* [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 0/8] powerpc: switch VDSO to C implementation
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
This is the seventh version of a series to switch powerpc VDSO to
generic C implementation.
Main changes since v7 are:
- Added gettime64 on PPC32
This series applies on today's powerpc/merge branch.
See the last patches for details on changes and performance.
Christophe Leroy (8):
powerpc/vdso64: Switch from __get_datapage() to get_datapage inline
macro
powerpc/vdso: Remove __kernel_datapage_offset and simplify
__get_datapage()
powerpc/vdso: Remove unused \tmp param in __get_datapage()
powerpc/processor: Move cpu_relax() into asm/vdso/processor.h
powerpc/vdso: Prepare for switching VDSO to generic C implementation.
powerpc/vdso: Switch VDSO to generic C implementation.
lib/vdso: force inlining of __cvdso_clock_gettime_common()
powerpc/vdso: Provide __kernel_clock_gettime64() on vdso32
arch/powerpc/Kconfig | 2 +
arch/powerpc/include/asm/clocksource.h | 7 +
arch/powerpc/include/asm/processor.h | 10 +-
arch/powerpc/include/asm/vdso/clocksource.h | 7 +
arch/powerpc/include/asm/vdso/gettimeofday.h | 175 +++++++++++
arch/powerpc/include/asm/vdso/processor.h | 23 ++
arch/powerpc/include/asm/vdso/vsyscall.h | 25 ++
arch/powerpc/include/asm/vdso_datapage.h | 50 ++--
arch/powerpc/kernel/asm-offsets.c | 49 +--
arch/powerpc/kernel/time.c | 91 +-----
arch/powerpc/kernel/vdso.c | 58 +---
arch/powerpc/kernel/vdso32/Makefile | 32 +-
arch/powerpc/kernel/vdso32/cacheflush.S | 2 +-
arch/powerpc/kernel/vdso32/config-fake32.h | 34 +++
arch/powerpc/kernel/vdso32/datapage.S | 7 +-
arch/powerpc/kernel/vdso32/gettimeofday.S | 300 +------------------
arch/powerpc/kernel/vdso32/vdso32.lds.S | 8 +-
arch/powerpc/kernel/vdso32/vgettimeofday.c | 35 +++
arch/powerpc/kernel/vdso64/Makefile | 23 +-
arch/powerpc/kernel/vdso64/cacheflush.S | 9 +-
arch/powerpc/kernel/vdso64/datapage.S | 31 +-
arch/powerpc/kernel/vdso64/gettimeofday.S | 243 +--------------
arch/powerpc/kernel/vdso64/vdso64.lds.S | 7 +-
arch/powerpc/kernel/vdso64/vgettimeofday.c | 29 ++
lib/vdso/gettimeofday.c | 2 +-
25 files changed, 460 insertions(+), 799 deletions(-)
create mode 100644 arch/powerpc/include/asm/clocksource.h
create mode 100644 arch/powerpc/include/asm/vdso/clocksource.h
create mode 100644 arch/powerpc/include/asm/vdso/gettimeofday.h
create mode 100644 arch/powerpc/include/asm/vdso/processor.h
create mode 100644 arch/powerpc/include/asm/vdso/vsyscall.h
create mode 100644 arch/powerpc/kernel/vdso32/config-fake32.h
create mode 100644 arch/powerpc/kernel/vdso32/vgettimeofday.c
create mode 100644 arch/powerpc/kernel/vdso64/vgettimeofday.c
--
2.25.0
^ permalink raw reply
* [PATCH v8 5/8] powerpc/vdso: Prepare for switching VDSO to generic C implementation.
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>
Prepare for switching VDSO to generic C implementation in following
patch. Here, we:
- Modify __get_datapage() to take an offset
- Prepare the helpers to call the C VDSO functions
- Prepare the required callbacks for the C VDSO functions
- Prepare the clocksource.h files to define VDSO_ARCH_CLOCKMODES
- Add the C trampolines to the generic C VDSO functions
powerpc is a bit special for VDSO as well as system calls in the
way that it requires setting CR SO bit which cannot be done in C.
Therefore, entry/exit needs to be performed in ASM.
Implementing __arch_get_vdso_data() would clobber the link register,
requiring the caller to save it. As the ASM calling function already
has to set a stack frame and saves the link register before calling
the C vdso function, retriving the vdso data pointer there is lighter.
Implement __arch_vdso_capable() and:
- When the timebase is used, make it always return true.
- When the RTC clock is used, make it always return false.
Provide vdso_shift_ns(), as the generic x >> s gives the following
bad result:
18: 35 25 ff e0 addic. r9,r5,-32
1c: 41 80 00 10 blt 2c <shift+0x14>
20: 7c 64 4c 30 srw r4,r3,r9
24: 38 60 00 00 li r3,0
...
2c: 54 69 08 3c rlwinm r9,r3,1,0,30
30: 21 45 00 1f subfic r10,r5,31
34: 7c 84 2c 30 srw r4,r4,r5
38: 7d 29 50 30 slw r9,r9,r10
3c: 7c 63 2c 30 srw r3,r3,r5
40: 7d 24 23 78 or r4,r9,r4
In our case the shift is always <= 32. In addition, the upper 32 bits
of the result are likely nul. Lets GCC know it, it also optimises the
following calculations.
With the patch, we get:
0: 21 25 00 20 subfic r9,r5,32
4: 7c 69 48 30 slw r9,r3,r9
8: 7c 84 2c 30 srw r4,r4,r5
c: 7d 24 23 78 or r4,r9,r4
10: 7c 63 2c 30 srw r3,r3,r5
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v8:
- New, splitted out of last patch of the series
---
arch/powerpc/include/asm/clocksource.h | 7 +
arch/powerpc/include/asm/vdso/clocksource.h | 7 +
arch/powerpc/include/asm/vdso/gettimeofday.h | 175 +++++++++++++++++++
arch/powerpc/include/asm/vdso_datapage.h | 6 +-
arch/powerpc/kernel/vdso32/vgettimeofday.c | 29 +++
arch/powerpc/kernel/vdso64/vgettimeofday.c | 29 +++
6 files changed, 250 insertions(+), 3 deletions(-)
create mode 100644 arch/powerpc/include/asm/clocksource.h
create mode 100644 arch/powerpc/include/asm/vdso/clocksource.h
create mode 100644 arch/powerpc/include/asm/vdso/gettimeofday.h
create mode 100644 arch/powerpc/kernel/vdso32/vgettimeofday.c
create mode 100644 arch/powerpc/kernel/vdso64/vgettimeofday.c
diff --git a/arch/powerpc/include/asm/clocksource.h b/arch/powerpc/include/asm/clocksource.h
new file mode 100644
index 000000000000..482185566b0c
--- /dev/null
+++ b/arch/powerpc/include/asm/clocksource.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_CLOCKSOURCE_H
+#define _ASM_CLOCKSOURCE_H
+
+#include <asm/vdso/clocksource.h>
+
+#endif
diff --git a/arch/powerpc/include/asm/vdso/clocksource.h b/arch/powerpc/include/asm/vdso/clocksource.h
new file mode 100644
index 000000000000..ec5d672d2569
--- /dev/null
+++ b/arch/powerpc/include/asm/vdso/clocksource.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSOCLOCKSOURCE_H
+#define __ASM_VDSOCLOCKSOURCE_H
+
+#define VDSO_ARCH_CLOCKMODES VDSO_CLOCKMODE_ARCHTIMER
+
+#endif
diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h
new file mode 100644
index 000000000000..4452897f9bd8
--- /dev/null
+++ b/arch/powerpc/include/asm/vdso/gettimeofday.h
@@ -0,0 +1,175 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_GETTIMEOFDAY_H
+#define __ASM_VDSO_GETTIMEOFDAY_H
+
+#include <asm/ptrace.h>
+
+#ifdef __ASSEMBLY__
+
+.macro cvdso_call funct
+ .cfi_startproc
+ PPC_STLU r1, -STACK_FRAME_OVERHEAD(r1)
+ mflr r0
+ .cfi_register lr, r0
+ PPC_STL r0, STACK_FRAME_OVERHEAD + PPC_LR_STKOFF(r1)
+ get_datapage r5, VDSO_DATA_OFFSET
+ bl \funct
+ PPC_LL r0, STACK_FRAME_OVERHEAD + PPC_LR_STKOFF(r1)
+ cmpwi r3, 0
+ mtlr r0
+ .cfi_restore lr
+ addi r1, r1, STACK_FRAME_OVERHEAD
+ crclr so
+ beqlr+
+ crset so
+ neg r3, r3
+ blr
+ .cfi_endproc
+.endm
+
+.macro cvdso_call_time funct
+ .cfi_startproc
+ PPC_STLU r1, -STACK_FRAME_OVERHEAD(r1)
+ mflr r0
+ .cfi_register lr, r0
+ PPC_STL r0, STACK_FRAME_OVERHEAD + PPC_LR_STKOFF(r1)
+ get_datapage r4, VDSO_DATA_OFFSET
+ bl \funct
+ PPC_LL r0, STACK_FRAME_OVERHEAD + PPC_LR_STKOFF(r1)
+ crclr so
+ mtlr r0
+ .cfi_restore lr
+ addi r1, r1, STACK_FRAME_OVERHEAD
+ blr
+ .cfi_endproc
+.endm
+
+#else
+
+#include <asm/time.h>
+#include <asm/unistd.h>
+#include <uapi/linux/time.h>
+
+#define VDSO_HAS_CLOCK_GETRES 1
+
+#define VDSO_HAS_TIME 1
+
+static __always_inline int do_syscall_2(const unsigned long _r0, const unsigned long _r3,
+ const unsigned long _r4)
+{
+ register long r0 asm("r0") = _r0;
+ register unsigned long r3 asm("r3") = _r3;
+ register unsigned long r4 asm("r4") = _r4;
+ register int ret asm ("r3");
+
+ asm volatile(
+ " sc\n"
+ " bns+ 1f\n"
+ " neg %0, %0\n"
+ "1:\n"
+ : "=r" (ret), "+r" (r4), "+r" (r0)
+ : "r" (r3)
+ : "memory", "r5", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "cr0", "ctr");
+
+ return ret;
+}
+
+static __always_inline
+int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz)
+{
+ return do_syscall_2(__NR_gettimeofday, (unsigned long)_tv, (unsigned long)_tz);
+}
+
+static __always_inline
+int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts);
+}
+
+static __always_inline
+int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts);
+}
+
+#ifdef CONFIG_VDSO32
+
+#define BUILD_VDSO32 1
+
+static __always_inline
+int clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
+{
+ return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts);
+}
+
+static __always_inline
+int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
+{
+ return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts);
+}
+#endif
+
+static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
+{
+ return get_tb();
+}
+
+const struct vdso_data *__arch_get_vdso_data(void);
+
+static inline bool vdso_clocksource_ok(const struct vdso_data *vd)
+{
+ return !__USE_RTC();
+}
+#define vdso_clocksource_ok vdso_clocksource_ok
+
+/*
+ * powerpc specific delta calculation.
+ *
+ * This variant removes the masking of the subtraction because the
+ * clocksource mask of all VDSO capable clocksources on powerpc is U64_MAX
+ * which would result in a pointless operation. The compiler cannot
+ * optimize it away as the mask comes from the vdso data and is not compile
+ * time constant.
+ */
+static __always_inline u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
+{
+ return (cycles - last) * mult;
+}
+#define vdso_calc_delta vdso_calc_delta
+
+#ifndef __powerpc64__
+static __always_inline u64 vdso_shift_ns(u64 ns, unsigned long shift)
+{
+ u32 hi = ns >> 32;
+ u32 lo = ns;
+
+ lo >>= shift;
+ lo |= hi << (32 - shift);
+ hi >>= shift;
+
+ if (likely(hi == 0))
+ return lo;
+
+ return ((u64)hi << 32) | lo;
+}
+#define vdso_shift_ns vdso_shift_ns
+#endif
+
+#ifdef __powerpc64__
+int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts,
+ const struct vdso_data *vd);
+int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res,
+ const struct vdso_data *vd);
+#else
+int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
+ const struct vdso_data *vd);
+int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res,
+ const struct vdso_data *vd);
+#endif
+int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
+ const struct vdso_data *vd);
+__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time,
+ const struct vdso_data *vd);
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index f3d7e4e2a45b..78b8f67e9873 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -116,14 +116,14 @@ extern struct vdso_data *vdso_data;
#else /* __ASSEMBLY__ */
-.macro get_datapage ptr
+.macro get_datapage ptr, offset=0
bcl 20, 31, .+4
999:
mflr \ptr
#if CONFIG_PPC_PAGE_SHIFT > 14
- addis \ptr, \ptr, (_vdso_datapage - 999b)@ha
+ addis \ptr, \ptr, (_vdso_datapage + \offset - 999b)@ha
#endif
- addi \ptr, \ptr, (_vdso_datapage - 999b)@l
+ addi \ptr, \ptr, (_vdso_datapage + \offset - 999b)@l
.endm
#endif /* __ASSEMBLY__ */
diff --git a/arch/powerpc/kernel/vdso32/vgettimeofday.c b/arch/powerpc/kernel/vdso32/vgettimeofday.c
new file mode 100644
index 000000000000..0b9ab4c22ef2
--- /dev/null
+++ b/arch/powerpc/kernel/vdso32/vgettimeofday.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Powerpc userspace implementations of gettimeofday() and similar.
+ */
+#include <linux/time.h>
+#include <linux/types.h>
+
+int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_gettime32_data(vd, clock, ts);
+}
+
+int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
+ const struct vdso_data *vd)
+{
+ return __cvdso_gettimeofday_data(vd, tv, tz);
+}
+
+int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_getres_time32_data(vd, clock_id, res);
+}
+
+__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd)
+{
+ return __cvdso_time_data(vd, time);
+}
diff --git a/arch/powerpc/kernel/vdso64/vgettimeofday.c b/arch/powerpc/kernel/vdso64/vgettimeofday.c
new file mode 100644
index 000000000000..5b5500058344
--- /dev/null
+++ b/arch/powerpc/kernel/vdso64/vgettimeofday.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Powerpc userspace implementations of gettimeofday() and similar.
+ */
+#include <linux/time.h>
+#include <linux/types.h>
+
+int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_gettime_data(vd, clock, ts);
+}
+
+int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
+ const struct vdso_data *vd)
+{
+ return __cvdso_gettimeofday_data(vd, tv, tz);
+}
+
+int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_getres_data(vd, clock_id, res);
+}
+
+__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd)
+{
+ return __cvdso_time_data(vd, time);
+}
--
2.25.0
^ permalink raw reply related
* [PATCH v8 8/8] powerpc/vdso: Provide __kernel_clock_gettime64() on vdso32
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>
Provides __kernel_clock_gettime64() on vdso32. This is the
64 bits version of __kernel_clock_gettime() which is
y2038 compliant.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/kernel/vdso32/gettimeofday.S | 9 +++++++++
arch/powerpc/kernel/vdso32/vdso32.lds.S | 1 +
arch/powerpc/kernel/vdso32/vgettimeofday.c | 6 ++++++
3 files changed, 16 insertions(+)
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index fd7b01c51281..a6e29f880e0e 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -35,6 +35,15 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
cvdso_call __c_kernel_clock_gettime
V_FUNCTION_END(__kernel_clock_gettime)
+/*
+ * Exact prototype of clock_gettime64()
+ *
+ * int __kernel_clock_gettime64(clockid_t clock_id, struct __timespec64 *ts);
+ *
+ */
+V_FUNCTION_BEGIN(__kernel_clock_gettime64)
+ cvdso_call __c_kernel_clock_gettime64
+V_FUNCTION_END(__kernel_clock_gettime64)
/*
* Exact prototype of clock_getres()
diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
index 6cf729612268..05b462143238 100644
--- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
@@ -144,6 +144,7 @@ VERSION
#ifndef CONFIG_PPC_BOOK3S_601
__kernel_gettimeofday;
__kernel_clock_gettime;
+ __kernel_clock_gettime64;
__kernel_clock_getres;
__kernel_time;
__kernel_get_tbfreq;
diff --git a/arch/powerpc/kernel/vdso32/vgettimeofday.c b/arch/powerpc/kernel/vdso32/vgettimeofday.c
index 0b9ab4c22ef2..f7f71fecf4ed 100644
--- a/arch/powerpc/kernel/vdso32/vgettimeofday.c
+++ b/arch/powerpc/kernel/vdso32/vgettimeofday.c
@@ -11,6 +11,12 @@ int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
return __cvdso_clock_gettime32_data(vd, clock, ts);
}
+int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_gettime_data(vd, clock, ts);
+}
+
int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
const struct vdso_data *vd)
{
--
2.25.0
^ permalink raw reply related
* [PATCH v8 6/8] powerpc/vdso: Switch VDSO to generic C implementation.
