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf,
if (ret)
return ret;
spin_lock(&ctx->csa.register_lock);
- ret = __spufs_dma_info_read(ctx, buf, len, pos);
+ ___spufs_dma_info_read(ctx, &info);
spin_unlock(&ctx->csa.register_lock);
spu_release_saved(ctx);
- return ret;
+ return simple_read_from_buffer(buf, len, pos, &info,
+ sizeof(info));
}
static const struct file_operations spufs_dma_info_fops = {
@@ -2136,13 +2165,31 @@ static const struct file_operations spufs_dma_info_fops = {
.llseek = no_llseek,
};
+static void ___spufs_proxydma_info_read(struct spu_context *ctx,
+ struct spu_proxydma_info *info)
+{
+ int i;
+
+ info->proxydma_info_type = ctx->csa.prob.dma_querytype_RW;
+ info->proxydma_info_mask = ctx->csa.prob.dma_querymask_RW;
+ info->proxydma_info_status = ctx->csa.prob.dma_tagstatus_R;
+
+ for (i = 0; i < 8; i++) {
+ struct mfc_cq_sr *qp = &info->proxydma_info_command_data[i];
+ struct mfc_cq_sr *puqp = &ctx->csa.priv2.puq[i];
+
+ qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW;
+ qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW;
+ qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW;
+ qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW;
+ }
+}
+
static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx,
char __user *buf, size_t len, loff_t *pos)
{
struct spu_proxydma_info info;
- struct mfc_cq_sr *qp, *puqp;
int ret = sizeof info;
- int i;
if (len < ret)
return -EINVAL;
@@ -2150,18 +2197,7 @@ static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx,
if (!access_ok(buf, len))
return -EFAULT;
- info.proxydma_info_type = ctx->csa.prob.dma_querytype_RW;
- info.proxydma_info_mask = ctx->csa.prob.dma_querymask_RW;
- info.proxydma_info_status = ctx->csa.prob.dma_tagstatus_R;
- for (i = 0; i < 8; i++) {
- qp = &info.proxydma_info_command_data[i];
- puqp = &ctx->csa.priv2.puq[i];
-
- qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW;
- qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW;
- qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW;
- qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW;
- }
+ ___spufs_proxydma_info_read(ctx, &info);
return simple_read_from_buffer(buf, len, pos, &info,
sizeof info);
@@ -2171,17 +2207,19 @@ static ssize_t spufs_proxydma_info_read(struct file *file, char __user *buf,
size_t len, loff_t *pos)
{
struct spu_context *ctx = file->private_data;
+ struct spu_proxydma_info info;
int ret;
ret = spu_acquire_saved(ctx);
if (ret)
return ret;
spin_lock(&ctx->csa.register_lock);
- ret = __spufs_proxydma_info_read(ctx, buf, len, pos);
+ ___spufs_proxydma_info_read(ctx, &info);
spin_unlock(&ctx->csa.register_lock);
spu_release_saved(ctx);
- return ret;
+ return simple_read_from_buffer(buf, len, pos, &info,
+ sizeof(info));
}
static const struct file_operations spufs_proxydma_info_fops = {
--
2.17.1
^ permalink raw reply related
* Re: [PATCH] powerpc: Add interrupt mode information in /proc/cpuinfo
From: Cédric Le Goater @ 2020-04-28 11:36 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev
In-Reply-To: <87v9ljg9dz.fsf@mpe.ellerman.id.au>
On 4/28/20 1:03 PM, Michael Ellerman wrote:
> Cédric Le Goater <clg@kaod.org> writes:
>> PowerNV and pSeries machines can run using the XIVE or XICS interrupt
>> mode. Report this information in /proc/cpuinfo :
>>
>> timebase : 512000000
>> platform : PowerNV
>> model : 9006-22C
>> machine : PowerNV 9006-22C
>> firmware : OPAL
>> MMU : Radix
>> IRQ : XIVE
>
> Hmmmm, I dunno. At what point do we stop putting random non CPU-related
> things in cpuinfo? :)
True.
> The IRQ mode is (reasonably) easily discovered in sys, eg:
>
> $ cat /sys/kernel/irq/*/chip_name | grep -m 1 XIVE
> XIVE-IRQ
>
> vs:
>
> $ cat /sys/kernel/irq/*/chip_name | grep -m 1 XICS
> XICS
That's good enough for error reporting
Thanks.
C.
>
> cheers
>
>> diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
>> index 3bc188da82ba..39ef3394038d 100644
>> --- a/arch/powerpc/platforms/powernv/setup.c
>> +++ b/arch/powerpc/platforms/powernv/setup.c
>> @@ -196,14 +196,18 @@ static void pnv_show_cpuinfo(struct seq_file *m)
>> model = of_get_property(root, "model", NULL);
>> seq_printf(m, "machine\t\t: PowerNV %s\n", model);
>> if (firmware_has_feature(FW_FEATURE_OPAL))
>> - seq_printf(m, "firmware\t: OPAL\n");
>> + seq_puts(m, "firmware\t: OPAL\n");
>> else
>> - seq_printf(m, "firmware\t: BML\n");
>> + seq_puts(m, "firmware\t: BML\n");
>> of_node_put(root);
>> if (radix_enabled())
>> - seq_printf(m, "MMU\t\t: Radix\n");
>> + seq_puts(m, "MMU\t\t: Radix\n");
>> else
>> - seq_printf(m, "MMU\t\t: Hash\n");
>> + seq_puts(m, "MMU\t\t: Hash\n");
>> + if (xive_enabled())
>> + seq_puts(m, "IRQ\t\t: XIVE\n");
>> + else
>> + seq_puts(m, "IRQ\t\t: XICS\n");
>> }
>>
>> static void pnv_prepare_going_down(void)
>> diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
>> index 0c8421dd01ab..d248fca67797 100644
>> --- a/arch/powerpc/platforms/pseries/setup.c
>> +++ b/arch/powerpc/platforms/pseries/setup.c
>> @@ -95,9 +95,13 @@ static void pSeries_show_cpuinfo(struct seq_file *m)
>> seq_printf(m, "machine\t\t: CHRP %s\n", model);
>> of_node_put(root);
>> if (radix_enabled())
>> - seq_printf(m, "MMU\t\t: Radix\n");
>> + seq_puts(m, "MMU\t\t: Radix\n");
>> else
>> - seq_printf(m, "MMU\t\t: Hash\n");
>> + seq_puts(m, "MMU\t\t: Hash\n");
>> + if (xive_enabled())
>> + seq_puts(m, "IRQ\t\t: XIVE\n");
>> + else
>> + seq_puts(m, "IRQ\t\t: XICS\n");
>> }
>>
>> /* Initialize firmware assisted non-maskable interrupts if
>> --
>> 2.25.3
^ permalink raw reply
* [PATCH] powerpc/spufs: Add rcu_read_lock() around fcheck()
From: Michael Ellerman @ 2020-04-28 11:48 UTC (permalink / raw)
To: linuxppc-dev; +Cc: linux-kernel, hch, viro, jk
Currently the spu coredump code triggers an RCU warning:
=============================
WARNING: suspicious RCU usage
5.7.0-rc3-01755-g7cd49f0b7ec7 #1 Not tainted
-----------------------------
include/linux/fdtable.h:95 suspicious rcu_dereference_check() usage!
other info that might help us debug this:
rcu_scheduler_active = 2, debug_locks = 1
1 lock held by spu-coredump/1343:
#0: c0000007fa22f430 (sb_writers#2){.+.+}-{0:0}, at: .do_coredump+0x1010/0x13c8
stack backtrace:
CPU: 0 PID: 1343 Comm: spu-coredump Not tainted 5.7.0-rc3-01755-g7cd49f0b7ec7 #1
Call Trace:
.dump_stack+0xec/0x15c (unreliable)
.lockdep_rcu_suspicious+0x120/0x144
.coredump_next_context+0x148/0x158
.spufs_coredump_extra_notes_size+0x54/0x190
.elf_coredump_extra_notes_size+0x34/0x50
.elf_core_dump+0xe48/0x19d0
.do_coredump+0xe50/0x13c8
.get_signal+0x864/0xd88
.do_notify_resume+0x158/0x3c8
.interrupt_exit_user_prepare+0x19c/0x208
interrupt_return+0x14/0x1c0
This comes from fcheck_files() via fcheck().
It's pretty clearly documented that fcheck() must be wrapped with
rcu_read_lock(), so fix it.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/platforms/cell/spufs/coredump.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 8b3296b62f65..0fc52cbaa552 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -82,13 +82,19 @@ static int match_context(const void *v, struct file *file, unsigned fd)
*/
static struct spu_context *coredump_next_context(int *fd)
{
+ struct spu_context *ctx;
struct file *file;
int n = iterate_fd(current->files, *fd, match_context, NULL);
if (!n)
return NULL;
*fd = n - 1;
+
+ rcu_read_lock();
file = fcheck(*fd);
- return SPUFS_I(file_inode(file))->i_ctx;
+ ctx = SPUFS_I(file_inode(file))->i_ctx;
+ rcu_read_unlock();
+
+ return ctx;
}
int spufs_coredump_extra_notes_size(void)
--
2.25.1
^ permalink raw reply related
* Re: [PATCH v4] pci: Make return value of pcie_capability_read*() consistent
From: Bjorn Helgaas @ 2020-04-28 11:43 UTC (permalink / raw)
To: Yicong Yang
Cc: Thomas Bogendoerfer, Saheed Bolarinwa, skhan, linux-mips,
linux-kernel, linux-pci, bjorn, linuxppc-dev
In-Reply-To: <4cc16e59-d346-5523-5072-eebe77d06a08@hisilicon.com>
On Tue, Apr 28, 2020 at 10:19:08AM +0800, Yicong Yang wrote:
> On 2020/4/28 2:13, Bjorn Helgaas wrote:
> >
> > I'm starting to think we're approaching this backwards. I searched
> > for PCIBIOS_FUNC_NOT_SUPPORTED, PCIBIOS_BAD_VENDOR_ID, and the other
> > error values. Almost every use is a *return* in a config accessor.
> > There are very, very few *tests* for these values.
>
> If we have certain reasons to reserve PCI_BIOS* error to identify
> PCI errors in PCI drivers, maybe redefine the PCI_BIOS* to generic
> error codes can solve the issues, and no need to call
> pcibios_err_to_errno() to do the conversion. Few changes may be
> made to current codes. One possible patch may look like below.
> Otherwise, maybe convert all PCI_BIOS* errors to generic error codes
> is a better idea.
>
> Not sure it's the best way or not. Just FYI.
That's a brilliant idea! We should still look carefully at all the
callers of the config accessors, but this would avoid changing all the
arch accessors, so the patch would be dramatically smaller.
> diff --git a/include/linux/pci.h b/include/linux/pci.h
> index 83ce1cd..843987c 100644
> --- a/include/linux/pci.h
> +++ b/include/linux/pci.h
> @@ -675,14 +675,18 @@ static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev) { return false;
>
> /* Error values that may be returned by PCI functions */
> #define PCIBIOS_SUCCESSFUL 0x00
> -#define PCIBIOS_FUNC_NOT_SUPPORTED 0x81
> -#define PCIBIOS_BAD_VENDOR_ID 0x83
> -#define PCIBIOS_DEVICE_NOT_FOUND 0x86
> -#define PCIBIOS_BAD_REGISTER_NUMBER 0x87
> -#define PCIBIOS_SET_FAILED 0x88
> -#define PCIBIOS_BUFFER_TOO_SMALL 0x89
> -
> -/* Translate above to generic errno for passing back through non-PCI code */
> +#define PCIBIOS_FUNC_NOT_SUPPORTED -ENOENT
> +#define PCIBIOS_BAD_VENDOR_ID -ENOTTY
> +#define PCIBIOS_DEVICE_NOT_FOUND -ENODEV
> +#define PCIBIOS_BAD_REGISTER_NUMBER -EFAULT
> +#define PCIBIOS_SET_FAILED -EIO
> +#define PCIBIOS_BUFFER_TOO_SMALL -ENOSPC
> +
> +/**
> + * Translate above to generic errno for passing back through non-PCI code
> + *
> + * Deprecated. Use the PCIBIOS_* directly without a translation.
> + */
> static inline int pcibios_err_to_errno(int err)
> {
> if (err <= PCIBIOS_SUCCESSFUL)
> @@ -690,17 +694,12 @@ static inline int pcibios_err_to_errno(int err)
>
> switch (err) {
> case PCIBIOS_FUNC_NOT_SUPPORTED:
> - return -ENOENT;
> case PCIBIOS_BAD_VENDOR_ID:
> - return -ENOTTY;
> case PCIBIOS_DEVICE_NOT_FOUND:
> - return -ENODEV;
> case PCIBIOS_BAD_REGISTER_NUMBER:
> - return -EFAULT;
> case PCIBIOS_SET_FAILED:
> - return -EIO;
> case PCIBIOS_BUFFER_TOO_SMALL:
> - return -ENOSPC;
> + return err;
> }
>
> return -ERANGE;
>
> > For example, the only tests for PCIBIOS_FUNC_NOT_SUPPORTED are in
> > xen_pcibios_err_to_errno() and pcibios_err_to_errno(), i.e., we're
> > just converting that value to -ENOENT or the Xen-specific thing.
> >
> > So I think the best approach might be to remove the PCIBIOS_* error
> > values completely and replace them with the corresponding values from
> > pcibios_err_to_errno(). For example, a part of the patch would look
> > like this:
> >
> > diff --git a/arch/mips/pci/ops-emma2rh.c b/arch/mips/pci/ops-emma2rh.c
> > index 65f47344536c..d4d9c902c147 100644
> > --- a/arch/mips/pci/ops-emma2rh.c
> > +++ b/arch/mips/pci/ops-emma2rh.c
> > @@ -100,7 +100,7 @@ static int pci_config_read(struct pci_bus *bus, unsigned int devfn, int where,
> > break;
> > default:
> > emma2rh_out32(EMMA2RH_PCI_IWIN0_CTR, backup_win0);
> > - return PCIBIOS_FUNC_NOT_SUPPORTED;
> > + return -ENOENT;
> > }
> >
> > emma2rh_out32(EMMA2RH_PCI_IWIN0_CTR, backup_win0);
> > @@ -149,7 +149,7 @@ static int pci_config_write(struct pci_bus *bus, unsigned int devfn, int where,
> > break;
> > default:
> > emma2rh_out32(EMMA2RH_PCI_IWIN0_CTR, backup_win0);
> > - return PCIBIOS_FUNC_NOT_SUPPORTED;
> > + return -ENOENT;
> > }
> > *(volatile u32 *)(base + (PCI_FUNC(devfn) << 8) +
> > (where & 0xfffffffc)) = data;
> > diff --git a/include/linux/pci.h b/include/linux/pci.h
> > index 83ce1cdf5676..f95637a8d391 100644
> > --- a/include/linux/pci.h
> > +++ b/include/linux/pci.h
> > @@ -675,7 +675,6 @@ static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev) { return false;
> >
> > /* Error values that may be returned by PCI functions */
> > #define PCIBIOS_SUCCESSFUL 0x00
> > -#define PCIBIOS_FUNC_NOT_SUPPORTED 0x81
> > #define PCIBIOS_BAD_VENDOR_ID 0x83
> > #define PCIBIOS_DEVICE_NOT_FOUND 0x86
> > #define PCIBIOS_BAD_REGISTER_NUMBER 0x87
> > @@ -689,8 +688,6 @@ static inline int pcibios_err_to_errno(int err)
> > return err; /* Assume already errno */
> >
> > switch (err) {
> > - case PCIBIOS_FUNC_NOT_SUPPORTED:
> > - return -ENOENT;
> > case PCIBIOS_BAD_VENDOR_ID:
> > return -ENOTTY;
> > case PCIBIOS_DEVICE_NOT_FOUND:
> > .
> >
>
^ permalink raw reply
* [PATCH v2] powerpc/64: BE option to use ELFv2 ABI for big endian kernels
From: Nicholas Piggin @ 2020-04-28 11:25 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin
Provide an option to use ELFv2 ABI for big endian builds. This works on
GCC and clang (since 2014). It is less well tested and supported by the
GNU toolchain, but it can give some useful advantages of the ELFv2 ABI
for BE (e.g., less stack usage). Some distros even build BE ELFv2
userspace.