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>
For VDSO32 on PPC64, we create a fake 32 bits config, on the same
principle as MIPS architecture, in order to get the correct parts of
the different asm header files.
With the C VDSO, the performance is slightly lower, but it is worth
it as it will ease maintenance and evolution, and also brings clocks
that are not supported with the ASM VDSO.
On an 8xx at 132 MHz, vdsotest with the ASM VDSO:
gettimeofday: vdso: 828 nsec/call
clock-getres-realtime-coarse: vdso: 391 nsec/call
clock-gettime-realtime-coarse: vdso: 614 nsec/call
clock-getres-realtime: vdso: 460 nsec/call
clock-gettime-realtime: vdso: 876 nsec/call
clock-getres-monotonic-coarse: vdso: 399 nsec/call
clock-gettime-monotonic-coarse: vdso: 691 nsec/call
clock-getres-monotonic: vdso: 460 nsec/call
clock-gettime-monotonic: vdso: 1026 nsec/call
On an 8xx at 132 MHz, vdsotest with the C VDSO:
gettimeofday: vdso: 955 nsec/call
clock-getres-realtime-coarse: vdso: 545 nsec/call
clock-gettime-realtime-coarse: vdso: 592 nsec/call
clock-getres-realtime: vdso: 545 nsec/call
clock-gettime-realtime: vdso: 941 nsec/call
clock-getres-monotonic-coarse: vdso: 545 nsec/call
clock-gettime-monotonic-coarse: vdso: 591 nsec/call
clock-getres-monotonic: vdso: 545 nsec/call
clock-gettime-monotonic: vdso: 940 nsec/call
It is even better for gettime with monotonic clocks.
Unsupported clocks with ASM VDSO:
clock-gettime-boottime: vdso: 3851 nsec/call
clock-gettime-tai: vdso: 3852 nsec/call
clock-gettime-monotonic-raw: vdso: 3396 nsec/call
Same clocks with C VDSO:
clock-gettime-tai: vdso: 941 nsec/call
clock-gettime-monotonic-raw: vdso: 1001 nsec/call
clock-gettime-monotonic-coarse: vdso: 591 nsec/call
On an 8321E at 333 MHz, vdsotest with the ASM VDSO:
gettimeofday: vdso: 220 nsec/call
clock-getres-realtime-coarse: vdso: 102 nsec/call
clock-gettime-realtime-coarse: vdso: 178 nsec/call
clock-getres-realtime: vdso: 129 nsec/call
clock-gettime-realtime: vdso: 235 nsec/call
clock-getres-monotonic-coarse: vdso: 105 nsec/call
clock-gettime-monotonic-coarse: vdso: 208 nsec/call
clock-getres-monotonic: vdso: 129 nsec/call
clock-gettime-monotonic: vdso: 274 nsec/call
On an 8321E at 333 MHz, vdsotest with the C VDSO:
gettimeofday: vdso: 272 nsec/call
clock-getres-realtime-coarse: vdso: 160 nsec/call
clock-gettime-realtime-coarse: vdso: 184 nsec/call
clock-getres-realtime: vdso: 166 nsec/call
clock-gettime-realtime: vdso: 281 nsec/call
clock-getres-monotonic-coarse: vdso: 160 nsec/call
clock-gettime-monotonic-coarse: vdso: 184 nsec/call
clock-getres-monotonic: vdso: 169 nsec/call
clock-gettime-monotonic: vdso: 275 nsec/call
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v7:
- Split out preparatory changes in a new preceding patch
- Added -fasynchronous-unwind-tables to CC flags.
v6:
- Added missing prototypes in asm/vdso/gettimeofday.h for __c_kernel_ functions.
- Using STACK_FRAME_OVERHEAD instead of INT_FRAME_SIZE
- Rebased on powerpc/merge as of 7 Apr 2020
- Fixed build failure with gcc 9
- Added a patch to create asm/vdso/processor.h and more cpu_relax() in it
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/Kconfig | 2 +
arch/powerpc/include/asm/vdso/vsyscall.h | 25 ++
arch/powerpc/include/asm/vdso_datapage.h | 40 +--
arch/powerpc/kernel/asm-offsets.c | 49 +---
arch/powerpc/kernel/time.c | 91 +------
arch/powerpc/kernel/vdso.c | 5 +-
arch/powerpc/kernel/vdso32/Makefile | 32 ++-
arch/powerpc/kernel/vdso32/config-fake32.h | 34 +++
arch/powerpc/kernel/vdso32/gettimeofday.S | 291 +--------------------
arch/powerpc/kernel/vdso64/Makefile | 23 +-
arch/powerpc/kernel/vdso64/gettimeofday.S | 243 +----------------
11 files changed, 144 insertions(+), 691 deletions(-)
create mode 100644 arch/powerpc/include/asm/vdso/vsyscall.h
create mode 100644 arch/powerpc/kernel/vdso32/config-fake32.h
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 924c541a9260..4e51454a3e7b 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -166,6 +166,7 @@ config PPC
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
select GENERIC_TIME_VSYSCALL
+ select GENERIC_GETTIMEOFDAY
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_HUGE_VMAP if PPC_BOOK3S_64 && PPC_RADIX_MMU
select HAVE_ARCH_JUMP_LABEL
@@ -197,6 +198,7 @@ config PPC
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
select HAVE_GCC_PLUGINS if GCC_VERSION >= 50200 # plugin support on gcc <= 5.1 is buggy on PPC
+ select HAVE_GENERIC_VDSO
select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
select HAVE_IDE
select HAVE_IOREMAP_PROT
diff --git a/arch/powerpc/include/asm/vdso/vsyscall.h b/arch/powerpc/include/asm/vdso/vsyscall.h
new file mode 100644
index 000000000000..c56a030c0623
--- /dev/null
+++ b/arch/powerpc/include/asm/vdso/vsyscall.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_VSYSCALL_H
+#define __ASM_VDSO_VSYSCALL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/timekeeper_internal.h>
+#include <asm/vdso_datapage.h>
+
+/*
+ * Update the vDSO data page to keep in sync with kernel timekeeping.
+ */
+static __always_inline
+struct vdso_data *__arch_get_k_vdso_data(void)
+{
+ return vdso_data->data;
+}
+#define __arch_get_k_vdso_data __arch_get_k_vdso_data
+
+/* The asm-generic header needs to be included after the definitions above */
+#include <asm-generic/vdso/vsyscall.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_VSYSCALL_H */
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index 78b8f67e9873..de7221be8de4 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -36,6 +36,7 @@
#include <linux/unistd.h>
#include <linux/time.h>
+#include <vdso/datapage.h>
#define SYSCALL_MAP_SIZE ((NR_syscalls + 31) / 32)
@@ -45,7 +46,7 @@
#ifdef CONFIG_PPC64
-struct vdso_data {
+struct vdso_arch_data {
__u8 eye_catcher[16]; /* Eyecatcher: SYSTEMCFG:PPC64 0x00 */
struct { /* Systemcfg version numbers */
__u32 major; /* Major number 0x10 */
@@ -59,13 +60,13 @@ struct vdso_data {
__u32 processor; /* Processor type 0x1C */
__u64 processorCount; /* # of physical processors 0x20 */
__u64 physicalMemorySize; /* Size of real memory(B) 0x28 */
- __u64 tb_orig_stamp; /* Timebase at boot 0x30 */
+ __u64 tb_orig_stamp; /* (NU) Timebase at boot 0x30 */
__u64 tb_ticks_per_sec; /* Timebase tics / sec 0x38 */
- __u64 tb_to_xs; /* Inverse of TB to 2^20 0x40 */
- __u64 stamp_xsec; /* 0x48 */
- __u64 tb_update_count; /* Timebase atomicity ctr 0x50 */
- __u32 tz_minuteswest; /* Minutes west of Greenwich 0x58 */
- __u32 tz_dsttime; /* Type of dst correction 0x5C */
+ __u64 tb_to_xs; /* (NU) Inverse of TB to 2^20 0x40 */
+ __u64 stamp_xsec; /* (NU) 0x48 */
+ __u64 tb_update_count; /* (NU) Timebase atomicity ctr 0x50 */
+ __u32 tz_minuteswest; /* (NU) Min. west of Greenwich 0x58 */
+ __u32 tz_dsttime; /* (NU) Type of dst correction 0x5C */
__u32 dcache_size; /* L1 d-cache size 0x60 */
__u32 dcache_line_size; /* L1 d-cache line size 0x64 */
__u32 icache_size; /* L1 i-cache size 0x68 */
@@ -78,14 +79,10 @@ struct vdso_data {
__u32 icache_block_size; /* L1 i-cache block size */
__u32 dcache_log_block_size; /* L1 d-cache log block size */
__u32 icache_log_block_size; /* L1 i-cache log block size */
- __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */
- __s32 wtom_clock_nsec; /* Wall to monotonic clock nsec */
- __s64 wtom_clock_sec; /* Wall to monotonic clock sec */
- __s64 stamp_xtime_sec; /* xtime secs as at tb_orig_stamp */
- __s64 stamp_xtime_nsec; /* xtime nsecs as at tb_orig_stamp */
- __u32 hrtimer_res; /* hrtimer resolution */
__u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */
__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
+
+ struct vdso_data data[CS_BASES];
};
#else /* CONFIG_PPC64 */
@@ -93,26 +90,15 @@ struct vdso_data {
/*
* And here is the simpler 32 bits version
*/
-struct vdso_data {
- __u64 tb_orig_stamp; /* Timebase at boot 0x30 */
+struct vdso_arch_data {
__u64 tb_ticks_per_sec; /* Timebase tics / sec 0x38 */
- __u64 tb_to_xs; /* Inverse of TB to 2^20 0x40 */
- __u64 stamp_xsec; /* 0x48 */
- __u32 tb_update_count; /* Timebase atomicity ctr 0x50 */
- __u32 tz_minuteswest; /* Minutes west of Greenwich 0x58 */
- __u32 tz_dsttime; /* Type of dst correction 0x5C */
- __s32 wtom_clock_sec; /* Wall to monotonic clock */
- __s32 wtom_clock_nsec;
- __s32 stamp_xtime_sec; /* xtime seconds as at tb_orig_stamp */
- __s32 stamp_xtime_nsec; /* xtime nsecs as at tb_orig_stamp */
- __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */
- __u32 hrtimer_res; /* hrtimer resolution */
__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
+ struct vdso_data data[CS_BASES];
};
#endif /* CONFIG_PPC64 */
-extern struct vdso_data *vdso_data;
+extern struct vdso_arch_data *vdso_data;
#else /* __ASSEMBLY__ */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index fcf24a365fc0..9a9b4a9353ff 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -394,47 +394,16 @@ int main(void)
#endif /* ! CONFIG_PPC64 */
/* datapage offsets for use by vdso */
- OFFSET(CFG_TB_ORIG_STAMP, vdso_data, tb_orig_stamp);
- OFFSET(CFG_TB_TICKS_PER_SEC, vdso_data, tb_ticks_per_sec);
- OFFSET(CFG_TB_TO_XS, vdso_data, tb_to_xs);
- OFFSET(CFG_TB_UPDATE_COUNT, vdso_data, tb_update_count);
- OFFSET(CFG_TZ_MINUTEWEST, vdso_data, tz_minuteswest);
- OFFSET(CFG_TZ_DSTTIME, vdso_data, tz_dsttime);
- OFFSET(CFG_SYSCALL_MAP32, vdso_data, syscall_map_32);
- OFFSET(WTOM_CLOCK_SEC, vdso_data, wtom_clock_sec);
- OFFSET(WTOM_CLOCK_NSEC, vdso_data, wtom_clock_nsec);
- OFFSET(STAMP_XTIME_SEC, vdso_data, stamp_xtime_sec);
- OFFSET(STAMP_XTIME_NSEC, vdso_data, stamp_xtime_nsec);
- OFFSET(STAMP_SEC_FRAC, vdso_data, stamp_sec_fraction);
- OFFSET(CLOCK_HRTIMER_RES, vdso_data, hrtimer_res);
+ OFFSET(VDSO_DATA_OFFSET, vdso_arch_data, data);
+ OFFSET(CFG_TB_TICKS_PER_SEC, vdso_arch_data, tb_ticks_per_sec);
+ OFFSET(CFG_SYSCALL_MAP32, vdso_arch_data, syscall_map_32);
#ifdef CONFIG_PPC64
- OFFSET(CFG_ICACHE_BLOCKSZ, vdso_data, icache_block_size);
- OFFSET(CFG_DCACHE_BLOCKSZ, vdso_data, dcache_block_size);
- OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_data, icache_log_block_size);
- OFFSET(CFG_DCACHE_LOGBLOCKSZ, vdso_data, dcache_log_block_size);
- OFFSET(CFG_SYSCALL_MAP64, vdso_data, syscall_map_64);
- OFFSET(TVAL64_TV_SEC, __kernel_old_timeval, tv_sec);
- OFFSET(TVAL64_TV_USEC, __kernel_old_timeval, tv_usec);
-#endif
- OFFSET(TSPC64_TV_SEC, __kernel_timespec, tv_sec);
- OFFSET(TSPC64_TV_NSEC, __kernel_timespec, tv_nsec);
- OFFSET(TVAL32_TV_SEC, old_timeval32, tv_sec);
- OFFSET(TVAL32_TV_USEC, old_timeval32, tv_usec);
- OFFSET(TSPC32_TV_SEC, old_timespec32, tv_sec);
- OFFSET(TSPC32_TV_NSEC, old_timespec32, tv_nsec);
- /* timeval/timezone offsets for use by vdso */
- OFFSET(TZONE_TZ_MINWEST, timezone, tz_minuteswest);
- OFFSET(TZONE_TZ_DSTTIME, timezone, tz_dsttime);
-
- /* Other bits used by the vdso */
- DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
- DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
- DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
- DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
- DEFINE(CLOCK_MAX, CLOCK_TAI);
- DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
- DEFINE(EINVAL, EINVAL);
- DEFINE(KTIME_LOW_RES, KTIME_LOW_RES);
+ OFFSET(CFG_ICACHE_BLOCKSZ, vdso_arch_data, icache_block_size);
+ OFFSET(CFG_DCACHE_BLOCKSZ, vdso_arch_data, dcache_block_size);
+ OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_arch_data, icache_log_block_size);
+ OFFSET(CFG_DCACHE_LOGBLOCKSZ, vdso_arch_data, dcache_log_block_size);
+ OFFSET(CFG_SYSCALL_MAP64, vdso_arch_data, syscall_map_64);
+#endif
#ifdef CONFIG_BUG
DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry));
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 6fcae436ae51..b63b1f97a1b3 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -91,6 +91,7 @@ static struct clocksource clocksource_timebase = {
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
.mask = CLOCKSOURCE_MASK(64),
.read = timebase_read,
+ .vdso_clock_mode = VDSO_CLOCKMODE_ARCHTIMER,
};
#define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF
@@ -855,95 +856,6 @@ static notrace u64 timebase_read(struct clocksource *cs)
return (u64)get_tb();
}
-
-void update_vsyscall(struct timekeeper *tk)
-{
- struct timespec64 xt;
- struct clocksource *clock = tk->tkr_mono.clock;
- u32 mult = tk->tkr_mono.mult;
- u32 shift = tk->tkr_mono.shift;
- u64 cycle_last = tk->tkr_mono.cycle_last;
- u64 new_tb_to_xs, new_stamp_xsec;
- u64 frac_sec;
-
- if (clock != &clocksource_timebase)
- return;
-
- xt.tv_sec = tk->xtime_sec;
- xt.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
-
- /* Make userspace gettimeofday spin until we're done. */
- ++vdso_data->tb_update_count;
- smp_mb();
-
- /*
- * This computes ((2^20 / 1e9) * mult) >> shift as a
- * 0.64 fixed-point fraction.