Reviewed-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
Since v1:
- Improved the override flavour name suggested by Segher.
- Improved changelog wording.
arch/powerpc/Kconfig | 19 +++++++++++++++++++
arch/powerpc/Makefile | 15 ++++++++++-----
arch/powerpc/boot/Makefile | 4 ++++
drivers/crypto/vmx/Makefile | 8 ++++++--
drivers/crypto/vmx/ppc-xlate.pl | 10 ++++++----
5 files changed, 45 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 924c541a9260..d9d2abc06c2c 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -147,6 +147,7 @@ config PPC
select ARCH_WEAK_RELEASE_ACQUIRE
select BINFMT_ELF
select BUILDTIME_TABLE_SORT
+ select BUILD_ELF_V2 if PPC64 && CPU_LITTLE_ENDIAN
select CLONE_BACKWARDS
select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN
select DYNAMIC_FTRACE if FUNCTION_TRACER
@@ -541,6 +542,24 @@ config KEXEC_FILE
config ARCH_HAS_KEXEC_PURGATORY
def_bool KEXEC_FILE
+config BUILD_ELF_V2
+ bool
+
+config BUILD_BIG_ENDIAN_ELF_V2
+ bool "Build big-endian kernel using ELFv2 ABI (EXPERIMENTAL)"
+ depends on PPC64 && CPU_BIG_ENDIAN && EXPERT
+ default n
+ select BUILD_ELF_V2
+ help
+ This builds the kernel image using the ELFv2 ABI, which has a
+ reduced stack overhead and faster function calls. This does not
+ affect the userspace ABIs.
+
+ ELFv2 is the standard ABI for little-endian, but for big-endian
+ this is an experimental option that is less tested (kernel and
+ toolchain). This requires gcc 4.9 or newer and binutils 2.24 or
+ newer.
+
config RELOCATABLE
bool "Build a relocatable kernel"
depends on PPC64 || (FLATMEM && (44x || FSL_BOOKE))
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index f310c32e88a4..e306b39d847e 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -92,10 +92,14 @@ endif
ifdef CONFIG_PPC64
ifndef CONFIG_CC_IS_CLANG
-cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1)
-cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mcall-aixdesc)
-aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1)
-aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mabi=elfv2
+ifdef CONFIG_BUILD_ELF_V2
+cflags-y += $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc))
+aflags-y += $(call cc-option,-mabi=elfv2)
+else
+cflags-y += $(call cc-option,-mabi=elfv1)
+cflags-y += $(call cc-option,-mcall-aixdesc)
+aflags-y += $(call cc-option,-mabi=elfv1)
+endif
endif
endif
@@ -144,7 +148,7 @@ endif
CFLAGS-$(CONFIG_PPC64) := $(call cc-option,-mtraceback=no)
ifndef CONFIG_CC_IS_CLANG
-ifdef CONFIG_CPU_LITTLE_ENDIAN
+ifdef CONFIG_BUILD_ELF_V2
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc))
AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2)
else
@@ -153,6 +157,7 @@ CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcall-aixdesc)
AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1)
endif
endif
+
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions)
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index c53a1b8bba8b..03942d08695d 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -41,6 +41,10 @@ endif
BOOTCFLAGS += -isystem $(shell $(BOOTCC) -print-file-name=include)
+ifdef CONFIG_BUILD_ELF_V2
+BOOTCFLAGS += $(call cc-option,-mabi=elfv2)
+endif
+
ifdef CONFIG_CPU_BIG_ENDIAN
BOOTCFLAGS += -mbig-endian
else
diff --git a/drivers/crypto/vmx/Makefile b/drivers/crypto/vmx/Makefile
index 709670d2b553..9aea34602beb 100644
--- a/drivers/crypto/vmx/Makefile
+++ b/drivers/crypto/vmx/Makefile
@@ -5,18 +5,22 @@ vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o aes
ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
override flavour := linux-ppc64le
else
+ifdef CONFIG_BUILD_ELF_V2
+override flavour := linux-ppc64-elfv2
+else
override flavour := linux-ppc64
endif
+endif
quiet_cmd_perl = PERL $@
cmd_perl = $(PERL) $(<) $(flavour) > $(@)
targets += aesp8-ppc.S ghashp8-ppc.S
-$(obj)/aesp8-ppc.S: $(src)/aesp8-ppc.pl FORCE
+$(obj)/aesp8-ppc.S: $(src)/aesp8-ppc.pl $(src)/ppc-xlate.pl FORCE
$(call if_changed,perl)
-$(obj)/ghashp8-ppc.S: $(src)/ghashp8-ppc.pl FORCE
+$(obj)/ghashp8-ppc.S: $(src)/ghashp8-ppc.pl $(src)/ppc-xlate.pl FORCE
$(call if_changed,perl)
clean-files := aesp8-ppc.S ghashp8-ppc.S
diff --git a/drivers/crypto/vmx/ppc-xlate.pl b/drivers/crypto/vmx/ppc-xlate.pl
index 36db2ef09e5b..9db0937d318b 100644
--- a/drivers/crypto/vmx/ppc-xlate.pl
+++ b/drivers/crypto/vmx/ppc-xlate.pl
@@ -9,6 +9,8 @@ open STDOUT,">$output" || die "can't open $output: $!";
my %GLOBALS;
my $dotinlocallabels=($flavour=~/linux/)?1:0;
+my $abielfv2=(($flavour =~ /linux-ppc64le/) or ($flavour =~ /linux-ppc64-elfv2/))?1:0;
+my $dotfunctions=($abielfv2=~1)?0:1;
################################################################
# directives which need special treatment on different platforms
@@ -40,7 +42,7 @@ my $globl = sub {
};
my $text = sub {
my $ret = ($flavour =~ /aix/) ? ".csect\t.text[PR],7" : ".text";
- $ret = ".abiversion 2\n".$ret if ($flavour =~ /linux.*64le/);
+ $ret = ".abiversion 2\n".$ret if ($abielfv2);
$ret;
};
my $machine = sub {
@@ -56,8 +58,8 @@ my $size = sub {
if ($flavour =~ /linux/)
{ shift;
my $name = shift; $name =~ s|^[\.\_]||;
- my $ret = ".size $name,.-".($flavour=~/64$/?".":"").$name;
- $ret .= "\n.size .$name,.-.$name" if ($flavour=~/64$/);
+ my $ret = ".size $name,.-".($dotfunctions?".":"").$name;
+ $ret .= "\n.size .$name,.-.$name" if ($dotfunctions);
$ret;