- * The computation in the else clause below won't overflow
- * (as long as the timebase frequency is >= 1.049 MHz)
- * but loses precision because we lose the low bits of the constant
- * in the shift. Note that 19342813113834067 ~= 2^(20+64) / 1e9.
- * For a shift of 24 the error is about 0.5e-9, or about 0.5ns
- * over a second. (Shift values are usually 22, 23 or 24.)
- * For high frequency clocks such as the 512MHz timebase clock
- * on POWER[6789], the mult value is small (e.g. 32768000)
- * and so we can shift the constant by 16 initially
- * (295147905179 ~= 2^(20+64-16) / 1e9) and then do the
- * remaining shifts after the multiplication, which gives a
- * more accurate result (e.g. with mult = 32768000, shift = 24,
- * the error is only about 1.2e-12, or 0.7ns over 10 minutes).
- */
- if (mult <= 62500000 && clock->shift >= 16)
- new_tb_to_xs = ((u64) mult * 295147905179ULL) >> (clock->shift - 16);
- else
- new_tb_to_xs = (u64) mult * (19342813113834067ULL >> clock->shift);
-
- /*
- * Compute the fractional second in units of 2^-32 seconds.
- * The fractional second is tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift
- * in nanoseconds, so multiplying that by 2^32 / 1e9 gives
- * it in units of 2^-32 seconds.
- * We assume shift <= 32 because clocks_calc_mult_shift()
- * generates shift values in the range 0 - 32.
- */
- frac_sec = tk->tkr_mono.xtime_nsec << (32 - shift);
- do_div(frac_sec, NSEC_PER_SEC);
-
- /*
- * Work out new stamp_xsec value for any legacy users of systemcfg.
- * stamp_xsec is in units of 2^-20 seconds.
- */
- new_stamp_xsec = frac_sec >> 12;
- new_stamp_xsec += tk->xtime_sec * XSEC_PER_SEC;
-
- /*
- * tb_update_count is used to allow the userspace gettimeofday code
- * to assure itself that it sees a consistent view of the tb_to_xs and
- * stamp_xsec variables. It reads the tb_update_count, then reads
- * tb_to_xs and stamp_xsec and then reads tb_update_count again. If
- * the two values of tb_update_count match and are even then the
- * tb_to_xs and stamp_xsec values are consistent. If not, then it
- * loops back and reads them again until this criteria is met.
- */
- vdso_data->tb_orig_stamp = cycle_last;
- vdso_data->stamp_xsec = new_stamp_xsec;
- vdso_data->tb_to_xs = new_tb_to_xs;
- vdso_data->wtom_clock_sec = tk->wall_to_monotonic.tv_sec;
- vdso_data->wtom_clock_nsec = tk->wall_to_monotonic.tv_nsec;
- vdso_data->stamp_xtime_sec = xt.tv_sec;
- vdso_data->stamp_xtime_nsec = xt.tv_nsec;
- vdso_data->stamp_sec_fraction = frac_sec;
- vdso_data->hrtimer_res = hrtimer_resolution;
- smp_wmb();
- ++(vdso_data->tb_update_count);
-}
-
-void update_vsyscall_tz(void)
-{
- vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
- vdso_data->tz_dsttime = sys_tz.tz_dsttime;
-}
-
static void __init clocksource_init(void)
{
struct clocksource *clock;
@@ -1113,7 +1025,6 @@ void __init time_init(void)
sys_tz.tz_dsttime = 0;
}
- vdso_data->tb_update_count = 0;
vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
/* initialise and enable the large decrementer (if we have one) */
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index d33fa22ddbed..6642dbe92946 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -17,6 +17,7 @@
#include <linux/elf.h>
#include <linux/security.h>
#include <linux/memblock.h>
+#include <vdso/datapage.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
@@ -71,10 +72,10 @@ static int vdso_ready;
* with it, it will become dynamically allocated
*/
static union {
- struct vdso_data data;
+ struct vdso_arch_data data;
u8 page[PAGE_SIZE];
} vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = &vdso_data_store.data;
+struct vdso_arch_data *vdso_data = &vdso_data_store.data;
/* Format of the patch table */
struct vdso_patch_def
diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
index e147bbdc12cd..b46c21ed9316 100644
--- a/arch/powerpc/kernel/vdso32/Makefile
+++ b/arch/powerpc/kernel/vdso32/Makefile
@@ -2,7 +2,23 @@
# List of files in the vdso, has to be asm only for now
-obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o
+ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN
+include $(srctree)/lib/vdso/Makefile
+
+obj-vdso32 = sigtramp.o datapage.o cacheflush.o note.o getcpu.o $(obj-vdso32-y)
+obj-vdso32 += gettimeofday.o
+
+ifneq ($(c-gettimeofday-y),)
+ ifdef CONFIG_PPC64
+ CFLAGS_vgettimeofday.o += -include $(srctree)/$(src)/config-fake32.h
+ endif
+ CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
+ CFLAGS_vgettimeofday.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+ CFLAGS_vgettimeofday.o += $(call cc-option, -fno-stack-protector)
+ CFLAGS_vgettimeofday.o += -DDISABLE_BRANCH_PROFILING
+ CFLAGS_vgettimeofday.o += -ffreestanding -fasynchronous-unwind-tables
+ CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE)
+endif
# Build rules
@@ -15,6 +31,7 @@ endif
CC32FLAGS :=
ifdef CONFIG_PPC64
CC32FLAGS += -m32
+KBUILD_CFLAGS := $(filter-out -mcmodel=medium,$(KBUILD_CFLAGS))
endif
targets := $(obj-vdso32) vdso32.so vdso32.so.dbg
@@ -23,6 +40,7 @@ obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
GCOV_PROFILE := n
KCOV_INSTRUMENT := n
UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
ccflags-y := -shared -fno-common -fno-builtin -nostdlib \
-Wl,-soname=linux-vdso32.so.1 -Wl,--hash-style=both
@@ -36,8 +54,8 @@ CPPFLAGS_vdso32.lds += -P -C -Upowerpc
$(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
# link rule for the .so file, .lds has to be first
-$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE
- $(call if_changed,vdso32ld)
+$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday.o FORCE
+ $(call if_changed,vdso32ld_and_check)
# strip rule for the .so file
$(obj)/%.so: OBJCOPYFLAGS := -S
@@ -47,12 +65,16 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
# assembly rules for the .S files
$(obj-vdso32): %.o: %.S FORCE
$(call if_changed_dep,vdso32as)
+$(obj)/vgettimeofday.o: %.o: %.c FORCE
+ $(call if_changed_dep,vdso32cc)
# actual build commands
-quiet_cmd_vdso32ld = VDSO32L $@
- cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
+quiet_cmd_vdso32ld_and_check = VDSO32L $@
+ cmd_vdso32ld_and_check = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) ; $(cmd_vdso_check)
quiet_cmd_vdso32as = VDSO32A $@
cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) -c -o $@ $<
+quiet_cmd_vdso32cc = VDSO32C $@
+ cmd_vdso32cc = $(VDSOCC) $(c_flags) $(CC32FLAGS) -c -o $@ $<
# install commands for the unstripped file
quiet_cmd_vdso_install = INSTALL $@
diff --git a/arch/powerpc/kernel/vdso32/config-fake32.h b/arch/powerpc/kernel/vdso32/config-fake32.h
new file mode 100644
index 000000000000..e16041fc15c9
--- /dev/null
+++ b/arch/powerpc/kernel/vdso32/config-fake32.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * In case of a 32 bit VDSO for a 64 bit kernel fake a 32 bit kernel
+ * configuration.
+ */
+
+#undef CONFIG_PPC64
+#undef CONFIG_64BIT
+#define CONFIG_PPC32
+#define CONFIG_32BIT 1
+#define CONFIG_GENERIC_ATOMIC64 1
+
+#ifdef CONFIG_PPC_BOOK3S_64
+#undef CONFIG_PPC_BOOK3S_64
+#undef CONFIG_PPC_PSERIES
+#define CONFIG_PPC_BOOK3S_32
+#else
+#define CONFIG_PPC_MMU_NOHASH_32
+#define CONFIG_FSL_BOOKE
+#endif
+
+#define CONFIG_TASK_SIZE 0
+#undef CONFIG_MMIOWB
+#undef CONFIG_PPC_SPLPAR
+#undef CONFIG_SPARSEMEM
+#undef CONFIG_PGTABLE_LEVELS
+#define CONFIG_PGTABLE_LEVELS 2
+#undef CONFIG_TRANSPARENT_HUGEPAGE
+#undef CONFIG_SPARSEMEM_VMEMMAP
+#undef CONFIG_FLATMEM
+#define CONFIG_FLATMEM
+#undef CONFIG_PPC_INDIRECT_MMIO
+#undef CONFIG_PPC_INDIRECT_PIO
+#undef CONFIG_EEH
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 0bbdce0f2a9c..fd7b01c51281 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -12,13 +12,7 @@
#include <asm/vdso_datapage.h>
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
-
-/* Offset for the low 32-bit part of a field of long type */
-#ifdef CONFIG_PPC64
-#define LOPART 4
-#else
-#define LOPART 0
-#endif
+#include <asm/vdso/gettimeofday.h>
.text
/*
@@ -28,32 +22,7 @@
*
*/
V_FUNCTION_BEGIN(__kernel_gettimeofday)
- .cfi_startproc
- mflr r12
- .cfi_register lr,r12
-
- mr. r10,r3 /* r10 saves tv */
- mr r11,r4 /* r11 saves tz */
- 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 */
- stw r3,TVAL32_TV_SEC(r10)
- stw r4,TVAL32_TV_USEC(r10)
-
-3: cmplwi r11,0 /* check if tz is NULL */
- mtlr r12
- crclr cr0*4+so
- li r3,0
- beqlr
-
- lwz r4,CFG_TZ_MINUTEWEST(r9)/* fill tz */
- lwz r5,CFG_TZ_DSTTIME(r9)
- stw r4,TZONE_TZ_MINWEST(r11)
- stw r5,TZONE_TZ_DSTTIME(r11)
-
- blr
- .cfi_endproc
+ cvdso_call __c_kernel_gettimeofday
V_FUNCTION_END(__kernel_gettimeofday)
/*
@@ -63,127 +32,7 @@ V_FUNCTION_END(__kernel_gettimeofday)
*
*/
V_FUNCTION_BEGIN(__kernel_clock_gettime)
- .cfi_startproc
- /* Check for supported clock IDs */
- cmpli cr0,r3,CLOCK_REALTIME
- cmpli cr1,r3,CLOCK_MONOTONIC
- cror cr0*4+eq,cr0*4+eq,cr1*4+eq
-
- cmpli cr5,r3,CLOCK_REALTIME_COARSE
- cmpli cr6,r3,CLOCK_MONOTONIC_COARSE
- cror cr5*4+eq,cr5*4+eq,cr6*4+eq
-
- cror cr0*4+eq,cr0*4+eq,cr5*4+eq
- bne cr0, .Lgettime_fallback
-
- mflr r12 /* r12 saves lr */
- .cfi_register lr,r12
- mr r11,r4 /* r11 saves tp */
- get_datapage r9
- LOAD_REG_IMMEDIATE(r7, NSEC_PER_SEC) /* load up NSEC_PER_SEC */
- beq cr5, .Lcoarse_clocks
-.Lprecise_clocks:
- bl __do_get_tspec@local /* get sec/nsec from tb & kernel */
- bne cr1, .Lfinish /* not monotonic -> all done */
-
- /*
- * CLOCK_MONOTONIC
- */
-
- /* now we must fixup using wall to monotonic. We need to snapshot
- * that value and do the counter trick again. Fortunately, we still
- * have the counter value in r8 that was returned by __do_get_xsec.
- * At this point, r3,r4 contain our sec/nsec values, r5 and r6
- * can be used, r7 contains NSEC_PER_SEC.
- */
-
- lwz r5,(WTOM_CLOCK_SEC+LOPART)(r9)
- lwz r6,WTOM_CLOCK_NSEC(r9)
-
- /* We now have our offset in r5,r6. We create a fake dependency
- * on that value and re-check the counter
- */
- or r0,r6,r5
- xor r0,r0,r0
- add r9,r9,r0
- lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
- cmpl cr0,r8,r0 /* check if updated */
- bne- .Lprecise_clocks
- b .Lfinish_monotonic
-
- /*
- * For coarse clocks we get data directly from the vdso data page, so
- * we don't need to call __do_get_tspec, but we still need to do the
- * counter trick.
- */
-.Lcoarse_clocks:
- lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
- andi. r0,r8,1 /* pending update ? loop */
- bne- .Lcoarse_clocks
- add r9,r9,r0 /* r0 is already 0 */
-
- /*
- * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
- * too
- */
- lwz r3,STAMP_XTIME_SEC+LOPART(r9)
- lwz r4,STAMP_XTIME_NSEC+LOPART(r9)
- bne cr6,1f
-
- /* CLOCK_MONOTONIC_COARSE */
- lwz r5,(WTOM_CLOCK_SEC+LOPART)(r9)
- lwz r6,WTOM_CLOCK_NSEC(r9)
-
- /* check if counter has updated */
- or r0,r6,r5
-1: or r0,r0,r3
- or r0,r0,r4
- xor r0,r0,r0
- add r3,r3,r0
- lwz r0,CFG_TB_UPDATE_COUNT+LOPART(r9)
- cmpl cr0,r0,r8 /* check if updated */
- bne- .Lcoarse_clocks
-
- /* Counter has not updated, so continue calculating proper values for
- * sec and nsec if monotonic coarse, or just return with the proper
- * values for realtime.
- */
- bne cr6, .Lfinish
-
- /* Calculate and store result. Note that this mimics the C code,
- * which may cause funny results if nsec goes negative... is that
- * possible at all ?
- */
-.Lfinish_monotonic:
- add r3,r3,r5
- add r4,r4,r6
- cmpw cr0,r4,r7
- cmpwi cr1,r4,0
- blt 1f
- subf r4,r7,r4
- addi r3,r3,1
-1: bge cr1, .Lfinish
- addi r3,r3,-1
- add r4,r4,r7
-
-.Lfinish:
- stw r3,TSPC32_TV_SEC(r11)
- stw r4,TSPC32_TV_NSEC(r11)
-
- mtlr r12
- crclr cr0*4+so
- li r3,0
- blr
-
- /*
- * syscall fallback
- */
-.Lgettime_fallback:
- li r0,__NR_clock_gettime
- .cfi_restore lr
- sc
- blr
- .cfi_endproc
+ cvdso_call __c_kernel_clock_gettime
V_FUNCTION_END(__kernel_clock_gettime)
@@ -194,37 +43,7 @@ V_FUNCTION_END(__kernel_clock_gettime)
*
*/
V_FUNCTION_BEGIN(__kernel_clock_getres)
- .cfi_startproc
- /* Check for supported clock IDs */
- cmplwi cr0, r3, CLOCK_MAX
- cmpwi cr1, r3, CLOCK_REALTIME_COARSE
- cmpwi cr7, r3, CLOCK_MONOTONIC_COARSE
- bgt cr0, 99f
- LOAD_REG_IMMEDIATE(r5, KTIME_LOW_RES)
- beq cr1, 1f
- beq cr7, 1f
-
- mflr r12
- .cfi_register lr,r12
- get_datapage r3
- lwz r5, CLOCK_HRTIMER_RES(r3)
- mtlr r12
-1: li r3,0
- cmpli cr0,r4,0
- crclr cr0*4+so
- beqlr
- stw r3,TSPC32_TV_SEC(r4)
- stw r5,TSPC32_TV_NSEC(r4)
- blr
-
- /*
- * invalid clock
- */
-99:
- li r3, EINVAL
- crset so
- blr
- .cfi_endproc
+ cvdso_call __c_kernel_clock_getres
V_FUNCTION_END(__kernel_clock_getres)
@@ -235,105 +54,5 @@ V_FUNCTION_END(__kernel_clock_getres)
*
*/
V_FUNCTION_BEGIN(__kernel_time)
- .cfi_startproc
- mflr r12
- .cfi_register lr,r12
-
- mr r11,r3 /* r11 holds t */
- get_datapage r9
-
- lwz r3,STAMP_XTIME_SEC+LOPART(r9)
-
- cmplwi r11,0 /* check if t is NULL */
- mtlr r12
- crclr cr0*4+so
- beqlr
- stw r3,0(r11) /* store result at *t */
- blr
- .cfi_endproc
+ cvdso_call_time __c_kernel_time
V_FUNCTION_END(__kernel_time)
-
-/*
- * This is the core of clock_gettime() and gettimeofday(),
- * it returns the current time in r3 (seconds) and r4.