}
else
@@ -142,7 +144,7 @@ my $vmr = sub {
# Some ABIs specify vrsave, special-purpose register #256, as reserved
# for system use.
-my $no_vrsave = ($flavour =~ /linux-ppc64le/);
+my $no_vrsave = ($abielfv2);
my $mtspr = sub {
my ($f,$idx,$ra) = @_;
if ($idx == 256 && $no_vrsave) {
--
2.23.0
^ permalink raw reply related
* Re: [PATCH] powerpc: Add interrupt mode information in /proc/cpuinfo
From: Michael Ellerman @ 2020-04-28 11:03 UTC (permalink / raw)
To: Cédric Le Goater; +Cc: linuxppc-dev, Cédric Le Goater
In-Reply-To: <20200427140644.332815-1-clg@kaod.org>
Cédric Le Goater <clg@kaod.org> writes:
> PowerNV and pSeries machines can run using the XIVE or XICS interrupt
> mode. Report this information in /proc/cpuinfo :
>
> timebase : 512000000
> platform : PowerNV
> model : 9006-22C
> machine : PowerNV 9006-22C
> firmware : OPAL
> MMU : Radix
> IRQ : XIVE
Hmmmm, I dunno. At what point do we stop putting random non CPU-related
things in cpuinfo? :)
The IRQ mode is (reasonably) easily discovered in sys, eg:
$ cat /sys/kernel/irq/*/chip_name | grep -m 1 XIVE
XIVE-IRQ
vs:
$ cat /sys/kernel/irq/*/chip_name | grep -m 1 XICS
XICS
cheers
> diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
> index 3bc188da82ba..39ef3394038d 100644
> --- a/arch/powerpc/platforms/powernv/setup.c
> +++ b/arch/powerpc/platforms/powernv/setup.c
> @@ -196,14 +196,18 @@ static void pnv_show_cpuinfo(struct seq_file *m)
> model = of_get_property(root, "model", NULL);
> seq_printf(m, "machine\t\t: PowerNV %s\n", model);
> if (firmware_has_feature(FW_FEATURE_OPAL))
> - seq_printf(m, "firmware\t: OPAL\n");
> + seq_puts(m, "firmware\t: OPAL\n");
> else
> - seq_printf(m, "firmware\t: BML\n");
> + seq_puts(m, "firmware\t: BML\n");
> of_node_put(root);
> if (radix_enabled())
> - seq_printf(m, "MMU\t\t: Radix\n");
> + seq_puts(m, "MMU\t\t: Radix\n");
> else
> - seq_printf(m, "MMU\t\t: Hash\n");
> + seq_puts(m, "MMU\t\t: Hash\n");
> + if (xive_enabled())
> + seq_puts(m, "IRQ\t\t: XIVE\n");
> + else
> + seq_puts(m, "IRQ\t\t: XICS\n");
> }
>
> static void pnv_prepare_going_down(void)
> diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
> index 0c8421dd01ab..d248fca67797 100644
> --- a/arch/powerpc/platforms/pseries/setup.c
> +++ b/arch/powerpc/platforms/pseries/setup.c
> @@ -95,9 +95,13 @@ static void pSeries_show_cpuinfo(struct seq_file *m)
> seq_printf(m, "machine\t\t: CHRP %s\n", model);
> of_node_put(root);
> if (radix_enabled())
> - seq_printf(m, "MMU\t\t: Radix\n");
> + seq_puts(m, "MMU\t\t: Radix\n");
> else
> - seq_printf(m, "MMU\t\t: Hash\n");
> + seq_puts(m, "MMU\t\t: Hash\n");
> + if (xive_enabled())
> + seq_puts(m, "IRQ\t\t: XIVE\n");
> + else
> + seq_puts(m, "IRQ\t\t: XICS\n");
> }
>
> /* Initialize firmware assisted non-maskable interrupts if
> --
> 2.25.3
^ permalink raw reply
* Re: [PATCH v2 1/2] cpufreq: qoriq: convert to a platform driver
From: Viresh Kumar @ 2020-04-28 11:01 UTC (permalink / raw)
To: rjw, Mian Yousaf Kaukab
Cc: andy.tang, linux-pm, sboyd, linuxppc-dev, linux-kernel,
leoyang.li, shawnguo, linux-clk, linux-arm-kernel
In-Reply-To: <20200421083000.16740-1-ykaukab@suse.de>
On 21-04-20, 10:29, Mian Yousaf Kaukab wrote:
> The driver has to be manually loaded if it is built as a module. It
> is neither exporting MODULE_DEVICE_TABLE nor MODULE_ALIAS. Moreover,
> no platform-device is created (and thus no uevent is sent) for the
> clockgen nodes it depends on.
>
> Convert the module to a platform driver with its own alias. Moreover,
> drop whitelisted SOCs. Platform device will be created only for the
> compatible platforms.
>
> Reviewed-by: Yuantian Tang <andy.tang@nxp.com>
> Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
> Signed-off-by: Mian Yousaf Kaukab <ykaukab@suse.de>
> ---
> v2:
> +Rafael, Stephen, linux-clk
> Add Reviewed-by and Acked-by tags
>
> drivers/cpufreq/qoriq-cpufreq.c | 76 ++++++++++++++++-------------------------
> 1 file changed, 29 insertions(+), 47 deletions(-)
@Rafael,
Though this looks to be PPC stuff, but it is used on both ARM and PPC. Do you
want to pick them up or should I do that ?
--
viresh
^ permalink raw reply
* Re: [PATCH v6 00/28] Initial Prefixed Instruction support
From: Balamuruhan S @ 2020-04-28 10:06 UTC (permalink / raw)
To: Jordan Niethe, linuxppc-dev; +Cc: alistair, npiggin, dja
In-Reply-To: <20200428015814.15380-1-jniethe5@gmail.com>
On Tue, 2020-04-28 at 11:57 +1000, Jordan Niethe wrote:
> A future revision of the ISA will introduce prefixed instructions. A
> prefixed instruction is composed of a 4-byte prefix followed by a
> 4-byte suffix.
>
> All prefixes have the major opcode 1. A prefix will never be a valid
> word instruction. A suffix may be an existing word instruction or a
> new instruction.
>
> This series enables prefixed instructions and extends the instruction
> emulation to support them. Then the places where prefixed instructions
> might need to be emulated are updated.
Hi Jordan,
I tried to test Kprobes with prefixed instruction on this patchset and
observed that kprobe/uprobe enablement patches are missing from v4.
Till v3 it were available,
https://patchwork.ozlabs.org/project/linuxppc-dev/patch/20200211053355.21574-11-jniethe5@gmail.com/
https://patchwork.ozlabs.org/project/linuxppc-dev/patch/20200211053355.21574-12-jniethe5@gmail.com/
was it missed for any dependencies/reason ? or will you plan it include in next
version ?
please let me know if you need help on it.
-- Bala
>
> v6 is based on feedback from Balamuruhan Suriyakumar, Alistair Popple,
> Christophe Leroy and Segher Boessenkool.
> The major changes:
> - Use the instruction type in more places that had been missed before
> - Fix issues with ppc32
> - Introduce new self tests for code patching and feature fixups
>
> v5 is based on feedback from Nick Piggins, Michael Ellerman, Balamuruhan
> Suriyakumar and Alistair Popple.
> The major changes:
> - The ppc instruction type is now a struct
> - Series now just based on next
> - ppc_inst_masked() dropped
> - Space for xmon breakpoints allocated in an assembly file
> - "Add prefixed instructions to instruction data type" patch seperated in
> to smaller patches
> - Calling convention for create_branch() is changed
> - Some places which had not been updated to use the data type are now
> updated
>
> v4 is based on feedback from Nick Piggins, Christophe Leroy and Daniel
> Axtens.
> The major changes:
> - Move xmon breakpoints from data section to text section
> - Introduce a data type for instructions on powerpc
>
> v3 is based on feedback from Christophe Leroy. The major changes:
> - Completely replacing store_inst() with patch_instruction() in
> xmon
> - Improve implementation of mread_instr() to not use mread().
> - Base the series on top of
> https://patchwork.ozlabs.org/patch/1232619/ as this will effect
> kprobes.
> - Some renaming and simplification of conditionals.
>
> v2 incorporates feedback from Daniel Axtens and and Balamuruhan
> S. The major changes are:
> - Squashing together all commits about SRR1 bits
> - Squashing all commits for supporting prefixed load stores
> - Changing abbreviated references to sufx/prfx -> suffix/prefix
> - Introducing macros for returning the length of an instruction
> - Removing sign extension flag from pstd/pld in sstep.c
> - Dropping patch "powerpc/fault: Use analyse_instr() to check for
> store with updates to sp" from the series, it did not really fit
> with prefixed enablement in the first place and as reported by Greg
> Kurz did not work correctly.
>
> Alistair Popple (1):
> powerpc: Enable Prefixed Instructions
>
> Jordan Niethe (27):
> powerpc/xmon: Remove store_inst() for patch_instruction()
> powerpc/xmon: Move breakpoint instructions to own array
> powerpc/xmon: Move breakpoints to text section
> powerpc/xmon: Use bitwise calculations in_breakpoint_table()
> powerpc: Change calling convention for create_branch() et. al.