- * On entry, r7 gives the resolution of r4, either USEC_PER_SEC
- * or NSEC_PER_SEC, giving r4 in microseconds or nanoseconds.
- * It expects the datapage ptr in r9 and doesn't clobber it.
- * It clobbers r0, r5 and r6.
- * On return, r8 contains the counter value that can be reused.
- * This clobbers cr0 but not any other cr field.
- */
-__do_get_tspec:
- .cfi_startproc
- /* Check for update count & load values. We use the low
- * order 32 bits of the update count
- */
-1: lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
- andi. r0,r8,1 /* pending update ? loop */
- bne- 1b
- xor r0,r8,r8 /* create dependency */
- add r9,r9,r0
-
- /* Load orig stamp (offset to TB) */
- lwz r5,CFG_TB_ORIG_STAMP(r9)
- lwz r6,(CFG_TB_ORIG_STAMP+4)(r9)
-
- /* Get a stable TB value */
-2: MFTBU(r3)
- MFTBL(r4)
- MFTBU(r0)
- cmplw cr0,r3,r0
- bne- 2b
-
- /* Subtract tb orig stamp and shift left 12 bits.
- */
- subfc r4,r6,r4
- subfe r0,r5,r3
- slwi r0,r0,12
- rlwimi. r0,r4,12,20,31
- slwi r4,r4,12
-
- /*
- * Load scale factor & do multiplication.
- * We only use the high 32 bits of the tb_to_xs value.
- * Even with a 1GHz timebase clock, the high 32 bits of
- * tb_to_xs will be at least 4 million, so the error from
- * ignoring the low 32 bits will be no more than 0.25ppm.
- * The error will just make the clock run very very slightly
- * slow until the next time the kernel updates the VDSO data,
- * at which point the clock will catch up to the kernel's value,
- * so there is no long-term error accumulation.
- */
- lwz r5,CFG_TB_TO_XS(r9) /* load values */
- mulhwu r4,r4,r5
- li r3,0
-
- beq+ 4f /* skip high part computation if 0 */
- mulhwu r3,r0,r5
- mullw r5,r0,r5
- addc r4,r4,r5
- addze r3,r3
-4:
- /* At this point, we have seconds since the xtime stamp
- * as a 32.32 fixed-point number in r3 and r4.
- * Load & add the xtime stamp.
- */
- lwz r5,STAMP_XTIME_SEC+LOPART(r9)
- lwz r6,STAMP_SEC_FRAC(r9)
- addc r4,r4,r6
- adde r3,r3,r5
-
- /* We create a fake dependency on the result in r3/r4
- * and re-check the counter
- */
- or r6,r4,r3
- xor r0,r6,r6
- add r9,r9,r0
- lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
- cmplw cr0,r8,r0 /* check if updated */
- bne- 1b
-
- mulhwu r4,r4,r7 /* convert to micro or nanoseconds */
-
- blr
- .cfi_endproc
diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
index 32ebb3522ea1..29bffd4863f2 100644
--- a/arch/powerpc/kernel/vdso64/Makefile
+++ b/arch/powerpc/kernel/vdso64/Makefile
@@ -1,8 +1,20 @@
# SPDX-License-Identifier: GPL-2.0
# List of files in the vdso, has to be asm only for now
+ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN
+include $(srctree)/lib/vdso/Makefile
+
obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o
+ifneq ($(c-gettimeofday-y),)
+ CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
+ CFLAGS_vgettimeofday.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+ CFLAGS_vgettimeofday.o += $(call cc-option, -fno-stack-protector)
+ CFLAGS_vgettimeofday.o += -DDISABLE_BRANCH_PROFILING
+ CFLAGS_vgettimeofday.o += -ffreestanding -fasynchronous-unwind-tables
+ CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE)
+endif
+
# Build rules
targets := $(obj-vdso64) vdso64.so vdso64.so.dbg
@@ -11,6 +23,7 @@ obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
GCOV_PROFILE := n
KCOV_INSTRUMENT := n
UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
ccflags-y := -shared -fno-common -fno-builtin -nostdlib \
-Wl,-soname=linux-vdso64.so.1 -Wl,--hash-style=both
@@ -20,12 +33,14 @@ obj-y += vdso64_wrapper.o
extra-y += vdso64.lds
CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
+$(obj)/vgettimeofday.o: %.o: %.c FORCE
+
# Force dependency (incbin is bad)
$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
# link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE
- $(call if_changed,vdso64ld)
+$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday.o FORCE
+ $(call if_changed,vdso64ld_and_check)
# strip rule for the .so file
$(obj)/%.so: OBJCOPYFLAGS := -S
@@ -33,8 +48,8 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
$(call if_changed,objcopy)
# actual build commands
-quiet_cmd_vdso64ld = VDSO64L $@
- cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
+quiet_cmd_vdso64ld_and_check = VDSO64L $@
+ cmd_vdso64ld_and_check = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) ; $(cmd_vdso_check)
# install commands for the unstripped file
quiet_cmd_vdso_install = INSTALL $@
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index 275f031d0bf1..d7a7bfb51081 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -9,8 +9,10 @@
#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
+#include <asm/vdso/gettimeofday.h>
.text
/*
@@ -20,31 +22,7 @@
*
*/
V_FUNCTION_BEGIN(__kernel_gettimeofday)
- .cfi_startproc
- mflr r12
- .cfi_register lr,r12
-
- mr r11,r3 /* r11 holds tv */
- mr r10,r4 /* r10 holds tz */
- get_datapage r3
- cmpldi r11,0 /* check if tv is NULL */
- beq 2f
- lis r7,1000000@ha /* load up USEC_PER_SEC */
- addi r7,r7,1000000@l
- bl V_LOCAL_FUNC(__do_get_tspec) /* get sec/us from tb & kernel */
- std r4,TVAL64_TV_SEC(r11) /* store sec in tv */
- std r5,TVAL64_TV_USEC(r11) /* store usec in tv */
-2: cmpldi r10,0 /* check if tz is NULL */
- beq 1f
- lwz r4,CFG_TZ_MINUTEWEST(r3)/* fill tz */
- lwz r5,CFG_TZ_DSTTIME(r3)
- stw r4,TZONE_TZ_MINWEST(r10)
- stw r5,TZONE_TZ_DSTTIME(r10)
-1: mtlr r12
- crclr cr0*4+so
- li r3,0 /* always success */
- blr
- .cfi_endproc
+ cvdso_call __c_kernel_gettimeofday
V_FUNCTION_END(__kernel_gettimeofday)
@@ -55,120 +33,7 @@ V_FUNCTION_END(__kernel_gettimeofday)
*
*/
V_FUNCTION_BEGIN(__kernel_clock_gettime)
- .cfi_startproc
- /* Check for supported clock IDs */
- cmpwi cr0,r3,CLOCK_REALTIME
- cmpwi cr1,r3,CLOCK_MONOTONIC
- cror cr0*4+eq,cr0*4+eq,cr1*4+eq
-
- cmpwi cr5,r3,CLOCK_REALTIME_COARSE
- cmpwi cr6,r3,CLOCK_MONOTONIC_COARSE
- cror cr5*4+eq,cr5*4+eq,cr6*4+eq
-
- cror cr0*4+eq,cr0*4+eq,cr5*4+eq
- bne cr0,99f
-
- mflr r12 /* r12 saves lr */
- .cfi_register lr,r12
- mr r11,r4 /* r11 saves tp */
- get_datapage r3
- lis r7,NSEC_PER_SEC@h /* want nanoseconds */
- ori r7,r7,NSEC_PER_SEC@l
- beq cr5,70f
-50: bl V_LOCAL_FUNC(__do_get_tspec) /* get time from tb & kernel */
- bne cr1,80f /* if not monotonic, all done */
-
- /*
- * CLOCK_MONOTONIC
- */
-
- /* now we must fixup using wall to monotonic. We need to snapshot
- * that value and do the counter trick again. Fortunately, we still
- * have the counter value in r8 that was returned by __do_get_tspec.
- * At this point, r4,r5 contain our sec/nsec values.
- */
-
- ld r6,WTOM_CLOCK_SEC(r3)
- lwa r9,WTOM_CLOCK_NSEC(r3)
-
- /* We now have our result in r6,r9. We create a fake dependency
- * on that result and re-check the counter
- */
- or r0,r6,r9
- xor r0,r0,r0
- add r3,r3,r0
- ld r0,CFG_TB_UPDATE_COUNT(r3)
- cmpld cr0,r0,r8 /* check if updated */
- bne- 50b
- b 78f
-
- /*
- * For coarse clocks we get data directly from the vdso data page, so
- * we don't need to call __do_get_tspec, but we still need to do the
- * counter trick.
- */
-70: ld r8,CFG_TB_UPDATE_COUNT(r3)
- andi. r0,r8,1 /* pending update ? loop */
- bne- 70b
- add r3,r3,r0 /* r0 is already 0 */
-
- /*
- * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
- * too
- */
- ld r4,STAMP_XTIME_SEC(r3)
- ld r5,STAMP_XTIME_NSEC(r3)
- bne cr6,75f
-
- /* CLOCK_MONOTONIC_COARSE */
- ld r6,WTOM_CLOCK_SEC(r3)
- lwa r9,WTOM_CLOCK_NSEC(r3)
-
- /* check if counter has updated */
- or r0,r6,r9
-75: or r0,r0,r4
- or r0,r0,r5
- xor r0,r0,r0
- add r3,r3,r0
- ld r0,CFG_TB_UPDATE_COUNT(r3)
- cmpld cr0,r0,r8 /* check if updated */
- bne- 70b
-
- /* Counter has not updated, so continue calculating proper values for
- * sec and nsec if monotonic coarse, or just return with the proper
- * values for realtime.
- */
- bne cr6,80f
-
- /* Add wall->monotonic offset and check for overflow or underflow */
-78: add r4,r4,r6
- add r5,r5,r9
- cmpd cr0,r5,r7
- cmpdi cr1,r5,0
- blt 79f
- subf r5,r7,r5
- addi r4,r4,1
-79: bge cr1,80f
- addi r4,r4,-1
- add r5,r5,r7
-
-80: std r4,TSPC64_TV_SEC(r11)
- std r5,TSPC64_TV_NSEC(r11)
-
- mtlr r12
- crclr cr0*4+so
- li r3,0
- blr
-
- /*
- * syscall fallback
- */
-99:
- li r0,__NR_clock_gettime
- .cfi_restore lr
- sc
- blr
- .cfi_endproc
+ cvdso_call __c_kernel_clock_gettime
V_FUNCTION_END(__kernel_clock_gettime)
@@ -179,34 +44,7 @@ V_FUNCTION_END(__kernel_clock_gettime)
*
*/
V_FUNCTION_BEGIN(__kernel_clock_getres)
- .cfi_startproc
- /* Check for supported clock IDs */
- cmpwi cr0,r3,CLOCK_REALTIME
- cmpwi cr1,r3,CLOCK_MONOTONIC
- cror cr0*4+eq,cr0*4+eq,cr1*4+eq
- bne cr0,99f
-
- mflr r12
- .cfi_register lr,r12
- get_datapage r3
- lwz r5, CLOCK_HRTIMER_RES(r3)
- mtlr r12
- li r3,0
- cmpldi cr0,r4,0
- crclr cr0*4+so
- beqlr
- std r3,TSPC64_TV_SEC(r4)
- std r5,TSPC64_TV_NSEC(r4)
- blr
-
- /*
- * syscall fallback
- */
-99:
- li r0,__NR_clock_getres
- sc
- blr
- .cfi_endproc
+ cvdso_call __c_kernel_clock_getres
V_FUNCTION_END(__kernel_clock_getres)
/*
@@ -216,74 +54,5 @@ V_FUNCTION_END(__kernel_clock_getres)
*
*/
V_FUNCTION_BEGIN(__kernel_time)
- .cfi_startproc
- mflr r12
- .cfi_register lr,r12
-
- mr r11,r3 /* r11 holds t */
- get_datapage r3
-
- ld r4,STAMP_XTIME_SEC(r3)
-
- cmpldi r11,0 /* check if t is NULL */
- beq 2f
- std r4,0(r11) /* store result at *t */
-2: mtlr r12
- crclr cr0*4+so
- mr r3,r4
- blr
- .cfi_endproc
+ cvdso_call_time __c_kernel_time
V_FUNCTION_END(__kernel_time)
-
-
-/*
- * This is the core of clock_gettime() and gettimeofday(),
- * it returns the current time in r4 (seconds) and r5.
- * On entry, r7 gives the resolution of r5, either USEC_PER_SEC
- * or NSEC_PER_SEC, giving r5 in microseconds or nanoseconds.
- * It expects the datapage ptr in r3 and doesn't clobber it.
- * It clobbers r0, r6 and r9.
- * On return, r8 contains the counter value that can be reused.
- * This clobbers cr0 but not any other cr field.
- */
-V_FUNCTION_BEGIN(__do_get_tspec)
- .cfi_startproc
- /* check for update count & load values */
-1: ld r8,CFG_TB_UPDATE_COUNT(r3)
- andi. r0,r8,1 /* pending update ? loop */
- bne- 1b
- xor r0,r8,r8 /* create dependency */
- add r3,r3,r0
-
- /* Get TB & offset it. We use the MFTB macro which will generate
- * workaround code for Cell.
- */
- MFTB(r6)
- ld r9,CFG_TB_ORIG_STAMP(r3)
- subf r6,r9,r6
-
- /* Scale result */
- ld r5,CFG_TB_TO_XS(r3)
- sldi r6,r6,12 /* compute time since stamp_xtime */
- mulhdu r6,r6,r5 /* in units of 2^-32 seconds */
-
- /* Add stamp since epoch */
- ld r4,STAMP_XTIME_SEC(r3)
- lwz r5,STAMP_SEC_FRAC(r3)
- or r0,r4,r5
- or r0,r0,r6
- xor r0,r0,r0
- add r3,r3,r0
- ld r0,CFG_TB_UPDATE_COUNT(r3)
- cmpld r0,r8 /* check if updated */
- bne- 1b /* reload if so */
-
- /* convert to seconds & nanoseconds and add to stamp */
- add r6,r6,r5 /* add on fractional seconds of xtime */
- mulhwu r5,r6,r7 /* compute micro or nanoseconds and */
- srdi r6,r6,32 /* seconds since stamp_xtime */
- clrldi r5,r5,32
- add r4,r4,r6
- blr
- .cfi_endproc
-V_FUNCTION_END(__do_get_tspec)
--
2.25.0
^ permalink raw reply related
* [PATCH v8 7/8] lib/vdso: force inlining of __cvdso_clock_gettime_common()
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>
When adding gettime64() to a 32 bit architecture (namely powerpc/32)
it has been noticed that GCC doesn't inline anymore
__cvdso_clock_gettime_common() because it is called twice
(Once by __cvdso_clock_gettime() and once by
__cvdso_clock_gettime32).
This has the effect of seriously degrading the performance:
Before the implementation of gettime64(), gettime() runs in:
clock-gettime-monotonic-raw: vdso: 1003 nsec/call
clock-gettime-monotonic-coarse: vdso: 592 nsec/call
clock-gettime-monotonic: vdso: 942 nsec/call
When adding a gettime64() entry point, the standard gettime()
performance is degraded by 30% to 50%:
clock-gettime-monotonic-raw: vdso: 1300 nsec/call
clock-gettime-monotonic-coarse: vdso: 900 nsec/call
clock-gettime-monotonic: vdso: 1232 nsec/call
Adding __always_inline() to __cvdso_clock_gettime_common()
regains the original performance.