> powerpc: Use a macro for creating instructions from u32s
> powerpc: Use an accessor for instructions
> powerpc: Use a function for getting the instruction op code
> powerpc: Use a function for byte swapping instructions
> powerpc: Introduce functions for instruction equality
> powerpc: Use a datatype for instructions
> powerpc: Use a function for reading instructions
> powerpc: Add a probe_user_read_inst() function
> powerpc: Add a probe_kernel_read_inst() function
> powerpc/kprobes: Use patch_instruction()
> powerpc: Define and use __get_user_instr{,inatomic}()
> powerpc: Introduce a function for reporting instruction length
> powerpc/xmon: Use a function for reading instructions
> powerpc/xmon: Move insertion of breakpoint for xol'ing
> powerpc: Make test_translate_branch() independent of instruction
> length
> powerpc: Define new SRR1 bits for a future ISA version
> powerpc: Add prefixed instructions to instruction data type
> powerpc: Test prefixed code patching
> powerpc: Test prefixed instructions in feature fixups
> powerpc: Support prefixed instructions in alignment handler
> powerpc sstep: Add support for prefixed load/stores
> powerpc sstep: Add support for prefixed fixed-point arithmetic
>
> arch/powerpc/include/asm/code-patching.h | 37 +-
> arch/powerpc/include/asm/inst.h | 106 ++++++
> arch/powerpc/include/asm/kprobes.h | 2 +-
> arch/powerpc/include/asm/reg.h | 7 +-
> arch/powerpc/include/asm/sstep.h | 15 +-
> arch/powerpc/include/asm/uaccess.h | 35 ++
> arch/powerpc/include/asm/uprobes.h | 7 +-
> arch/powerpc/kernel/align.c | 13 +-
> arch/powerpc/kernel/asm-offsets.c | 8 +
> arch/powerpc/kernel/epapr_paravirt.c | 7 +-
> arch/powerpc/kernel/hw_breakpoint.c | 5 +-
> arch/powerpc/kernel/jump_label.c | 5 +-
> arch/powerpc/kernel/kgdb.c | 9 +-
> arch/powerpc/kernel/kprobes.c | 24 +-
> arch/powerpc/kernel/mce_power.c | 5 +-
> arch/powerpc/kernel/module_64.c | 3 +-
> arch/powerpc/kernel/optprobes.c | 91 +++--
> arch/powerpc/kernel/optprobes_head.S | 3 +
> arch/powerpc/kernel/security.c | 9 +-
> arch/powerpc/kernel/setup_32.c | 8 +-
> arch/powerpc/kernel/trace/ftrace.c | 160 ++++----
> arch/powerpc/kernel/traps.c | 20 +-
> arch/powerpc/kernel/uprobes.c | 5 +-
> arch/powerpc/kernel/vecemu.c | 20 +-
> arch/powerpc/kvm/book3s_hv_nested.c | 2 +-
> arch/powerpc/kvm/book3s_hv_rm_mmu.c | 2 +-
> arch/powerpc/kvm/emulate_loadstore.c | 2 +-
> arch/powerpc/lib/Makefile | 2 +-
> arch/powerpc/lib/code-patching.c | 305 ++++++++-------
> arch/powerpc/lib/feature-fixups-test.S | 68 ++++
> arch/powerpc/lib/feature-fixups.c | 159 ++++++--
> arch/powerpc/lib/inst.c | 69 ++++
> arch/powerpc/lib/sstep.c | 461 ++++++++++++++++-------
> arch/powerpc/lib/test_code-patching.S | 19 +
> arch/powerpc/lib/test_emulate_step.c | 56 +--
> arch/powerpc/mm/fault.c | 15 +-
> arch/powerpc/perf/core-book3s.c | 4 +-
> arch/powerpc/xmon/Makefile | 2 +-
> arch/powerpc/xmon/xmon.c | 94 +++--
> arch/powerpc/xmon/xmon_bpts.S | 11 +
> arch/powerpc/xmon/xmon_bpts.h | 14 +
> 41 files changed, 1307 insertions(+), 582 deletions(-)
> create mode 100644 arch/powerpc/include/asm/inst.h
> create mode 100644 arch/powerpc/lib/inst.c
> create mode 100644 arch/powerpc/lib/test_code-patching.S
> create mode 100644 arch/powerpc/xmon/xmon_bpts.S
> create mode 100644 arch/powerpc/xmon/xmon_bpts.h
>
^ permalink raw reply
* [PATCH v2 3/3] mm/page_alloc: Keep memoryless cpuless node 0 offline
From: Srikar Dronamraju @ 2020-04-28 9:38 UTC (permalink / raw)
To: Andrew Morton
Cc: Michal Hocko, Srikar Dronamraju, Linus Torvalds, linux-kernel,
linux-mm, Mel Gorman, Kirill A. Shutemov, Christopher Lameter,
linuxppc-dev, Vlastimil Babka
In-Reply-To: <20200428093836.27190-1-srikar@linux.vnet.ibm.com>
Currently Linux kernel with CONFIG_NUMA on a system with multiple
possible nodes, marks node 0 as online at boot. However in practice,
there are systems which have node 0 as memoryless and cpuless.
This can cause numa_balancing to be enabled on systems with only one node
with memory and CPUs. The existence of this dummy node which is cpuless and
memoryless node can confuse users/scripts looking at output of lscpu /
numactl.
By marking, N_ONLINE as NODE_MASK_NONE, lets stop assuming that Node 0 is
always online.
v5.7-rc3
available: 2 nodes (0,2)
node 0 cpus:
node 0 size: 0 MB
node 0 free: 0 MB
node 2 cpus: 0 1 2 3 4 5 6 7
node 2 size: 32625 MB
node 2 free: 31490 MB
node distances:
node 0 2
0: 10 20
2: 20 10
proc and sys files
------------------
/sys/devices/system/node/online: 0,2
/proc/sys/kernel/numa_balancing: 1
/sys/devices/system/node/has_cpu: 2
/sys/devices/system/node/has_memory: 2
/sys/devices/system/node/has_normal_memory: 2
/sys/devices/system/node/possible: 0-31
v5.7-rc3 + patch
------------------
available: 1 nodes (2)
node 2 cpus: 0 1 2 3 4 5 6 7
node 2 size: 32625 MB
node 2 free: 31487 MB
node distances:
node 2
2: 10
proc and sys files
------------------
/sys/devices/system/node/online: 2
/proc/sys/kernel/numa_balancing: 0
/sys/devices/system/node/has_cpu: 2
/sys/devices/system/node/has_memory: 2
/sys/devices/system/node/has_normal_memory: 2
/sys/devices/system/node/possible: 0-31
Note: On Powerpc, cpu_to_node of possible but not present cpus would
previously return 0. Hence this commit depends on commit ("powerpc/numa: Set
numa_node for all possible cpus") and commit ("powerpc/numa: Prefer node id
queried from vphn"). Without the 2 commits, Powerpc system might crash.
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Christopher Lameter <cl@linux.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog v1:->v2:
- Rebased to v5.7-rc3
- Updated the changelog.
mm/page_alloc.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 69827d4fa052..03b89592af04 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -116,8 +116,10 @@ EXPORT_SYMBOL(latent_entropy);
*/
nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
[N_POSSIBLE] = NODE_MASK_ALL,
+#ifdef CONFIG_NUMA
+ [N_ONLINE] = NODE_MASK_NONE,
+#else
[N_ONLINE] = { { [0] = 1UL } },
-#ifndef CONFIG_NUMA
[N_NORMAL_MEMORY] = { { [0] = 1UL } },
#ifdef CONFIG_HIGHMEM
[N_HIGH_MEMORY] = { { [0] = 1UL } },
--
2.20.1
^ permalink raw reply related
* [PATCH v2 0/3] Offline memoryless cpuless node 0
From: Srikar Dronamraju @ 2020-04-28 9:38 UTC (permalink / raw)
To: Andrew Morton
Cc: Michal Hocko, Srikar Dronamraju, Linus Torvalds, linux-kernel,
linux-mm, Mel Gorman, Kirill A. Shutemov, Christopher Lameter,
linuxppc-dev, Vlastimil Babka
Changelog v1:->v2:
- Rebased to v5.7-rc3
- Updated the changelog.
Linux kernel configured with CONFIG_NUMA on a system with multiple
possible nodes, marks node 0 as online at boot. However in practice,
there are systems which have node 0 as memoryless and cpuless.
This can cause
1. numa_balancing to be enabled on systems with only one online node.
2. Existence of dummy (cpuless and memoryless) node which can confuse
users/scripts looking at output of lscpu / numactl.
This patchset wants to correct this anomaly.
This should only affect systems that have CONFIG_MEMORYLESS_NODES.