In terms of code size, the inlining increases the code size
by only 176 bytes. This is in the noise for a kernel image.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
lib/vdso/gettimeofday.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index a2909af4b924..7938d3c4901d 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -210,7 +210,7 @@ static __always_inline int do_coarse(const struct vdso_data *vd, clockid_t clk,
return 0;
}
-static __maybe_unused int
+static __always_inline int
__cvdso_clock_gettime_common(const struct vdso_data *vd, clockid_t clock,
struct __kernel_timespec *ts)
{
--
2.25.0
^ permalink raw reply related
* [PATCH 1/2] powerpc: Keep .rela* sections when CONFIG_RELOCATABLE is defined
From: H.J. Lu @ 2020-04-28 13:21 UTC (permalink / raw)
To: linux-kernel
Cc: linux-arch, Yu-cheng Yu, Kees Cook, Arnd Bergmann, Paul Mackerras,
Naveen N . Rao, Borislav Petkov, linuxppc-dev
arch/powerpc/kernel/vmlinux.lds.S has
#ifdef CONFIG_RELOCATABLE
...
.rela.dyn : AT(ADDR(.rela.dyn) - LOAD_OFFSET)
{
__rela_dyn_start = .;
*(.rela*)
}
#endif
...
DISCARDS
/DISCARD/ : {
*(*.EMB.apuinfo)
*(.glink .iplt .plt .rela* .comment)
*(.gnu.version*)
*(.gnu.attributes)
*(.eh_frame)
}
Since .rela* sections are needed when CONFIG_RELOCATABLE is defined,
don't discard .rela* sections if CONFIG_RELOCATABLE is defined.
Signed-off-by: H.J. Lu <hjl.tools@gmail.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
---
arch/powerpc/kernel/vmlinux.lds.S | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 31a0f201fb6f..4ba07734a210 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -366,9 +366,12 @@ SECTIONS
DISCARDS
/DISCARD/ : {
*(*.EMB.apuinfo)
- *(.glink .iplt .plt .rela* .comment)
+ *(.glink .iplt .plt .comment)
*(.gnu.version*)
*(.gnu.attributes)
*(.eh_frame)
+#ifndef CONFIG_RELOCATABLE
+ *(.rela*)
+#endif
}
}
--
2.25.4
^ permalink raw reply related
* [PATCH 2/2] Discard .note.gnu.property sections in generic NOTES
From: H.J. Lu @ 2020-04-28 13:21 UTC (permalink / raw)
To: linux-kernel
Cc: linux-arch, Yu-cheng Yu, Kees Cook, Arnd Bergmann, Paul Mackerras,
Naveen N . Rao, Borislav Petkov, linuxppc-dev
In-Reply-To: <20200428132105.170886-1-hjl.tools@gmail.com>
With the command-line option, -mx86-used-note=yes, the x86 assembler
in binutils 2.32 and above generates a program property note in a note
section, .note.gnu.property, to encode used x86 ISAs and features. But
kernel linker script only contains a single NOTE segment:
PHDRS {
text PT_LOAD FLAGS(5);
data PT_LOAD FLAGS(6);
percpu PT_LOAD FLAGS(6);
init PT_LOAD FLAGS(7);
note PT_NOTE FLAGS(0);
}
SECTIONS
{
...
.notes : AT(ADDR(.notes) - 0xffffffff80000000) { __start_notes = .; KEEP(*(.not
e.*)) __stop_notes = .; } :text :note
...
}
The NOTE segment generated by kernel linker script is aligned to 4 bytes.
But .note.gnu.property section must be aligned to 8 bytes on x86-64 and
we get
[hjl@gnu-skx-1 linux]$ readelf -n vmlinux
Displaying notes found in: .notes
Owner Data size Description
Xen 0x00000006 Unknown note type: (0x00000006)
description data: 6c 69 6e 75 78 00
Xen 0x00000004 Unknown note type: (0x00000007)
description data: 32 2e 36 00
xen-3.0 0x00000005 Unknown note type: (0x006e6558)
description data: 08 00 00 00 03
readelf: Warning: note with invalid namesz and/or descsz found at offset 0x50
readelf: Warning: type: 0xffffffff, namesize: 0x006e6558, descsize:
0x80000000, alignment: 8
[hjl@gnu-skx-1 linux]$
Since note.gnu.property section in kernel image is never used, this patch
discards .note.gnu.property sections in kernel linker script by adding
/DISCARD/ : {
*(.note.gnu.property)
}
before kernel NOTE segment in generic NOTES.
Signed-off-by: H.J. Lu <hjl.tools@gmail.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
---
include/asm-generic/vmlinux.lds.h | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 71e387a5fe90..95cd678428f4 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -833,7 +833,14 @@
#define TRACEDATA
#endif
+/*
+ * Discard .note.gnu.property sections which are unused and have
+ * different alignment requirement from kernel note sections.
+ */
#define NOTES \
+ /DISCARD/ : { \
+ *(.note.gnu.property) \
+ } \
.notes : AT(ADDR(.notes) - LOAD_OFFSET) { \
__start_notes = .; \
KEEP(*(.note.*)) \
--
2.25.4
^ permalink raw reply related
* Re: [PATCH] powerpc/spufs: Add rcu_read_lock() around fcheck()
From: Christoph Hellwig @ 2020-04-28 13:52 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev, linux-kernel, hch, viro, jk
In-Reply-To: <20200428114811.68436-1-mpe@ellerman.id.au>
On Tue, Apr 28, 2020 at 09:48:11PM +1000, Michael Ellerman wrote:
>
> This comes from fcheck_files() via fcheck().
>
> It's pretty clearly documented that fcheck() must be wrapped with
> rcu_read_lock(), so fix it.
But for this to actually be useful you'd need the rcu read lock until
your are done with the file (or got a reference).
^ permalink raw reply
* Re: [RFC PATCH] powerpc/spufs: fix copy_to_user while atomic
From: Christoph Hellwig @ 2020-04-28 13:54 UTC (permalink / raw)
To: Jeremy Kerr
Cc: Arnd Bergmann, linuxppc-dev, linux-kernel, Eric W . Biederman,
linux-fsdevel, Andrew Morton, Linus Torvalds, Christoph Hellwig,
Alexander Viro
In-Reply-To: <20200428120207.15728-1-jk@ozlabs.org>
On Tue, Apr 28, 2020 at 08:02:07PM +0800, Jeremy Kerr wrote:
> 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.
I recognize plenty of sniplets from that :) Your patch looks good
to me:
Reviewed-by: Christoph Hellwig <hch@lst.de>
^ permalink raw reply
* [PATCH v2 1/2] powerpc/ftrace: Simplify error checking when patching instructions
From: Naveen N. Rao @ 2020-04-28 14:03 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Steven Rostedt
In-Reply-To: <cover.1588082133.git.naveen.n.rao@linux.vnet.ibm.com>
Introduce a macro PATCH_INSN_OR_GOTO() to simplify instruction patching,
and to make the error messages more uniform and useful:
- print an error message that includes the original return value
- print the function name and line numbers, so that the offending
location is clear
- goto a label which always return -EPERM, which ftrace_bug() expects
for proper error handling
Also eliminate use of patch_branch() since most such uses already call
create_branch() for error checking before patching. Instead, use the
return value from create_branch() with PATCH_INSN_OR_GOTO().
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
---
arch/powerpc/kernel/trace/ftrace.c | 96 +++++++++++++++++++-----------
1 file changed, 60 insertions(+), 36 deletions(-)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 7ea0ca044b65..63edbd48af42 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -31,6 +31,17 @@
#ifdef CONFIG_DYNAMIC_FTRACE
+#define PATCH_INSN_OR_GOTO(addr, instr, label) \
+do { \
+ int rc = patch_instruction((unsigned int *)(addr), instr); \
+ if (rc) { \
+ pr_err("%s:%d Error patching instruction at 0x%pK (%pS): %d\n", \
+ __func__, __LINE__, \
+ (void *)(addr), (void *)(addr), rc); \
+ goto label; \
+ } \
+} while (0)
+
/*
* We generally only have a single long_branch tramp and at most 2 or 3 plt
* tramps generated. But, we don't use the plt tramps currently. We also allot
@@ -78,10 +89,12 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
}
/* replace the text with the new text */
- if (patch_instruction((unsigned int *)ip, new))
- return -EPERM;
+ PATCH_INSN_OR_GOTO(ip, new, patch_err);
return 0;
+
+patch_err:
+ return -EPERM;
}
/*
@@ -204,12 +217,12 @@ __ftrace_make_nop(struct module *mod,
}
#endif /* CONFIG_MPROFILE_KERNEL */
- if (patch_instruction((unsigned int *)ip, pop)) {
- pr_err("Patching NOP failed.\n");
- return -EPERM;
- }
+ PATCH_INSN_OR_GOTO(ip, pop, patch_err);
return 0;
+
+patch_err:
+ return -EPERM;
}
#else /* !PPC64 */
@@ -276,10 +289,12 @@ __ftrace_make_nop(struct module *mod,
op = PPC_INST_NOP;
- if (patch_instruction((unsigned int *)ip, op))
- return -EPERM;
+ PATCH_INSN_OR_GOTO(ip, op, patch_err);
return 0;
+
+patch_err:
+ return -EPERM;
}
#endif /* PPC64 */
#endif /* CONFIG_MODULES */
@@ -322,7 +337,7 @@ static int add_ftrace_tramp(unsigned long tramp)
*/
static int setup_mcount_compiler_tramp(unsigned long tramp)
{
- int i, op;
+ unsigned int i, op;
unsigned long ptr;
static unsigned long ftrace_plt_tramps[NUM_FTRACE_TRAMPS];
@@ -366,16 +381,14 @@ static int setup_mcount_compiler_tramp(unsigned long tramp)
#else
ptr = ppc_global_function_entry((void *)ftrace_caller);
#endif
- if (!create_branch((void *)tramp, ptr, 0)) {
+ op = create_branch((void *)tramp, ptr, 0);
+ if (!op) {
pr_debug("%ps is not reachable from existing mcount tramp\n",
(void *)ptr);
return -1;
}
- if (patch_branch((unsigned int *)tramp, ptr, 0)) {
- pr_debug("REL24 out of range!\n");
- return -1;
- }
+ PATCH_INSN_OR_GOTO(tramp, op, patch_err);
if (add_ftrace_tramp(tramp)) {
pr_debug("No tramp locations left\n");
@@ -383,6 +396,9 @@ static int setup_mcount_compiler_tramp(unsigned long tramp)
}
return 0;
+
+patch_err:
+ return -EPERM;
}
static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)
@@ -416,12 +432,12 @@ static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)
}
}
- if (patch_instruction((unsigned int *)ip, PPC_INST_NOP)) {
- pr_err("Patching NOP failed.\n");
- return -EPERM;
- }
+ PATCH_INSN_OR_GOTO(ip, PPC_INST_NOP, patch_err);
return 0;
+
+patch_err:
+ return -EPERM;
}
int ftrace_make_nop(struct module *mod,
@@ -557,17 +573,18 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
}
/* Ensure branch is within 24 bits */
- if (!create_branch(ip, tramp, BRANCH_SET_LINK)) {
+ op[0] = create_branch(ip, tramp, BRANCH_SET_LINK);
+ if (!op[0]) {
pr_err("Branch out of range\n");
return -EINVAL;
}
- if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
- pr_err("REL24 out of range!\n");
- return -EINVAL;
- }
+ PATCH_INSN_OR_GOTO(ip, op[0], patch_err);
return 0;
+
+patch_err:
+ return -EPERM;
}
#else /* !CONFIG_PPC64: */
@@ -603,10 +620,12 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
pr_devel("write to %lx\n", rec->ip);
- if (patch_instruction((unsigned int *)ip, op))
- return -EPERM;
+ PATCH_INSN_OR_GOTO(ip, op, patch_err);
return 0;
+
+patch_err:
+ return -EPERM;
}
#endif /* CONFIG_PPC64 */
#endif /* CONFIG_MODULES */
@@ -650,12 +669,18 @@ static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr)
return -EINVAL;
}
- if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
- pr_err("Error patching branch to ftrace tramp!\n");
+ op = create_branch(ip, tramp, BRANCH_SET_LINK);
+ if (!op) {
+ pr_err("Branch out of range\n");
return -EINVAL;
}
+ PATCH_INSN_OR_GOTO(ip, op, patch_err);
+
return 0;
+
+patch_err:
+ return -EPERM;
}
int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
@@ -748,10 +773,8 @@ __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
/* The new target may be within range */
if (test_24bit_addr(ip, addr)) {
/* within range */
- if (patch_branch((unsigned int *)ip, addr, BRANCH_SET_LINK)) {
- pr_err("REL24 out of range!\n");
- return -EINVAL;
- }
+ op = create_branch((unsigned int *)ip, addr, BRANCH_SET_LINK);
+ PATCH_INSN_OR_GOTO(ip, op, patch_err);
return 0;
}
@@ -776,17 +799,18 @@ __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
}
/* Ensure branch is within 24 bits */
- if (!create_branch((unsigned int *)ip, tramp, BRANCH_SET_LINK)) {
+ op = create_branch((unsigned int *)ip, tramp, BRANCH_SET_LINK);
+ if (!op) {
pr_err("Branch out of range\n");
return -EINVAL;
}
- if (patch_branch((unsigned int *)ip, tramp, BRANCH_SET_LINK)) {
- pr_err("REL24 out of range!\n");
- return -EINVAL;
- }
+ PATCH_INSN_OR_GOTO(ip, op, patch_err);
return 0;
+
+patch_err:
+ return -EPERM;
}
#endif
--
2.25.1
^ permalink raw reply related
* [PATCH v2 0/2] powerpc: Enhance error handling with patch_instruction()
From: Naveen N. Rao @ 2020-04-28 14:03 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Steven Rostedt
Changes in v2:
- Change macro to use 'goto' instead of 'return'
- Rename macro to indicate use of 'goto'
- Convert more patch_instruction() uses in optprobes to use the new
macro.
- Drop 1st patch, which added error checking in do_patch_instruction()
since that is being covered in a separate patchset.
v1:
http://lkml.kernel.org/r/cover.1587654213.git.naveen.n.rao@linux.vnet.ibm.com
- Naveen
Naveen N. Rao (2):
powerpc/ftrace: Simplify error checking when patching instructions
powerpc/kprobes: Check return value of patch_instruction()
arch/powerpc/kernel/kprobes.c | 13 +++-
arch/powerpc/kernel/optprobes.c | 109 +++++++++++++++++++++--------
arch/powerpc/kernel/trace/ftrace.c | 96 +++++++++++++++----------
3 files changed, 149 insertions(+), 69 deletions(-)
base-commit: 8299da600ad05b8aa0f15ec0f5f03bd40e37d6f0
--
2.25.1
^ permalink raw reply
* [PATCH v2 2/2] powerpc/kprobes: Check return value of patch_instruction()
From: Naveen N. Rao @ 2020-04-28 14:03 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Steven Rostedt
In-Reply-To: <cover.1588082133.git.naveen.n.rao@linux.vnet.ibm.com>
patch_instruction() can fail in some scenarios. Add appropriate error
checking so that such failures are caught and logged, and suitable error
code is returned.
Fixes: d07df82c43be8 ("powerpc/kprobes: Move kprobes over to patch_instruction()")
Fixes: f3eca95638931 ("powerpc/kprobes/optprobes: Use patch_instruction()")
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
---
arch/powerpc/kernel/kprobes.c | 13 +++-
arch/powerpc/kernel/optprobes.c | 109 +++++++++++++++++++++++---------
2 files changed, 89 insertions(+), 33 deletions(-)
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 81efb605113e..9eb1cc05ddd5 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -19,6 +19,7 @@
#include <linux/extable.h>
#include <linux/kdebug.h>
#include <linux/slab.h>
+#include <linux/bug.h>
#include <asm/code-patching.h>
#include <asm/cacheflush.h>
#include <asm/sstep.h>
@@ -138,13 +139,21 @@ NOKPROBE_SYMBOL(arch_prepare_kprobe);
void arch_arm_kprobe(struct kprobe *p)
{
- patch_instruction(p->addr, BREAKPOINT_INSTRUCTION);
+ int rc = patch_instruction(p->addr, BREAKPOINT_INSTRUCTION);
+
+ if (WARN_ON(rc))
+ pr_err("Failed to patch trap at 0x%pK: %d\n",
+ (void *)p->addr, rc);
}
NOKPROBE_SYMBOL(arch_arm_kprobe);
void arch_disarm_kprobe(struct kprobe *p)
{
- patch_instruction(p->addr, p->opcode);
+ int rc = patch_instruction(p->addr, p->opcode);
+
+ if (WARN_ON(rc))
+ pr_err("Failed to remove trap at 0x%pK: %d\n",
+ (void *)p->addr, rc);
}
NOKPROBE_SYMBOL(arch_disarm_kprobe);
diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c
index 024f7aad1952..20897600db2e 100644
--- a/arch/powerpc/kernel/optprobes.c
+++ b/arch/powerpc/kernel/optprobes.c
@@ -139,52 +139,80 @@ void arch_remove_optimized_kprobe(struct optimized_kprobe *op)
}
}
+#define PATCH_INSN_OR_GOTO(addr, instr, label) \
+do { \
+ int rc = patch_instruction((unsigned int *)(addr), instr); \
+ if (rc) { \
+ pr_err("%s:%d Error patching instruction at 0x%pK (%pS): %d\n", \
+ __func__, __LINE__, \
+ (void *)(addr), (void *)(addr), rc); \
+ goto label; \
+ } \
+} while (0)
+
/*
* emulate_step() requires insn to be emulated as
* second parameter. Load register 'r4' with the
* instruction.