Currently there are only 2 architectures ia64 and powerpc that have this
config.
Note: Patch 3 in this patch series depends on patches 1 and 2.
Without patches 1 and 2, patch 3 might crash powerpc.
v5.7-rc3
available: 2 nodes (0,2)
node 0 cpus:
node 0 size: 0 MB
node 0 free: 0 MB
node 2 cpus: 0 1 2 3 4 5 6 7
node 2 size: 32625 MB
node 2 free: 31490 MB
node distances:
node 0 2
0: 10 20
2: 20 10
proc and sys files
------------------
/sys/devices/system/node/online: 0,2
/proc/sys/kernel/numa_balancing: 1
/sys/devices/system/node/has_cpu: 2
/sys/devices/system/node/has_memory: 2
/sys/devices/system/node/has_normal_memory: 2
/sys/devices/system/node/possible: 0-31
v5.7-rc3 + patches
------------------
available: 1 nodes (2)
node 2 cpus: 0 1 2 3 4 5 6 7
node 2 size: 32625 MB
node 2 free: 31487 MB
node distances:
node 2
2: 10
proc and sys files
------------------
/sys/devices/system/node/online: 2
/proc/sys/kernel/numa_balancing: 0
/sys/devices/system/node/has_cpu: 2
/sys/devices/system/node/has_memory: 2
/sys/devices/system/node/has_normal_memory: 2
/sys/devices/system/node/possible: 0-31
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Christopher Lameter <cl@linux.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Srikar Dronamraju (3):
powerpc/numa: Set numa_node for all possible cpus
powerpc/numa: Prefer node id queried from vphn
mm/page_alloc: Keep memoryless cpuless node 0 offline
arch/powerpc/mm/numa.c | 32 ++++++++++++++++++++++----------
mm/page_alloc.c | 4 +++-
2 files changed, 25 insertions(+), 11 deletions(-)
--
2.20.1
^ permalink raw reply
* [PATCH v2 2/3] powerpc/numa: Prefer node id queried from vphn
From: Srikar Dronamraju @ 2020-04-28 9:38 UTC (permalink / raw)
To: Andrew Morton
Cc: Michal Hocko, Srikar Dronamraju, Linus Torvalds, linux-kernel,
linux-mm, Mel Gorman, Kirill A. Shutemov, Christopher Lameter,
linuxppc-dev, Vlastimil Babka
In-Reply-To: <20200428093836.27190-1-srikar@linux.vnet.ibm.com>
Node id queried from the static device tree may not
be correct. For example: it may always show 0 on a shared processor.
Hence prefer the node id queried from vphn and fallback on the device tree
based node id if vphn query fails.
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Christopher Lameter <cl@linux.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog v1:->v2:
- Rebased to v5.7-rc3
arch/powerpc/mm/numa.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index b3615b7fdbdf..281531340230 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -719,20 +719,20 @@ static int __init parse_numa_properties(void)
*/
for_each_present_cpu(i) {
struct device_node *cpu;
- int nid;
-
- cpu = of_get_cpu_node(i, NULL);
- BUG_ON(!cpu);
- nid = of_node_to_nid_single(cpu);
- of_node_put(cpu);
+ int nid = vphn_get_nid(i);
/*
* Don't fall back to default_nid yet -- we will plug
* cpus into nodes once the memory scan has discovered
* the topology.
*/
- if (nid < 0)
- continue;
+ if (nid == NUMA_NO_NODE) {
+ cpu = of_get_cpu_node(i, NULL);
+ if (cpu) {
+ nid = of_node_to_nid_single(cpu);
+ of_node_put(cpu);
+ }
+ }
node_set_online(nid);
}
--
2.20.1
^ permalink raw reply related
* [PATCH v2 1/3] powerpc/numa: Set numa_node for all possible cpus
From: Srikar Dronamraju @ 2020-04-28 9:38 UTC (permalink / raw)
To: Andrew Morton
Cc: Michal Hocko, Srikar Dronamraju, Linus Torvalds, linux-kernel,
linux-mm, Mel Gorman, Kirill A. Shutemov, Christopher Lameter,
linuxppc-dev, Vlastimil Babka
In-Reply-To: <20200428093836.27190-1-srikar@linux.vnet.ibm.com>
A Powerpc system with multiple possible nodes and with CONFIG_NUMA
enabled always used to have a node 0, even if node 0 does not any cpus
or memory attached to it. As per PAPR, node affinity of a cpu is only
available once its present / online. For all cpus that are possible but
not present, cpu_to_node() would point to node 0.
To ensure a cpuless, memoryless dummy node is not online, powerpc need
to make sure all possible but not present cpu_to_node are set to a
proper node.
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Christopher Lameter <cl@linux.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog v1:->v2:
- Rebased to v5.7-rc3
arch/powerpc/mm/numa.c | 16 ++++++++++++++--
1 file changed, 14 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 9fcf2d195830..b3615b7fdbdf 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -931,8 +931,20 @@ void __init mem_topology_setup(void)
reset_numa_cpu_lookup_table();
- for_each_present_cpu(cpu)
- numa_setup_cpu(cpu);
+ for_each_possible_cpu(cpu) {
+ /*
+ * Powerpc with CONFIG_NUMA always used to have a node 0,
+ * even if it was memoryless or cpuless. For all cpus that
+ * are possible but not present, cpu_to_node() would point
+ * to node 0. To remove a cpuless, memoryless dummy node,
+ * powerpc need to make sure all possible but not present
+ * cpu_to_node are set to a proper node.
+ */
+ if (cpu_present(cpu))
+ numa_setup_cpu(cpu);
+ else
+ set_cpu_numa_node(cpu, first_online_node);
+ }
}
void __init initmem_init(void)
--
2.20.1
^ permalink raw reply related
* Re: [PATCH 2/7] signal: factor copy_siginfo_to_external32 from copy_siginfo_to_user32
From: Christoph Hellwig @ 2020-04-28 7:48 UTC (permalink / raw)
To: Christophe Leroy
Cc: Eric W . Biederman, Arnd Bergmann, linuxppc-dev, linux-kernel,
Alexander Viro, linux-fsdevel, Andrew Morton, Linus Torvalds,
Christoph Hellwig, Jeremy Kerr
In-Reply-To: <ddbaba35-9cc5-dfb9-3cae-51b026de5b65@c-s.fr>
On Tue, Apr 28, 2020 at 09:45:46AM +0200, Christophe Leroy wrote:
>> I guess that might be a worthwhile middle ground. Still not a fan of
>> all these ifdefs..
>>
>
> Can't we move the small X32 specific part out of
> __copy_siginfo_to_user32(), in an arch specific helper that voids for other
> architectures ?
>
> Something like:
>
> if (!arch_special_something(&new, from)) {
> new.si_utime = from->si_utime;
> new.si_stime = from->si_stime;
> }
>
> Then the arch_special_something() does what it wants in x86 and returns 1,
> and for architectures not implementating it, a generic version return 0 all
> the time.
The main issue is that we need an explicit paramter to select x32,
as it can't just be discovered from the calling context otherwise.
The rest is just sugarcoating.
^ permalink raw reply
* Re: [PATCH 2/7] signal: factor copy_siginfo_to_external32 from copy_siginfo_to_user32
From: Christophe Leroy @ 2020-04-28 7:45 UTC (permalink / raw)
To: Christoph Hellwig, Andrew Morton
Cc: Eric W . Biederman, Arnd Bergmann, linuxppc-dev, linux-kernel,
Jeremy Kerr, linux-fsdevel, Linus Torvalds, Alexander Viro
In-Reply-To: <20200428070935.GE18754@lst.de>
Le 28/04/2020 à 09:09, Christoph Hellwig a écrit :
> On Mon, Apr 27, 2020 at 03:40:50PM -0700, Andrew Morton wrote:
>>> https://www.spinics.net/lists/kernel/msg3473847.html
>>> https://www.spinics.net/lists/kernel/msg3473840.html
>>> https://www.spinics.net/lists/kernel/msg3473843.html
>>
>> OK, but that doesn't necessitate the above monstrosity? How about
>>
>> static int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
>> const struct kernel_siginfo *from, bool x32_ABI)
>> {
>> struct compat_siginfo new;
>> copy_siginfo_to_external32(&new, from);
>> ...