*/
-void patch_imm32_load_insns(unsigned int val, kprobe_opcode_t *addr)
+static int patch_imm32_load_insns(unsigned int val, kprobe_opcode_t *addr)
{
/* addis r4,0,(insn)@h */
- patch_instruction(addr, PPC_INST_ADDIS | ___PPC_RT(4) |
- ((val >> 16) & 0xffff));
+ PATCH_INSN_OR_GOTO(addr, PPC_INST_ADDIS | ___PPC_RT(4) |
+ ((val >> 16) & 0xffff),
+ patch_err);
addr++;
/* ori r4,r4,(insn)@l */
- patch_instruction(addr, PPC_INST_ORI | ___PPC_RA(4) |
- ___PPC_RS(4) | (val & 0xffff));
+ PATCH_INSN_OR_GOTO(addr, PPC_INST_ORI | ___PPC_RA(4) |
+ ___PPC_RS(4) | (val & 0xffff),
+ patch_err);
+
+ return 0;
+
+patch_err:
+ return -EFAULT;
}
/*
* Generate instructions to load provided immediate 64-bit value
* to register 'r3' and patch these instructions at 'addr'.
*/
-void patch_imm64_load_insns(unsigned long val, kprobe_opcode_t *addr)
+static int patch_imm64_load_insns(unsigned long val, kprobe_opcode_t *addr)
{
/* lis r3,(op)@highest */
- patch_instruction(addr, PPC_INST_ADDIS | ___PPC_RT(3) |
- ((val >> 48) & 0xffff));
+ PATCH_INSN_OR_GOTO(addr, PPC_INST_ADDIS | ___PPC_RT(3) |
+ ((val >> 48) & 0xffff),
+ patch_err);
addr++;
/* ori r3,r3,(op)@higher */
- patch_instruction(addr, PPC_INST_ORI | ___PPC_RA(3) |
- ___PPC_RS(3) | ((val >> 32) & 0xffff));
+ PATCH_INSN_OR_GOTO(addr, PPC_INST_ORI | ___PPC_RA(3) |
+ ___PPC_RS(3) | ((val >> 32) & 0xffff),
+ patch_err);
addr++;
/* rldicr r3,r3,32,31 */
- patch_instruction(addr, PPC_INST_RLDICR | ___PPC_RA(3) |
- ___PPC_RS(3) | __PPC_SH64(32) | __PPC_ME64(31));
+ PATCH_INSN_OR_GOTO(addr, PPC_INST_RLDICR | ___PPC_RA(3) |
+ ___PPC_RS(3) | __PPC_SH64(32) | __PPC_ME64(31),
+ patch_err);
addr++;
/* oris r3,r3,(op)@h */
- patch_instruction(addr, PPC_INST_ORIS | ___PPC_RA(3) |
- ___PPC_RS(3) | ((val >> 16) & 0xffff));
+ PATCH_INSN_OR_GOTO(addr, PPC_INST_ORIS | ___PPC_RA(3) |
+ ___PPC_RS(3) | ((val >> 16) & 0xffff),
+ patch_err);
addr++;
/* ori r3,r3,(op)@l */
- patch_instruction(addr, PPC_INST_ORI | ___PPC_RA(3) |
- ___PPC_RS(3) | (val & 0xffff));
+ PATCH_INSN_OR_GOTO(addr, PPC_INST_ORI | ___PPC_RA(3) |
+ ___PPC_RS(3) | (val & 0xffff),
+ patch_err);
+
+ return 0;
+
+patch_err:
+ return -EFAULT;
}
int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
@@ -216,30 +244,33 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
* be within 32MB on either side of the current instruction.
*/
b_offset = (unsigned long)buff - (unsigned long)p->addr;
- if (!is_offset_in_branch_range(b_offset))
+ if (!is_offset_in_branch_range(b_offset)) {
+ rc = -ERANGE;
goto error;
+ }
/* Check if the return address is also within 32MB range */
b_offset = (unsigned long)(buff + TMPL_RET_IDX) -
(unsigned long)nip;
- if (!is_offset_in_branch_range(b_offset))
+ if (!is_offset_in_branch_range(b_offset)) {
+ rc = -ERANGE;
goto error;
+ }
/* Setup template */
/* We can optimize this via patch_instruction_window later */
size = (TMPL_END_IDX * sizeof(kprobe_opcode_t)) / sizeof(int);
pr_devel("Copying template to %p, size %lu\n", buff, size);
- for (i = 0; i < size; i++) {
- rc = patch_instruction(buff + i, *(optprobe_template_entry + i));
- if (rc < 0)
- goto error;
- }
+ for (i = 0; i < size; i++)
+ PATCH_INSN_OR_GOTO(buff + i, *(optprobe_template_entry + i),
+ patch_err);
/*
* Fixup the template with instructions to:
* 1. load the address of the actual probepoint
*/
- patch_imm64_load_insns((unsigned long)op, buff + TMPL_OP_IDX);
+ if (patch_imm64_load_insns((unsigned long)op, buff + TMPL_OP_IDX))
+ goto patch_err;
/*
* 2. branch to optimized_callback() and emulate_step()
@@ -248,6 +279,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
emulate_step_addr = (kprobe_opcode_t *)ppc_kallsyms_lookup_name("emulate_step");
if (!op_callback_addr || !emulate_step_addr) {
WARN(1, "Unable to lookup optimized_callback()/emulate_step()\n");
+ rc = -ERANGE;
goto error;
}
@@ -259,21 +291,29 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
(unsigned long)emulate_step_addr,
BRANCH_SET_LINK);
- if (!branch_op_callback || !branch_emulate_step)
+ if (!branch_op_callback || !branch_emulate_step) {
+ rc = -ERANGE;
goto error;
+ }
+
+ PATCH_INSN_OR_GOTO(buff + TMPL_CALL_HDLR_IDX, branch_op_callback,
+ patch_err);
- patch_instruction(buff + TMPL_CALL_HDLR_IDX, branch_op_callback);
- patch_instruction(buff + TMPL_EMULATE_IDX, branch_emulate_step);
+ PATCH_INSN_OR_GOTO(buff + TMPL_EMULATE_IDX, branch_emulate_step,
+ patch_err);
/*
* 3. load instruction to be emulated into relevant register, and
*/
- patch_imm32_load_insns(*p->ainsn.insn, buff + TMPL_INSN_IDX);
+ if (patch_imm32_load_insns(*p->ainsn.insn, buff + TMPL_INSN_IDX))
+ goto patch_err;
/*
* 4. branch back from trampoline
*/
- patch_branch(buff + TMPL_RET_IDX, (unsigned long)nip, 0);
+ PATCH_INSN_OR_GOTO(buff + TMPL_RET_IDX,
+ create_branch(buff + TMPL_RET_IDX, (unsigned long)nip, 0),
+ patch_err);
flush_icache_range((unsigned long)buff,
(unsigned long)(&buff[TMPL_END_IDX]));
@@ -282,9 +322,11 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
return 0;
+patch_err:
+ rc = -EFAULT;
error:
free_ppc_optinsn_slot(buff, 0);
- return -ERANGE;
+ return rc;
}
@@ -307,6 +349,7 @@ void arch_optimize_kprobes(struct list_head *oplist)
{
struct optimized_kprobe *op;
struct optimized_kprobe *tmp;
+ int rc;
list_for_each_entry_safe(op, tmp, oplist, list) {
/*
@@ -315,9 +358,13 @@ void arch_optimize_kprobes(struct list_head *oplist)
*/
memcpy(op->optinsn.copied_insn, op->kp.addr,
RELATIVEJUMP_SIZE);
- patch_instruction(op->kp.addr,
+ rc = patch_instruction(op->kp.addr,
create_branch((unsigned int *)op->kp.addr,
(unsigned long)op->optinsn.insn, 0));
+ if (rc)
+ pr_err("%s:%d: Error patching instruction at 0x%pK: %d\n",
+ __func__, __LINE__,
+ (void *)(op->kp.addr), rc);
list_del_init(&op->list);
}
}
--
2.25.1
^ permalink raw reply related
* Re: [PATCH v8 8/8] powerpc/vdso: Provide __kernel_clock_gettime64() on vdso32
From: Christophe Leroy @ 2020-04-28 15:03 UTC (permalink / raw)
To: Russell Currey; +Cc: linuxppc-dev
In-Reply-To: <e78344d3fcc1d33bfb1782e430b7f0529f6c612f.1588079622.git.christophe.leroy@c-s.fr>
Hi,
On 04/28/2020 01:16 PM, Christophe Leroy wrote:
> Provides __kernel_clock_gettime64() on vdso32. This is the
> 64 bits version of __kernel_clock_gettime() which is
> y2038 compliant.
>
> Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Why does snowpatch still report upstream failure ? This is fixed in
latest powerpc/merge which is
commit d9e4eabb775e1ba56d83bd4047de2413a21f87ce
Merge: 54dc28ff5e0b 51184ae37e05
Author: Michael Ellerman <mpe@ellerman.id.au>
Date: Tue Apr 28 09:01:47 2020 +1000
Automatic merge of branches 'master', 'next' and 'fixes' into merge
Looks like snowpatch is still using
commit 54dc28ff5e0b3585224d49a31b53e030342ca5c3
Merge: 5d23fec1ac1d b2768df24ec4
Author: Michael Ellerman <mpe@ellerman.id.au>
Date: Sun Apr 26 09:44:18 2020 +1000
Automatic merge of branches 'master', 'next' and 'fixes' into merge
Why ?
Christophe
> ---
> arch/powerpc/kernel/vdso32/gettimeofday.S | 9 +++++++++
> arch/powerpc/kernel/vdso32/vdso32.lds.S | 1 +
> arch/powerpc/kernel/vdso32/vgettimeofday.c | 6 ++++++
> 3 files changed, 16 insertions(+)
>
> diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
> index fd7b01c51281..a6e29f880e0e 100644
> --- a/arch/powerpc/kernel/vdso32/gettimeofday.S
> +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
> @@ -35,6 +35,15 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
> cvdso_call __c_kernel_clock_gettime
> V_FUNCTION_END(__kernel_clock_gettime)
>
> +/*
> + * Exact prototype of clock_gettime64()
> + *
> + * int __kernel_clock_gettime64(clockid_t clock_id, struct __timespec64 *ts);
> + *
> + */
> +V_FUNCTION_BEGIN(__kernel_clock_gettime64)
> + cvdso_call __c_kernel_clock_gettime64
> +V_FUNCTION_END(__kernel_clock_gettime64)
>
> /*
> * Exact prototype of clock_getres()
> diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
> index 6cf729612268..05b462143238 100644
> --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
> +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
> @@ -144,6 +144,7 @@ VERSION
> #ifndef CONFIG_PPC_BOOK3S_601
> __kernel_gettimeofday;
> __kernel_clock_gettime;
> + __kernel_clock_gettime64;
> __kernel_clock_getres;
> __kernel_time;
> __kernel_get_tbfreq;
> diff --git a/arch/powerpc/kernel/vdso32/vgettimeofday.c b/arch/powerpc/kernel/vdso32/vgettimeofday.c
> index 0b9ab4c22ef2..f7f71fecf4ed 100644
> --- a/arch/powerpc/kernel/vdso32/vgettimeofday.c
> +++ b/arch/powerpc/kernel/vdso32/vgettimeofday.c
> @@ -11,6 +11,12 @@ int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
> return __cvdso_clock_gettime32_data(vd, clock, ts);
> }
>
> +int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts,
> + const struct vdso_data *vd)
> +{
> + return __cvdso_clock_gettime_data(vd, clock, ts);
> +}
> +
> int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
> const struct vdso_data *vd)
> {
^ permalink raw reply
* Re: [PATCH net] ibmvnic: Fall back to 16 H_SEND_SUB_CRQ_INDIRECT entries with old FW
From: Thomas Falcon @ 2020-04-28 15:35 UTC (permalink / raw)
To: Juliet Kim, netdev; +Cc: linuxppc-dev
In-Reply-To: <20200427173343.16626-1-julietk@linux.vnet.ibm.com>
On 4/27/20 12:33 PM, Juliet Kim wrote:
> The maximum entries for H_SEND_SUB_CRQ_INDIRECT has increased on
> some platforms from 16 to 128. If Live Partition Mobility is used
> to migrate a running OS image from a newer source platform to an
> older target platform, then H_SEND_SUB_CRQ_INDIRECT will fail with
> H_PARAMETER if 128 entries are queued.
>
> Fix this by falling back to 16 entries if H_PARAMETER is returned
> from the hcall().
Thanks for the submission, but I am having a hard time believing that
this is what is happening since the driver does not support sending
multiple frames per hypervisor call at this time. Even if it were the
case, this approach would omit frame data needed by the VF, so the
second attempt may still fail. Are there system logs available that show
the driver is attempting to send transmissions with greater than 16
descriptors?
Thanks,
Tom
>
> Signed-off-by: Juliet Kim <julietk@linux.vnet.ibm.com>
> ---
> drivers/net/ethernet/ibm/ibmvnic.c | 11 +++++++++++
> 1 file changed, 11 insertions(+)
>
> diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
> index 4bd33245bad6..b66c2f26a427 100644
> --- a/drivers/net/ethernet/ibm/ibmvnic.c
> +++ b/drivers/net/ethernet/ibm/ibmvnic.c
> @@ -1656,6 +1656,17 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
> lpar_rc = send_subcrq_indirect(adapter, handle_array[queue_num],
> (u64)tx_buff->indir_dma,
> (u64)num_entries);
> +
> + /* Old firmware accepts max 16 num_entries */
> + if (lpar_rc == H_PARAMETER && num_entries > 16) {
> + tx_crq.v1.n_crq_elem = 16;
> + tx_buff->num_entries = 16;
> + lpar_rc = send_subcrq_indirect(adapter,
> + handle_array[queue_num],
> + (u64)tx_buff->indir_dma,
> + 16);
> + }
> +
> dma_unmap_single(dev, tx_buff->indir_dma,
> sizeof(tx_buff->indir_arr), DMA_TO_DEVICE);
> } else {
^ permalink raw reply
* Re: [RFC PATCH] powerpc/spufs: fix copy_to_user while atomic
From: Arnd Bergmann @ 2020-04-28 16:00 UTC (permalink / raw)
To: Jeremy Kerr
Cc: linuxppc-dev, linux-kernel@vger.kernel.org, Eric W . Biederman,
Linux FS-devel Mailing List, Andrew Morton, Linus Torvalds,
Christoph Hellwig, Alexander Viro
In-Reply-To: <20200428120207.15728-1-jk@ozlabs.org>
On Tue, Apr 28, 2020 at 2:05 PM Jeremy Kerr <jk@ozlabs.org> wrote:
>
> 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>
> ---
Thanks for fixing this!
I wonder how far it should be backported, given that this has been broken for
14 years now.
Fixes: bf1ab978be23 ("[POWERPC] coredump: Add SPU elf notes to coredump.")
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
^ permalink raw reply
* Re: [PATCH v8 8/8] powerpc/vdso: Provide __kernel_clock_gettime64() on vdso32
From: Arnd Bergmann @ 2020-04-28 16:05 UTC (permalink / raw)
To: Christophe Leroy
Cc: Nathan Lynch, linux-arch, linux-kernel@vger.kernel.org,
Paul Mackerras, Andy Lutomirski, Thomas Gleixner,
Vincenzo Frascino, linuxppc-dev
In-Reply-To: <e78344d3fcc1d33bfb1782e430b7f0529f6c612f.1588079622.git.christophe.leroy@c-s.fr>
On Tue, Apr 28, 2020 at 3:16 PM Christophe Leroy
<christophe.leroy@c-s.fr> wrote:
>
> Provides __kernel_clock_gettime64() on vdso32. This is the
> 64 bits version of __kernel_clock_gettime() which is
> y2038 compliant.
>
> Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Looks good to me
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
There was a bug on ARM for the corresponding function, so far it is unclear
if this was a problem related to particular hardware, the 32-bit kernel code,
or the common implementation of clock_gettime64 in the vdso library,
see https://github.com/richfelker/musl-cross-make/issues/96
Just to be sure that powerpc is not affected by the same issue, can you
confirm that repeatedly calling clock_gettime64 on powerpc32, alternating
between vdso and syscall, results in monotically increasing times?
Arnd
^ permalink raw reply
* Re: [RFC PATCH v2 7/7] powerpc/selftest: reuse ppc-opcode macros to avoid redundancy
From: Naveen N. Rao @ 2020-04-28 16:14 UTC (permalink / raw)
To: Balamuruhan S, mpe
Cc: ravi.bangoria, jniethe5, paulus, sandipan, linuxppc-dev
In-Reply-To: <20200424070853.443969-8-bala24@linux.ibm.com>
Balamuruhan S wrote:
> Avoid redefining macros to encode ppc instructions instead reuse it from
> ppc-opcode.h, Makefile changes are necessary to compile memcmp_64.S with
> __ASSEMBLY__ defined from selftests.
>
> Signed-off-by: Balamuruhan S <bala24@linux.ibm.com>
> ---
> .../selftests/powerpc/stringloops/Makefile | 34 ++++++++++++++----
> .../powerpc/stringloops/asm/asm-const.h | 1 +
> .../powerpc/stringloops/asm/ppc-opcode.h | 36 +------------------
> 3 files changed, 29 insertions(+), 42 deletions(-)
> create mode 120000 tools/testing/selftests/powerpc/stringloops/asm/asm-const.h
> mode change 100644 => 120000 tools/testing/selftests/powerpc/stringloops/asm/ppc-opcode.h
>
> diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile
> index 7fc0623d85c3..efe76c5a5b94 100644
> --- a/tools/testing/selftests/powerpc/stringloops/Makefile
> +++ b/tools/testing/selftests/powerpc/stringloops/Makefile
> @@ -1,26 +1,44 @@
> # SPDX-License-Identifier: GPL-2.0
> # The loops are all 64-bit code
> -CFLAGS += -I$(CURDIR)
> +GIT_VERSION = $(shell git describe --always --long --dirty || echo "unknown")
> +CFLAGS += -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) -I$(CURDIR)/../include
I'm not sure why there are some extra flags added here. Not sure if it
is required for this change, or if they are separate changes. Trying to
build this from 'tools/testing/selftests/powerpc/' with 'make
stringloops' shows slightly different compile flags being used.
- Naveen
^ permalink raw reply
* Re: [RFC PATCH v2 0/7] consolidate PowerPC instruction encoding macros
From: Naveen N. Rao @ 2020-04-28 16:15 UTC (permalink / raw)
To: Balamuruhan S, mpe
Cc: ravi.bangoria, jniethe5, paulus, sandipan, linuxppc-dev
In-Reply-To: <20200424070853.443969-1-bala24@linux.ibm.com>
Balamuruhan S wrote:
> ppc-opcode.h have base instruction encoding wrapped with stringify_in_c()
> for raw encoding to have compatibility. But there are redundant macros for
> base instruction encodings in bpf, instruction emulation test infrastructure
> and powerpc selftests.
>
> Currently PPC_INST_* macros are used for encoding instruction opcode and PPC_*
> for raw instuction encoding, this rfc patchset introduces PPC_RAW_* macros for
> base instruction encoding and reuse it from elsewhere. With this change we can
> avoid redundant macro definitions in multiple files and start adding new
> instructions in ppc-opcode.h in future.
>
> Changes in v2:
> -------------
> Fix review comments/suggestions from Naveen and Michael Ellerman,
>
> * Rename PPC_ENCODE_* to PPC_RAW_* for base instruction encoding macros.
> * Split the patches that does mass renaming and make them simpler that just
> adds new macros.
> * Keep the patch to update all the existing names later (patch 6).
> * Lot of PPC_INST_* macros are used only in ppc-opcode.h for PPC_* macros,
> fold PPC_INST_* encoding into PPC_RAW_* to avoid using them accidentally.
> * Fixed clipped macros that was due to a typo/copy-paste
> * Consolidated all the instruction encoding macros from bpf_jit.h to
> ppc-opcode.h
> * squashed patch that removes the duplicate macro PPC_MR() in bpf_jit.h
> * merge few changes in bpf_jit files from patch 2 into patch 3
> * few fixes in powerpc selftest stringloops Makefile
> * build tested for ppc64le_defconfig, ppc64e_defconfig and pmac32_defconfig
> * Rebased on next branch of linuxppc tree
>
> Testing:
> -------
> * Tested it by compiling vmlinux and comparing objdump of it with and without
> the patchset and observed that it remains same,
>
> # diff vmlinux_objdump vmlinux_rfc_objdump
> 2c2
> < vmlinux: file format elf64-powerpcle
> ---
> > vmlinux_rfc: file format elf64-powerpcle
>
> * Tested building it with this changes for Fedora30 config, booted VM
> with powerpc next and powerpc next + patchset to run powerpc selftest and
> ftrace selftest. There were couple of failures that were common and
> patchset did not introduce any new failures.
>
> ftrace selftest:
> ---------------
> # # of passed: 96
> # # of failed: 1
> # # of unresolved: 7
> # # of untested: 0
> # # of unsupported: 1
> # # of xfailed: 1
> # # of undefined(test bug): 0
> not ok 1 selftests: ftrace: ftracetest # exit=1
>
> powerpc selftest:
> ----------------
> not ok 7 selftests: powerpc/dscr: dscr_sysfs_thread_test # exit=1
> not ok 20 selftests: powerpc/pmu/ebb: lost_exception_test # TIMEOUT
> not ok 2 selftests: powerpc/security: spectre_v2 # exit=1
>
> Thanks to Naveen, Sandipan and Michael on overall suggestions/improvements.
>
> I would request for review and suggestions to make it better.
>
> v1: https://lists.ozlabs.org/pipermail/linuxppc-dev/2020-March/206494.html
>
> Balamuruhan S (7):
> powerpc/ppc-opcode: introduce PPC_RAW_* macros for base instruction
> encoding
> powerpc/ppc-opcode: move ppc instruction encoding from
> test_emulate_step
> powerpc/bpf_jit: reuse instruction macros from ppc-opcode.h
> powerpc/ppc-opcode: consolidate powerpc instructions from bpf_jit.h
> powerpc/ppc-opcode: reuse raw instruction macros to stringify
> powerpc/ppc-opcode: fold PPC_INST_* macros into PPC_RAW_* macros
> powerpc/selftest: reuse ppc-opcode macros to avoid redundancy
>
> arch/powerpc/include/asm/ppc-opcode.h | 706 +++++++++++-------
> arch/powerpc/lib/test_emulate_step.c | 155 ++--
> arch/powerpc/net/bpf_jit.h | 184 +----
> arch/powerpc/net/bpf_jit32.h | 34 +-
> arch/powerpc/net/bpf_jit64.h | 16 +-
> arch/powerpc/net/bpf_jit_comp.c | 134 ++--
> arch/powerpc/net/bpf_jit_comp64.c | 298 ++++----
> .../selftests/powerpc/stringloops/Makefile | 34 +-
> .../powerpc/stringloops/asm/asm-const.h | 1 +
> .../powerpc/stringloops/asm/ppc-opcode.h | 36 +-
> 10 files changed, 762 insertions(+), 836 deletions(-)
> create mode 120000 tools/testing/selftests/powerpc/stringloops/asm/asm-const.h
> mode change 100644 => 120000 tools/testing/selftests/powerpc/stringloops/asm/ppc-opcode.h
This LGTM. Except the last patch:
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Thanks!
- Naveen
^ permalink raw reply
* Re: [RFC PATCH v2 4/7] powerpc/ppc-opcode: consolidate powerpc instructions from bpf_jit.h
From: Naveen N. Rao @ 2020-04-28 16:19 UTC (permalink / raw)
To: Balamuruhan S, mpe
Cc: ravi.bangoria, jniethe5, paulus, sandipan, linuxppc-dev
In-Reply-To: <20200424070853.443969-5-bala24@linux.ibm.com>
Balamuruhan S wrote:
> move macro definitions of powerpc instructions from bpf_jit.h to ppc-opcode.h
> and adopt the users of the macros accordingly. `PPC_MR()` is defined twice in
> bpf_jit.h, remove the duplicate one.
>
> Signed-off-by: Balamuruhan S <bala24@linux.ibm.com>
> ---
> arch/powerpc/include/asm/ppc-opcode.h | 139 +++++++++++++
> arch/powerpc/net/bpf_jit.h | 166 ++-------------
> arch/powerpc/net/bpf_jit32.h | 24 +--
> arch/powerpc/net/bpf_jit64.h | 12 +-
> arch/powerpc/net/bpf_jit_comp.c | 132 ++++++------
> arch/powerpc/net/bpf_jit_comp64.c | 278 +++++++++++++-------------
> 6 files changed, 378 insertions(+), 373 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
> index 2ae0afc5c2bb..6b9a891884be 100644
> --- a/arch/powerpc/include/asm/ppc-opcode.h
> +++ b/arch/powerpc/include/asm/ppc-opcode.h
> @@ -79,6 +79,16 @@
> #define IMM_L(i) ((uintptr_t)(i) & 0xffff)
> #define IMM_DS(i) ((uintptr_t)(i) & 0xfffc)
>
> +/*
> + * 16-bit immediate helper macros: HA() is for use with sign-extending instrs
> + * (e.g. LD, ADDI). If the bottom 16 bits is "-ve", add another bit into the
> + * top half to negate the effect (i.e. 0xffff + 1 = 0x(1)0000).
> + */
> +#define IMM_H(i) ((uintptr_t)(i)>>16)
> +#define IMM_HA(i) (((uintptr_t)(i)>>16) + \
> + (((uintptr_t)(i) & 0x8000) >> 15))
> +
Not needed for this patch series, but at some point, we should move over
to using the PPC_LO(), PPC_HI() and PPC_HA() macros that are defined
later in this file.
- Naveen
^ permalink raw reply
* Re: [RFC PATCH] powerpc/spufs: fix copy_to_user while atomic
From: Christoph Hellwig @ 2020-04-28 17:11 UTC (permalink / raw)
To: Jeremy Kerr
Cc: Arnd Bergmann, linuxppc-dev, linux-kernel, Eric W . Biederman,
linux-fsdevel, Andrew Morton, Linus Torvalds, Christoph Hellwig,
Alexander Viro
In-Reply-To: <20200428120207.15728-1-jk@ozlabs.org>
FYI, these little hunks reduce the difference to my version, maybe
you can fold them in?
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index c62d77ddaf7d3..1861436a6091d 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -2107,7 +2107,6 @@ static const struct file_operations spufs_wbox_info_fops = {
static void ___spufs_dma_info_read(struct spu_context *ctx,
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;
@@ -2116,8 +2115,8 @@ static void ___spufs_dma_info_read(struct spu_context *ctx,
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];
- spuqp = &ctx->csa.priv2.spuq[i];
+ struct mfc_cq_sr *qp = &info->dma_info_command_data[i];
+ struct mfc_cq_sr *qp, *spuqp = &ctx->csa.priv2.spuq[i];
qp->mfc_cq_data0_RW = spuqp->mfc_cq_data0_RW;
qp->mfc_cq_data1_RW = spuqp->mfc_cq_data1_RW;
@@ -2166,7 +2165,7 @@ static const struct file_operations spufs_dma_info_fops = {
};
static void ___spufs_proxydma_info_read(struct spu_context *ctx,
- struct spu_proxydma_info *info)
+ struct spu_proxydma_info *info)
{
int i;
^ permalink raw reply related
* Re: [PATCH v3 00/29] Convert files to ReST - part 2
From: Jonathan Corbet @ 2020-04-28 19:01 UTC (permalink / raw)
To: Mauro Carvalho Chehab
Cc: Linux Doc Mailing List, linux-usb, linux-kernel, codalist,
linux-xfs, linux-cachefs, linux-fsdevel, linuxppc-dev
In-Reply-To: <cover.1588021877.git.mchehab+huawei@kernel.org>
On Mon, 27 Apr 2020 23:16:52 +0200
Mauro Carvalho Chehab <mchehab+huawei@kernel.org> wrote:
> This is the second part of a series I wrote sometime ago where I manually
> convert lots of files to be properly parsed by Sphinx as ReST files.
>
> As it touches on lot of stuff, this series is based on today's linux-next,
> at tag next-20190617.
>
> The first version of this series had 57 patches. The first part with 28 patches
> were already merged. Right now, there are still ~76 patches pending applying
> (including this series), and that's because I opted to do ~1 patch per converted
> directory.
>
> That sounds too much to be send on a single round. So, I'm opting to split
> it on 3 parts for the conversion, plus a final patch adding orphaned books
> to existing ones.
>
> Those patches should probably be good to be merged either by subsystem
> maintainers or via the docs tree.
So I'm happy to merge this set, but there is one thing that worries me a
bit...
> fs/cachefiles/Kconfig | 4 +-
> fs/coda/Kconfig | 2 +-
> fs/configfs/inode.c | 2 +-
> fs/configfs/item.c | 2 +-
> fs/fscache/Kconfig | 8 +-
> fs/fscache/cache.c | 8 +-
> fs/fscache/cookie.c | 2 +-
> fs/fscache/object.c | 4 +-
> fs/fscache/operation.c | 2 +-
> fs/locks.c | 2 +-
> include/linux/configfs.h | 2 +-
> include/linux/fs_context.h | 2 +-
> include/linux/fscache-cache.h | 4 +-
> include/linux/fscache.h | 42 +-
> include/linux/lsm_hooks.h | 2 +-
I'd feel a bit better if I could get an ack or two from filesystem folks
before I venture that far out of my own yard...what say you all?
Thanks,
jon
^ permalink raw reply
* [PATCH] fixup! signal: factor copy_siginfo_to_external32 from copy_siginfo_to_user32
From: Arnd Bergmann @ 2020-04-28 19:56 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Arnd Bergmann, Jeremy Kerr, linux-kernel, Eric W . Biederman,
linux-fsdevel, Andrew Morton, linuxppc-dev, Alexander Viro
In-Reply-To: <20200428074827.GA19846@lst.de>
I think I found a way to improve the x32 handling:
This is a simplification over Christoph's "[PATCH 2/7] signal: factor
copy_siginfo_to_external32 from copy_siginfo_to_user32", reducing the
x32 specifics in the common code to a single #ifdef/#endif check, in
order to keep it more readable for everyone else.
Christoph, if you like it, please fold into your patch.