>> }
>>
>> int copy_siginfo_to_user32(struct compat_siginfo __user *to,
>> const struct kernel_siginfo *from)
>> {
>> #if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION)
>> return __copy_siginfo_to_user32(to, from, in_x32_syscall());
>> #else
>> return __copy_siginfo_to_user32(to, from, 0);
>> #endif
>> }
>>
>> Or something like that - I didn't try very hard. We know how to do
>> this stuff, and surely this thing isn't how!
>
> I guess that might be a worthwhile middle ground. Still not a fan of
> all these ifdefs..
>
Can't we move the small X32 specific part out of
__copy_siginfo_to_user32(), in an arch specific helper that voids for
other architectures ?
Something like:
if (!arch_special_something(&new, from)) {
new.si_utime = from->si_utime;
new.si_stime = from->si_stime;
}
Then the arch_special_something() does what it wants in x86 and returns
1, and for architectures not implementating it, a generic version return
0 all the time.
Christophe
^ permalink raw reply
* Re: [PATCH 2/7] signal: factor copy_siginfo_to_external32 from copy_siginfo_to_user32
From: Christoph Hellwig @ 2020-04-28 7:09 UTC (permalink / raw)
To: Andrew Morton
Cc: Arnd Bergmann, Linus Torvalds, linux-kernel, Alexander Viro,
Jeremy Kerr, linux-fsdevel, linuxppc-dev, Christoph Hellwig,
Eric W . Biederman
In-Reply-To: <20200427154050.e431ad7fb228610cc6b95973@linux-foundation.org>
On Mon, Apr 27, 2020 at 03:40:50PM -0700, Andrew Morton wrote:
> > https://www.spinics.net/lists/kernel/msg3473847.html
> > https://www.spinics.net/lists/kernel/msg3473840.html
> > https://www.spinics.net/lists/kernel/msg3473843.html
>
> OK, but that doesn't necessitate the above monstrosity? How about
>
> static int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
> const struct kernel_siginfo *from, bool x32_ABI)
> {
> struct compat_siginfo new;
> copy_siginfo_to_external32(&new, from);
> ...
> }
>
> int copy_siginfo_to_user32(struct compat_siginfo __user *to,
> const struct kernel_siginfo *from)
> {
> #if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION)
> return __copy_siginfo_to_user32(to, from, in_x32_syscall());
> #else
> return __copy_siginfo_to_user32(to, from, 0);
> #endif
> }
>
> Or something like that - I didn't try very hard. We know how to do
> this stuff, and surely this thing isn't how!
I guess that might be a worthwhile middle ground. Still not a fan of
all these ifdefs..
^ permalink raw reply
* Re: [PATCH 1/5] powerpc/spufs: simplify spufs core dumping
From: Christoph Hellwig @ 2020-04-28 6:57 UTC (permalink / raw)
To: Jeremy Kerr
Cc: Arnd Bergmann, linuxppc-dev, linux-kernel, Eric W . Biederman,
linux-fsdevel, Andrew Morton, Linus Torvalds, Christoph Hellwig,
Al Viro
In-Reply-To: <fc3b45c91e5cd50baa1fec7710f1e64cbe616f77.camel@ozlabs.org>
On Tue, Apr 28, 2020 at 10:51:56AM +0800, Jeremy Kerr wrote:
> Hi Al & Christoph,
>
> > Again, this really needs fixing. Preferably - as a separate commit
> > preceding this series, so that it could be
> > backported. simple_read_from_buffer() is a blocking operation.
>
> I'll put together a patch that fixes this.
>
> Christoph: I'll do it in a way that matches your changes to the _read
> functions, so hopefully those hunks would just drop from your change,
> leaving only the _dump additions. Would that work?
Sure.
^ permalink raw reply
* Re: [PATCH v8 0/7] powerpc/perf: Add json file metric support for the hv_24x7 socket/chip level events
From: kajoljain @ 2020-04-28 6:32 UTC (permalink / raw)
To: acme, linuxppc-dev, mpe, sukadev
Cc: mark.rutland, ravi.bangoria, maddy, tglx, jmario, mpetlan, peterz,
gregkh, linux-kernel, alexander.shishkin, linux-perf-users, ak,
yao.jin, anju, mamatha4, jolsa, namhyung, mingo, kan.liang
In-Reply-To: <20200401203340.31402-1-kjain@linux.ibm.com>
Hi Arnaldo,
Please let me know if there any changes required in this patchset,
as some of its patches are still not part of your perf/core tree.
Thanks,
Kajol Jain
On 4/2/20 2:03 AM, Kajol Jain wrote:
> Patchset adds json file metric support for the hv_24x7 socket/chip level
> events. "hv_24x7" pmu interface events needs system dependent parameter
> like socket/chip/core. For example, hv_24x7 chip level events needs
> specific chip-id to which the data is requested should be added as part
> of pmu events.
>
> So to enable JSON file support to "hv_24x7" interface, patchset reads
> total number of sockets details in sysfs under
> "/sys/devices/hv_24x7/interface/".
>
> Second patch of the patchset adds expr_scanner_ctx object to hold user
> data for the expr scanner, which can be used to hold runtime parameter.
>
> Patch 4 & 6 of the patchset handles perf tool plumbing needed to replace
> the "?" character in the metric expression to proper value and hv_24x7
> json metric file for different Socket/chip resources.
>
> Patch set also enable Hz/hz prinitg for --metric-only option to print
> metric data for bus frequency.
>
> Applied and tested all these patches cleanly on top of jiri's flex changes
> with the changes done by Kan Liang for "Support metric group constraint"
> patchset and made required changes.
>
> Also apply this patch on top of the fix patch send earlier
> for printing metric name incase overlapping events.
> https://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git/commit/?h=perf/core&id=37cd7f65bf71a48f25eeb6d9be5dacb20d008ea6
>
> Changelog:
> v7 -> v8
> - Add test case for testing parsing of "?" in metric expression
> - Reaname variables name to runtime
>
> v6 -> v7
> - Spit patchset into two patch series one for kernel changes and other
> for tool side changes.
> - Made changes Suggested by Jiri, including rather then reading runtime
> parameter from metric name, actually add it in structure egroup and
> metric_expr.
> - As we don't need to read runtime parameter from metric name,
> now I am not appending it and rather just printing it in
> generic_metric function.
>
> Kernel Side changes patch series: https://lkml.org/lkml/2020/3/27/58
>
> v5 -> v6
> - resolve compilation issue due to rearranging patch series.
> - Rather then adding new function to take careof case for runtime param
> in metricgroup__add_metric, using metricgroup__add_metric_param itself
> for that work.
> - Address some optimization suggested like using directly file path
> rather then adding new macro in header.c
> - Change commit message on patch where we are adding "?" support
> by adding simple example.
>
> v4 -> v5
> - Using sysfs__read_int instead of sysfs__read_ull while reading
> parameter value in powerpc/util/header.c file.
>
> - Using asprintf rather then malloc and sprintf
> Suggested by Arnaldo Carvalho de Melo
>
> - Break patch 6 from previous version to two patch,
> - One to add refactor current "metricgroup__add_metric" function
> and another where actually "?" handling infra added.
>
> - Add expr__runtimeparam as part of 'expr_scanner_ctx' struct
> rather then making it global variable. Thanks Jiri for
> adding this structure to hold user data for the expr scanner.
>
> - Add runtime param as agrugement to function 'expr__find_other'
> and 'expr__parse' and made changes on references accordingly.
>
> v3 -> v4
> - Apply these patch on top of Kan liang changes.
> As suggested by Jiri.
>
> v2 -> v3
> - Remove setting event_count to 0 part in function 'h_24x7_event_read'
> with comment rather then adding 0 to event_count value.
> Suggested by: Sukadev Bhattiprolu
>
> - Apply tool side changes require to replace "?" on Jiri's flex patch
> series and made all require changes to make it compatible with added
> flex change.