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jeremy Kerr <jk@ozlabs.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
arch/x86/include/asm/compat.h | 10 ++++++++++
arch/x86/kernel/signal.c | 23 +++++++++++++++++++++++
kernel/signal.c | 15 ++-------------
3 files changed, 35 insertions(+), 13 deletions(-)
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 52e9f3480f69..9341ea3da757 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -214,7 +214,17 @@ static inline bool in_compat_syscall(void)
#endif
struct compat_siginfo;
+#ifdef CONFIG_X86_X32_ABI
int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
const kernel_siginfo_t *from, bool x32_ABI);
+#else
+int copy_siginfo_to_user32(struct compat_siginfo __user *to,
+ const kernel_siginfo_t *from);
+static inline int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
+ const kernel_siginfo_t *from, bool x32_ABI)
+{
+ return copy_siginfo_to_user32(to, from);
+}
+#endif
#endif /* _ASM_X86_COMPAT_H */
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 83b74fb38c8f..0e166571d28b 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -511,6 +511,29 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
}
#endif /* CONFIG_X86_32 */
+#ifdef CONFIG_X86_X32_ABI
+int copy_siginfo_to_user32(struct compat_siginfo __user *to,
+ const struct kernel_siginfo *from)
+{
+ return __copy_siginfo_to_user32(to, from, in_x32_syscall());
+}
+
+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);
+ if (x32_ABI && from->si_signo == SIGCHLD) {
+ new._sifields._sigchld_x32._utime = from->si_utime;
+ new._sifields._sigchld_x32._stime = from->si_stime;
+ }
+ if (copy_to_user(to, &new, sizeof(struct compat_siginfo)))
+ return -EFAULT;
+ return 0;
+}
+#endif
+
static int x32_setup_rt_frame(struct ksignal *ksig,
compat_sigset_t *set,
struct pt_regs *regs)
diff --git a/kernel/signal.c b/kernel/signal.c
index 1a81602050b4..935facca4860 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3318,29 +3318,18 @@ void copy_siginfo_to_external32(struct compat_siginfo *to,
}
}
+#ifndef CONFIG_X86_X32_ABI
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());
-}
-int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
- const struct kernel_siginfo *from, bool x32_ABI)
-#endif
{
struct compat_siginfo new;
copy_siginfo_to_external32(&new, from);
-#ifdef CONFIG_X86_X32_ABI
- if (x32_ABI && from->si_signo == SIGCHLD) {
- new._sifields._sigchld_x32._utime = from->si_utime;
- new._sifields._sigchld_x32._stime = from->si_stime;
- }
-#endif
if (copy_to_user(to, &new, sizeof(struct compat_siginfo)))
return -EFAULT;
return 0;
}
+#endif
static int post_copy_siginfo_from_user32(kernel_siginfo_t *to,
const struct compat_siginfo *from)
--
2.26.0
^ permalink raw reply related
* [PATCH v4 1/4] hugetlbfs: add arch_hugetlb_valid_size
From: Mike Kravetz @ 2020-04-28 20:56 UTC (permalink / raw)
To: linux-mm, linux-kernel, linux-arm-kernel, linuxppc-dev,
linux-riscv, linux-s390, sparclinux, linux-doc
Cc: Dave Hansen, Heiko Carstens, Peter Xu, Paul Mackerras,
Will Deacon, Mina Almasry, Jonathan Corbet, Christian Borntraeger,
Ingo Molnar, Catalin Marinas, Longpeng, Albert Ou, Vasily Gorbik,
Paul Walmsley, Thomas Gleixner, Gerald Schaefer,
Nitesh Narayan Lal, Randy Dunlap, Palmer Dabbelt, Andrew Morton,
David S . Miller, Mike Kravetz
In-Reply-To: <20200428205614.246260-1-mike.kravetz@oracle.com>
The architecture independent routine hugetlb_default_setup sets up
the default huge pages size. It has no way to verify if the passed
value is valid, so it accepts it and attempts to validate at a later
time. This requires undocumented cooperation between the arch specific
and arch independent code.
For architectures that support more than one huge page size, provide
a routine arch_hugetlb_valid_size to validate a huge page size.
hugetlb_default_setup can use this to validate passed values.
arch_hugetlb_valid_size will also be used in a subsequent patch to
move processing of the "hugepagesz=" in arch specific code to a common
routine in arch independent code.
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> [s390]
Acked-by: Will Deacon <will@kernel.org>
---
arch/arm64/mm/hugetlbpage.c | 17 +++++++++++++----
arch/powerpc/mm/hugetlbpage.c | 20 +++++++++++++-------
arch/riscv/mm/hugetlbpage.c | 26 +++++++++++++++++---------
arch/s390/mm/hugetlbpage.c | 16 ++++++++++++----
arch/sparc/mm/init_64.c | 24 ++++++++++++++++--------
arch/x86/mm/hugetlbpage.c | 17 +++++++++++++----
include/linux/hugetlb.h | 1 +
mm/hugetlb.c | 21 ++++++++++++++++++---
8 files changed, 103 insertions(+), 39 deletions(-)
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index bbeb6a5a6ba6..069b96ee2aec 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -462,17 +462,26 @@ static int __init hugetlbpage_init(void)
}
arch_initcall(hugetlbpage_init);
-static __init int setup_hugepagesz(char *opt)
+bool __init arch_hugetlb_valid_size(unsigned long size)
{
- unsigned long ps = memparse(opt, &opt);
-
- switch (ps) {
+ switch (size) {
#ifdef CONFIG_ARM64_4K_PAGES
case PUD_SIZE:
#endif
case CONT_PMD_SIZE:
case PMD_SIZE:
case CONT_PTE_SIZE:
+ return true;
+ }
+
+ return false;
+}
+
+static __init int setup_hugepagesz(char *opt)
+{
+ unsigned long ps = memparse(opt, &opt);
+
+ if (arch_hugetlb_valid_size(ps)) {
add_huge_page_size(ps);
return 1;
}
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 33b3461d91e8..de54d2a37830 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -558,7 +558,7 @@ unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
return vma_kernel_pagesize(vma);
}
-static int __init add_huge_page_size(unsigned long long size)
+bool __init arch_hugetlb_valid_size(unsigned long size)
{
int shift = __ffs(size);
int mmu_psize;
@@ -566,20 +566,26 @@ static int __init add_huge_page_size(unsigned long long size)
/* Check that it is a page size supported by the hardware and
* that it fits within pagetable and slice limits. */
if (size <= PAGE_SIZE || !is_power_of_2(size))
- return -EINVAL;
+ return false;
mmu_psize = check_and_get_huge_psize(shift);
if (mmu_psize < 0)
- return -EINVAL;
+ return false;
BUG_ON(mmu_psize_defs[mmu_psize].shift != shift);
- /* Return if huge page size has already been setup */
- if (size_to_hstate(size))
- return 0;
+ return true;
+}
- hugetlb_add_hstate(shift - PAGE_SHIFT);
+static int __init add_huge_page_size(unsigned long long size)
+{
+ int shift = __ffs(size);
+
+ if (!arch_hugetlb_valid_size((unsigned long)size))
+ return -EINVAL;
+ if (!size_to_hstate(size))
+ hugetlb_add_hstate(shift - PAGE_SHIFT);
return 0;
}
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index a6189ed36c5f..da1f516bc451 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -12,21 +12,29 @@ int pmd_huge(pmd_t pmd)
return pmd_leaf(pmd);
}
+bool __init arch_hugetlb_valid_size(unsigned long size)
+{
+ if (size == HPAGE_SIZE)
+ return true;
+ else if (IS_ENABLED(CONFIG_64BIT) && size == PUD_SIZE)
+ return true;
+ else
+ return false;
+}
+
static __init int setup_hugepagesz(char *opt)
{
unsigned long ps = memparse(opt, &opt);
- if (ps == HPAGE_SIZE) {
- hugetlb_add_hstate(HPAGE_SHIFT - PAGE_SHIFT);
- } else if (IS_ENABLED(CONFIG_64BIT) && ps == PUD_SIZE) {
- hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
- } else {
- hugetlb_bad_size();
- pr_err("hugepagesz: Unsupported page size %lu M\n", ps >> 20);
- return 0;
+ if (arch_hugetlb_valid_size(ps)) {
+ hugetlb_add_hstate(ilog2(ps) - PAGE_SHIFT);
+ return 1;
}
- return 1;
+ hugetlb_bad_size();
+ pr_err("hugepagesz: Unsupported page size %lu M\n", ps >> 20);
+ return 0;
+
}
__setup("hugepagesz=", setup_hugepagesz);
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index f01daddcbc5e..ac25b207624c 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -251,16 +251,24 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address,
return pud_page(*pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
}
+bool __init arch_hugetlb_valid_size(unsigned long size)
+{
+ if (MACHINE_HAS_EDAT1 && size == PMD_SIZE)
+ return true;
+ else if (MACHINE_HAS_EDAT2 && size == PUD_SIZE)
+ return true;
+ else
+ return false;
+}
+
static __init int setup_hugepagesz(char *opt)
{
unsigned long size;
char *string = opt;
size = memparse(opt, &opt);
- if (MACHINE_HAS_EDAT1 && size == PMD_SIZE) {
- hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
- } else if (MACHINE_HAS_EDAT2 && size == PUD_SIZE) {
- hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+ if (arch_hugetlb_valid_size(size)) {
+ hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT);
} else {
hugetlb_bad_size();
pr_err("hugepagesz= specifies an unsupported page size %s\n",
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 1cf0d666dea3..2bfe8e22b706 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -360,16 +360,11 @@ static void __init pud_huge_patch(void)
__asm__ __volatile__("flush %0" : : "r" (addr));
}
-static int __init setup_hugepagesz(char *string)
+bool __init arch_hugetlb_valid_size(unsigned long size)
{
- unsigned long long hugepage_size;
- unsigned int hugepage_shift;
+ unsigned int hugepage_shift = ilog2(size);
unsigned short hv_pgsz_idx;
unsigned int hv_pgsz_mask;
- int rc = 0;
-
- hugepage_size = memparse(string, &string);
- hugepage_shift = ilog2(hugepage_size);
switch (hugepage_shift) {
case HPAGE_16GB_SHIFT:
@@ -397,7 +392,20 @@ static int __init setup_hugepagesz(char *string)
hv_pgsz_mask = 0;
}
- if ((hv_pgsz_mask & cpu_pgsz_mask) == 0U) {
+ if ((hv_pgsz_mask & cpu_pgsz_mask) == 0U)
+ return false;
+
+ return true;
+}
+
+static int __init setup_hugepagesz(char *string)
+{
+ unsigned long long hugepage_size;
+ int rc = 0;
+
+ hugepage_size = memparse(string, &string);
+
+ if (!arch_hugetlb_valid_size((unsigned long)hugepage_size)) {
hugetlb_bad_size();
pr_err("hugepagesz=%llu not supported by MMU.\n",
hugepage_size);
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 5bfd5aef5378..1c4372bfe782 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -181,13 +181,22 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
#endif /* CONFIG_HUGETLB_PAGE */
#ifdef CONFIG_X86_64
+bool __init arch_hugetlb_valid_size(unsigned long size)
+{
+ if (size == PMD_SIZE)
+ return true;
+ else if (size == PUD_SIZE && boot_cpu_has(X86_FEATURE_GBPAGES))
+ return true;
+ else
+ return false;
+}
+
static __init int setup_hugepagesz(char *opt)
{
unsigned long ps = memparse(opt, &opt);
- if (ps == PMD_SIZE) {
- hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
- } else if (ps == PUD_SIZE && boot_cpu_has(X86_FEATURE_GBPAGES)) {
- hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+
+ if (arch_hugetlb_valid_size(ps)) {
+ hugetlb_add_hstate(ilog2(ps) - PAGE_SHIFT);
} else {
hugetlb_bad_size();
printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n",
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 43a1cef8f0f1..2eb15f5ab01e 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -521,6 +521,7 @@ int __init alloc_bootmem_huge_page(struct hstate *h);
void __init hugetlb_bad_size(void);
void __init hugetlb_add_hstate(unsigned order);
+bool __init arch_hugetlb_valid_size(unsigned long size);
struct hstate *size_to_hstate(unsigned long size);
#ifndef HUGE_MAX_HSTATE
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index bcabbe02192b..63ca4241ea87 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3256,6 +3256,12 @@ static int __init hugetlb_init(void)
}
subsys_initcall(hugetlb_init);
+/* Overwritten by architectures with more huge page sizes */
+bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size)
+{
+ return size == HPAGE_SIZE;
+}
+
/* Should be called on processing a hugepagesz=... option */
void __init hugetlb_bad_size(void)
{
@@ -3331,12 +3337,21 @@ static int __init hugetlb_nrpages_setup(char *s)
}
__setup("hugepages=", hugetlb_nrpages_setup);
-static int __init hugetlb_default_setup(char *s)
+static int __init default_hugepagesz_setup(char *s)
{
- default_hstate_size = memparse(s, &s);
+ unsigned long size;
+
+ size = (unsigned long)memparse(s, NULL);
+
+ if (!arch_hugetlb_valid_size(size)) {
+ pr_err("HugeTLB: unsupported default_hugepagesz %s\n", s);
+ return 0;
+ }
+
+ default_hstate_size = size;
return 1;
}
-__setup("default_hugepagesz=", hugetlb_default_setup);
+__setup("default_hugepagesz=", default_hugepagesz_setup);
static unsigned int cpuset_mems_nr(unsigned int *array)
{
--
2.25.4
^ permalink raw reply related
* [PATCH v4 0/4] Clean up hugetlb boot command line processing
From: Mike Kravetz @ 2020-04-28 20:56 UTC (permalink / raw)
To: linux-mm, linux-kernel, linux-arm-kernel, linuxppc-dev,
linux-riscv, linux-s390, sparclinux, linux-doc
Cc: Dave Hansen, Heiko Carstens, Peter Xu, Paul Mackerras,
Will Deacon, Mina Almasry, Jonathan Corbet, Christian Borntraeger,
Ingo Molnar, Catalin Marinas, Longpeng, Albert Ou, Vasily Gorbik,
Paul Walmsley, Thomas Gleixner, Nitesh Narayan Lal, Randy Dunlap,
Palmer Dabbelt, Andrew Morton, David S . Miller, Mike Kravetz
v4 -
Fixed huge page order definitions for arm64 (Qian Cai)
Removed hugepages_supported() checks in command line processing as
powerpc does not set hugepages_supported until later in boot (Sandipan)
Added Acks, Reviews and Tested (Will, Gerald, Anders, Sandipan)
v3 -
Used weak attribute method of defining arch_hugetlb_valid_size.
This eliminates changes to arch specific hugetlb.h files (Peter)
Updated documentation (Peter, Randy)
Fixed handling of implicitly specified gigantic page preallocation
in existing code and removed documentation of such. There is now
no difference between handling of gigantic and non-gigantic pages.
(Peter, Nitesh).
This requires the most review as there is a small change to
undocumented behavior. See patch 4 commit message for details.
Added Acks and Reviews (Mina, Peter)
v2 -
Fix build errors with patch 1 (Will)
Change arch_hugetlb_valid_size arg to unsigned long and remove
irrelevant 'extern' keyword (Christophe)
Documentation and other misc changes (Randy, Christophe, Mina)
Do not process command line options if !hugepages_supported()
(Dave, but it sounds like we may want to additional changes to
hugepages_supported() for x86? If that is needed I would prefer
a separate patch.)
Longpeng(Mike) reported a weird message from hugetlb command line processing
and proposed a solution [1]. While the proposed patch does address the
specific issue, there are other related issues in command line processing.
As hugetlbfs evolved, updates to command line processing have been made to
meet immediate needs and not necessarily in a coordinated manner. The result
is that some processing is done in arch specific code, some is done in arch
independent code and coordination is problematic. Semantics can vary between
architectures.
The patch series does the following:
- Define arch specific arch_hugetlb_valid_size routine used to validate
passed huge page sizes.
- Move hugepagesz= command line parsing out of arch specific code and into
an arch independent routine.
- Clean up command line processing to follow desired semantics and
document those semantics.
[1] https://lore.kernel.org/linux-mm/20200305033014.1152-1-longpeng2@huawei.com
Mike Kravetz (4):
hugetlbfs: add arch_hugetlb_valid_size
hugetlbfs: move hugepagesz= parsing to arch independent code
hugetlbfs: remove hugetlb_add_hstate() warning for existing hstate
hugetlbfs: clean up command line processing
.../admin-guide/kernel-parameters.txt | 40 ++--
Documentation/admin-guide/mm/hugetlbpage.rst | 35 ++++
arch/arm64/mm/hugetlbpage.c | 30 +--
arch/powerpc/mm/hugetlbpage.c | 30 +--
arch/riscv/mm/hugetlbpage.c | 24 +--
arch/s390/mm/hugetlbpage.c | 24 +--
arch/sparc/mm/init_64.c | 43 +----
arch/x86/mm/hugetlbpage.c | 23 +--
include/linux/hugetlb.h | 2 +-
mm/hugetlb.c | 180 ++++++++++++++----
10 files changed, 260 insertions(+), 171 deletions(-)
--
2.25.4
^ 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