>
> v1 -> v2
> - Rename hv-24x7 metric json file as nest_metrics.json
>
> Jiri Olsa (2):
> perf expr: Add expr_ prefix for parse_ctx and parse_id
> perf expr: Add expr_scanner_ctx object
>
> Kajol Jain (5):
> perf/tools: Refactoring metricgroup__add_metric function
> perf/tools: Enhance JSON/metric infrastructure to handle "?"
> perf/tests/expr: Added test for runtime param in metric expression
> tools/perf: Enable Hz/hz prinitg for --metric-only option
> perf/tools/pmu-events/powerpc: Add hv_24x7 socket/chip level metric
> events
>
> tools/perf/arch/powerpc/util/header.c | 8 ++
> .../arch/powerpc/power9/nest_metrics.json | 19 +++++
> tools/perf/tests/expr.c | 20 +++--
> tools/perf/util/expr.c | 25 +++---
> tools/perf/util/expr.h | 19 +++--
> tools/perf/util/expr.l | 37 ++++++---
> tools/perf/util/expr.y | 6 +-
> tools/perf/util/metricgroup.c | 78 +++++++++++++------
> tools/perf/util/metricgroup.h | 2 +
> tools/perf/util/stat-display.c | 2 -
> tools/perf/util/stat-shadow.c | 19 +++--
> 11 files changed, 164 insertions(+), 71 deletions(-)
> create mode 100644 tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json
>
^ permalink raw reply
* Re: [PATCH v6 03/28] powerpc/xmon: Move breakpoints to text section
From: Christophe Leroy @ 2020-04-28 5:36 UTC (permalink / raw)
To: Jordan Niethe
Cc: Alistair Popple, Nicholas Piggin, Balamuruhan S, linuxppc-dev,
Daniel Axtens
In-Reply-To: <CACzsE9oF4eLH_5JUrSC1XfyWG_QzJ45HK=Rj+XwfxhuVxe5k0g@mail.gmail.com>
Le 28/04/2020 à 07:30, Jordan Niethe a écrit :
> On Tue, Apr 28, 2020 at 3:20 PM Christophe Leroy
> <christophe.leroy@c-s.fr> wrote:
>>
>>
>>
>> Le 28/04/2020 à 03:57, Jordan Niethe a écrit :
>>> The instructions for xmon's breakpoint are stored bpt_table[] which is in
>>> the data section. This is problematic as the data section may be marked
>>> as no execute. Move bpt_table[] to the text section.
>>>
>>> Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
>>> ---
>>> v6: - New to series. Was part of the previous patch.
>>> - Make BPT_SIZE available in assembly
>>> ---
>>> arch/powerpc/kernel/asm-offsets.c | 8 ++++++++
>>> arch/powerpc/xmon/Makefile | 2 +-
>>> arch/powerpc/xmon/xmon.c | 6 +-----
>>> arch/powerpc/xmon/xmon_bpts.S | 9 +++++++++
>>> arch/powerpc/xmon/xmon_bpts.h | 14 ++++++++++++++
>>> 5 files changed, 33 insertions(+), 6 deletions(-)
>>> create mode 100644 arch/powerpc/xmon/xmon_bpts.S
>>> create mode 100644 arch/powerpc/xmon/xmon_bpts.h
>>>
>>> diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
>>> index c25e562f1cd9..2401f415f423 100644
>>> --- a/arch/powerpc/kernel/asm-offsets.c
>>> +++ b/arch/powerpc/kernel/asm-offsets.c
>>> @@ -70,6 +70,10 @@
>>> #include <asm/fixmap.h>
>>> #endif
>>>
>>> +#ifdef CONFIG_XMON
>>> +#include "../xmon/xmon_bpts.h"
>>> +#endif
>>> +
>>> #define STACK_PT_REGS_OFFSET(sym, val) \
>>> DEFINE(sym, STACK_FRAME_OVERHEAD + offsetof(struct pt_regs, val))
>>>
>>> @@ -783,5 +787,9 @@ int main(void)
>>> DEFINE(VIRT_IMMR_BASE, (u64)__fix_to_virt(FIX_IMMR_BASE));
>>> #endif
>>>
>>> +#ifdef CONFIG_XMON
>>> + DEFINE(BPT_SIZE, BPT_SIZE);
>>> +#endif
>>> +
>>> return 0;
>>> }
>>> diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
>>> index c3842dbeb1b7..515a13ea6f28 100644
>>> --- a/arch/powerpc/xmon/Makefile
>>> +++ b/arch/powerpc/xmon/Makefile
>>> @@ -21,7 +21,7 @@ endif
>>>
>>> ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
>>>
>>> -obj-y += xmon.o nonstdio.o spr_access.o
>>> +obj-y += xmon.o nonstdio.o spr_access.o xmon_bpts.o
>>>
>>> ifdef CONFIG_XMON_DISASSEMBLY
>>> obj-y += ppc-dis.o ppc-opc.o
>>> diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
>>> index a064392df1b8..f7ce3ea8694c 100644
>>> --- a/arch/powerpc/xmon/xmon.c
>>> +++ b/arch/powerpc/xmon/xmon.c
>>> @@ -62,6 +62,7 @@
>>>
>>> #include "nonstdio.h"
>>> #include "dis-asm.h"
>>> +#include "xmon_bpts.h"
>>>
>>> #ifdef CONFIG_SMP
>>> static cpumask_t cpus_in_xmon = CPU_MASK_NONE;
>>> @@ -108,7 +109,6 @@ struct bpt {
>>> #define BP_TRAP 2
>>> #define BP_DABR 4
>>>
>>> -#define NBPTS 256
>>> static struct bpt bpts[NBPTS];
>>> static struct bpt dabr;
>>> static struct bpt *iabr;
>>> @@ -116,10 +116,6 @@ static unsigned bpinstr = 0x7fe00008; /* trap */
>>>
>>> #define BP_NUM(bp) ((bp) - bpts + 1)
>>>
>>> -#define BPT_SIZE (sizeof(unsigned int) * 2)
>>> -#define BPT_WORDS (BPT_SIZE / sizeof(unsigned int))
>>> -static unsigned int bpt_table[NBPTS * BPT_WORDS];
>>> -
>>> /* Prototypes */
>>> static int cmds(struct pt_regs *);
>>> static int mread(unsigned long, void *, int);
>>> diff --git a/arch/powerpc/xmon/xmon_bpts.S b/arch/powerpc/xmon/xmon_bpts.S
>>> new file mode 100644
>>> index 000000000000..f3ad0ab50854
>>> --- /dev/null
>>> +++ b/arch/powerpc/xmon/xmon_bpts.S
>>> @@ -0,0 +1,9 @@
>>> +/* SPDX-License-Identifier: GPL-2.0 */
>>> +#include <asm/ppc_asm.h>
>>> +#include <asm/asm-compat.h>
>>> +#include <asm/asm-offsets.h>
>>> +#include "xmon_bpts.h"
>>> +
>>> +.global bpt_table
>>> +bpt_table:
>>> + .space NBPTS * BPT_SIZE
>>
>> No alignment required ? Standard alignment (probably 4 bytes ?) is
>> acceptable ?
> No, I'll add a .balign 4 to be sure.
I think it is aligned to 4 by default. My question was to know whether 4
is enough.
I see BPT_SIZE is 8, should the alignment be at least 8 ?
>>
>>
>>> diff --git a/arch/powerpc/xmon/xmon_bpts.h b/arch/powerpc/xmon/xmon_bpts.h
>>> new file mode 100644
>>> index 000000000000..b7e94375db86
>>> --- /dev/null
>>> +++ b/arch/powerpc/xmon/xmon_bpts.h
>>> @@ -0,0 +1,14 @@
>>> +/* SPDX-License-Identifier: GPL-2.0 */
>>> +#ifndef XMON_BPTS_H
>>> +#define XMON_BPTS_H
>>> +
>>> +#define NBPTS 256
>>> +#ifndef __ASSEMBLY__
>>> +#define BPT_SIZE (sizeof(unsigned int) * 2)
>>> +#define BPT_WORDS (BPT_SIZE / sizeof(unsigned int))
>>> +
>>> +extern unsigned int bpt_table[NBPTS * BPT_WORDS];
>>> +
>>> +#endif /* __ASSEMBLY__ */
>>> +
>>> +#endif /* XMON_BPTS_H */
>>>
>>
>> Christophe
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox