* [PATCH v7 4/7] powerpc/processor: Move cpu_relax() into asm/vdso/processor.h
From: Christophe Leroy @ 2020-04-20 16:56 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, nathanl
Cc: arnd, linux-kernel, luto, tglx, vincenzo.frascino, linuxppc-dev
In-Reply-To: <cover.1587401492.git.christophe.leroy@c-s.fr>
cpu_relax() need to be in asm/vdso/processor.h to be used by
the C VDSO generic library.
Move it there.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/processor.h | 10 ++--------
arch/powerpc/include/asm/vdso/processor.h | 23 +++++++++++++++++++++++
2 files changed, 25 insertions(+), 8 deletions(-)
create mode 100644 arch/powerpc/include/asm/vdso/processor.h
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index eedcbfb9a6ff..89c9eab8e45c 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -6,6 +6,8 @@
* Copyright (C) 2001 PPC 64 Team, IBM Corp
*/
+#include <vdso/processor.h>
+
#include <asm/reg.h>
#ifdef CONFIG_VSX
@@ -63,14 +65,6 @@ extern int _chrp_type;
#endif /* defined(__KERNEL__) && defined(CONFIG_PPC32) */
-/* Macros for adjusting thread priority (hardware multi-threading) */
-#define HMT_very_low() asm volatile("or 31,31,31 # very low priority")
-#define HMT_low() asm volatile("or 1,1,1 # low priority")
-#define HMT_medium_low() asm volatile("or 6,6,6 # medium low priority")
-#define HMT_medium() asm volatile("or 2,2,2 # medium priority")
-#define HMT_medium_high() asm volatile("or 5,5,5 # medium high priority")
-#define HMT_high() asm volatile("or 3,3,3 # high priority")
-
#ifdef __KERNEL__
#ifdef CONFIG_PPC64
diff --git a/arch/powerpc/include/asm/vdso/processor.h b/arch/powerpc/include/asm/vdso/processor.h
new file mode 100644
index 000000000000..39b9beace9ca
--- /dev/null
+++ b/arch/powerpc/include/asm/vdso/processor.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_VDSO_PROCESSOR_H
+#define __ASM_VDSO_PROCESSOR_H
+
+#ifndef __ASSEMBLY__
+
+/* Macros for adjusting thread priority (hardware multi-threading) */
+#define HMT_very_low() asm volatile("or 31, 31, 31 # very low priority")
+#define HMT_low() asm volatile("or 1, 1, 1 # low priority")
+#define HMT_medium_low() asm volatile("or 6, 6, 6 # medium low priority")
+#define HMT_medium() asm volatile("or 2, 2, 2 # medium priority")
+#define HMT_medium_high() asm volatile("or 5, 5, 5 # medium high priority")
+#define HMT_high() asm volatile("or 3, 3, 3 # high priority")
+
+#ifdef CONFIG_PPC64
+#define cpu_relax() do { HMT_low(); HMT_medium(); barrier(); } while (0)
+#else
+#define cpu_relax() barrier()
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_PROCESSOR_H */
--
2.25.0
^ permalink raw reply related
* [PATCH v7 7/7] [NOT TO BE MERGED] Export sysrq_mask
From: Christophe Leroy @ 2020-04-20 16:56 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, nathanl
Cc: arnd, linux-kernel, luto, tglx, vincenzo.frascino, linuxppc-dev
In-Reply-To: <cover.1587401492.git.christophe.leroy@c-s.fr>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
drivers/tty/sysrq.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 5e0d0813da55..a0760bcd7a97 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -74,6 +74,7 @@ int sysrq_mask(void)
return 1;
return sysrq_enabled;
}
+EXPORT_SYMBOL_GPL(sysrq_mask);
/*
* A value of 1 means 'all', other nonzero values are an op mask:
--
2.25.0
^ permalink raw reply related
* [PATCH v7 5/7] powerpc/vdso: Prepare for switching VDSO to generic C implementation.
From: Christophe Leroy @ 2020-04-20 16:56 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, nathanl
Cc: arnd, linux-kernel, luto, tglx, vincenzo.frascino, linuxppc-dev
In-Reply-To: <cover.1587401492.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 v7 6/7] powerpc/vdso: Switch VDSO to generic C implementation.
From: Christophe Leroy @ 2020-04-20 16:56 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, nathanl
Cc: arnd, linux-kernel, luto, tglx, vincenzo.frascino, linuxppc-dev
In-Reply-To: <cover.1587401492.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
* Re: [musl] Powerpc Linux 'scv' system call ABI proposal take 2
From: Rich Felker @ 2020-04-20 17:27 UTC (permalink / raw)
To: Nicholas Piggin
Cc: libc-dev, libc-alpha, linuxppc-dev, Adhemerval Zanella, musl
In-Reply-To: <1587356128.aslvdnmtbw.astroid@bobo.none>
On Mon, Apr 20, 2020 at 02:31:58PM +1000, Nicholas Piggin wrote:
> Excerpts from Rich Felker's message of April 20, 2020 2:09 pm:
> > On Mon, Apr 20, 2020 at 12:32:21PM +1000, Nicholas Piggin wrote:
> >> Excerpts from Rich Felker's message of April 20, 2020 11:34 am:
> >> > On Mon, Apr 20, 2020 at 11:10:25AM +1000, Nicholas Piggin wrote:
> >> >> Excerpts from Rich Felker's message of April 17, 2020 4:31 am:
> >> >> > Note that because lr is clobbered we need at least once normally
> >> >> > call-clobbered register that's not syscall clobbered to save lr in.
> >> >> > Otherwise stack frame setup is required to spill it.
> >> >>
> >> >> The kernel would like to use r9-r12 for itself. We could do with fewer
> >> >> registers, but we have some delay establishing the stack (depends on a
> >> >> load which depends on a mfspr), and entry code tends to be quite store
> >> >> heavy whereas on the caller side you have r1 set up (modulo stack
> >> >> updates), and the system call is a long delay during which time the
> >> >> store queue has significant time to drain.
> >> >>
> >> >> My feeling is it would be better for kernel to have these scratch
> >> >> registers.
> >> >
> >> > If your new kernel syscall mechanism requires the caller to make a
> >> > whole stack frame it otherwise doesn't need and spill registers to it,
> >> > it becomes a lot less attractive. Some of those 90 cycles saved are
> >> > immediately lost on the userspace side, plus you either waste icache
> >> > at the call point or require the syscall to go through a
> >> > userspace-side helper function that performs the spill and restore.
> >>
> >> You would be surprised how few cycles that takes on a high end CPU. Some
> >> might be a couple of %. I am one for counting cycles mind you, I'm not
> >> being flippant about it. If we can come up with something faster I'd be
> >> up for it.
> >
> > If the cycle count is trivial then just do it on the kernel side.
>
> The cycle count for user is, because you have r1 ready. Kernel does not
> have its stack ready, it has to mfspr rX ; ld rY,N(rX); to get stack to
> save into.
>
> Which is also wasted work for a userspace.
>
> Now that I think about it, no stack frame is even required! lr is saved
> into the caller's stack when its clobbered with an asm, just as when
> it's used for a function call.
No. If there is a non-clobbered register, lr can be moved to the
non-clobbered register rather than saved to the stack. However it
looks like (1) gcc doesn't take advantage of that possibility, but (2)
the caller already arranged for there to be space on the stack to save
lr, so the cost is only one store and one load, not any stack
adjustment or other frame setup. So it's probably not a really big
deal. However, just adding "lr" clobber to existing syscall in musl
increased the size of a simple syscall function (getuid) from 20 bytes
to 36 bytes.
> >> > syscall arg registers still preserved? If not, this is a major cost on
> >> > the userspace side, since any call point that has to loop-and-retry
> >> > (e.g. futex) now needs to make its own place to store the original
> >> > values.)
> >>
> >> Powerpc system calls never did. We could have scv preserve them, but
> >> you'd still need to restore r3. We could make an ABI which does not
> >> clobber r3 but puts the return value in r9, say. I'd like to see what
> >> the user side code looks like to take advantage of such a thing though.
> >
> > Oh wow, I hadn't realized that, but indeed the code we have now is
> > allowing for the kernel to clobber them all. So at least this isn't
> > getting any worse I guess. I think it was a very poor choice of
> > behavior though and a disadvantage vs what other archs do (some of
> > them preserve all registers; others preserve only normally call-saved
> > ones plus the syscall arg ones and possibly a few other specials).
>
> Well, we could change it. Does the generated code improve significantly
> we take those clobbers away?
I'd have to experiment a bit more to see. It's not going to help at
all in functions which are pure syscall wrappers that just do the
syscall and return, since the arg regs are dead after the syscall
anyway (the caller must assume they were clobbered). But where
syscalls are inlined and used in a loop, like a futex wait, it might
make a nontrivial difference.
Unfortunately even if you did change it for the new scv mechanism, it
would be hard to take advantage of the change while also supporting
sc, unless we used a helper function that just did scv directly, but
saved/restored all the arg regs when using the legacy sc mechanism.
Just inlining the hwcap conditional and clobbering more regs in one
code path than in the other likely would not help; gcc won't
shrink-wrap the clobbered/non-clobbered paths separately, and even if
it did, when this were inlined somewhere like a futex loop, it'd end
up having to lift the conditional out of the loop to be very
advantageous, then making the code much larger by producing two copies
of the loop. So I think just behaving similarly to the old sc method
is probably the best option we have...
Rich
^ permalink raw reply
* Re: [PATCH 6/8] simplefs: add file creation functions
From: Emanuele Giuseppe Esposito @ 2020-04-20 13:57 UTC (permalink / raw)
To: Greg Kroah-Hartman
Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
ocfs2-devel, Christoph Hellwig, Andrew Donnellan, Matthew Garrett,
linux-efi, Arnd Bergmann, Daniel Borkmann, Christian Borntraeger,
linux-rdma, Mark Fasheh, Anton Vorontsov, John Fastabend,
James Morris, Ard Biesheuvel, Jason Gunthorpe, Doug Ledford,
oprofile-list, Yonghong Song, Ian Kent, Andrii Nakryiko,
Alexey Dobriyan, Serge E. Hallyn, Robert Richter,
Thomas Zimmermann, Vasily Gorbik, Tony Luck, Kees Cook,
James E.J. Bottomley, autofs, Maarten Lankhorst, Mike Marciniszyn,
Maxime Ripard, linux-fsdevel, Manoj N. Kumar, Uma Krishnan,
Jakub Kicinski, KP Singh, Trond Myklebust, Matthew R. Ochs,
David S. Miller, Felipe Balbi, linux-nfs, Iurii Zaikin,
linux-scsi, Martin K. Petersen, linux-mm, linux-s390,
Dennis Dalessandro, Miklos Szeredi, linux-security-module,
linux-kernel, Anna Schumaker, Luis Chamberlain, Chuck Lever,
Jeremy Kerr, Daniel Vetter, Colin Cross, Frederic Barrat,
Paolo Bonzini, Andrew Morton, Mike Kravetz, linuxppc-dev,
Martin KaFai Lau, Joel Becker, Alexander Viro
In-Reply-To: <20200414125626.GC720679@kroah.com>
On 4/14/20 2:56 PM, Greg Kroah-Hartman wrote:
> On Tue, Apr 14, 2020 at 02:43:00PM +0200, Emanuele Giuseppe Esposito wrote:
>> A bunch of code is duplicated between debugfs and tracefs, unify it to the
>> simplefs library.
>>
>> The code is very similar, except that dentry and inode creation are unified
>> into a single function (unlike start_creating in debugfs and tracefs, which
>> only takes care of dentries). This adds an output parameter to the creation
>> functions, but pushes all error recovery into fs/simplefs.c.
>>
>> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
>> ---
>> fs/simplefs.c | 150 +++++++++++++++++++++++++++++++++++++++
>> include/linux/simplefs.h | 19 +++++
>> 2 files changed, 169 insertions(+)
>
> What's wrong with libfs, isn't that supposed to be for these types of
> "common" filesystem interactions?
>
> Why create a whole "new" fs for this?
I assume you meant a new file. These new functions are used only by a
few filesystems, and I didn't want to include them in vmlinux
unconditionally, so I introduced simplefs.c and CONFIG_SIMPLEFS instead
of extending libfs.c. In this way only fs that need this code like
debugfs and tracefs will load it.
Thank you,
Emanuele
^ permalink raw reply
* Re: [PATCH 4/8] fs: introduce simple_new_inode
From: Emanuele Giuseppe Esposito @ 2020-04-20 13:58 UTC (permalink / raw)
To: Greg Kroah-Hartman
Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
ocfs2-devel, Christoph Hellwig, Andrew Donnellan, Matthew Garrett,
linux-efi, Arnd Bergmann, Daniel Borkmann, Christian Borntraeger,
linux-rdma, Mark Fasheh, Anton Vorontsov, John Fastabend,
James Morris, Ard Biesheuvel, Jason Gunthorpe, Doug Ledford,
oprofile-list, Yonghong Song, Ian Kent, Andrii Nakryiko,
Alexey Dobriyan, Serge E. Hallyn, Robert Richter,
Thomas Zimmermann, Vasily Gorbik, Tony Luck, Kees Cook,
James E.J. Bottomley, autofs, Maarten Lankhorst, Mike Marciniszyn,
Maxime Ripard, linux-fsdevel, Manoj N. Kumar, Uma Krishnan,
Jakub Kicinski, KP Singh, Trond Myklebust, Matthew R. Ochs,
David S. Miller, Felipe Balbi, linux-nfs, Iurii Zaikin,
linux-scsi, Martin K. Petersen, linux-mm, linux-s390,
Dennis Dalessandro, Miklos Szeredi, linux-security-module,
linux-kernel, Anna Schumaker, Luis Chamberlain, Chuck Lever,
Jeremy Kerr, Daniel Vetter, Colin Cross, Frederic Barrat,
Paolo Bonzini, Andrew Morton, Mike Kravetz, linuxppc-dev,
Martin KaFai Lau, Joel Becker, Alexander Viro
In-Reply-To: <20200414130140.GD720679@kroah.com>
On 4/14/20 3:01 PM, Greg Kroah-Hartman wrote:
> On Tue, Apr 14, 2020 at 02:42:58PM +0200, Emanuele Giuseppe Esposito wrote:
>> It is a common special case for new_inode to initialize the
>> time to the current time and the inode to get_next_ino().
>> Introduce a core function that does it and use it throughout
>> Linux.
>
> Shouldn't this just be called new_inode_current_time()?
>
> How is anyone going to remember what simple_new_inode() does to the
> inode structure?
I noticed that most functions in libfs.c are called "simple_*" when they
do the right thing for the majority of simple use cases (e.g.,
simple_symlink_inode_operations or simple_dir_operations). I can
certainly rename the function.
Thank you for all the feedback, I will incorporate it and send a new
patch series soon.
Emanuele
>
>> --- a/fs/libfs.c
>> +++ b/fs/libfs.c
>> @@ -595,6 +595,18 @@ int simple_write_end(struct file *file, struct address_space *mapping,
>> }
>> EXPORT_SYMBOL(simple_write_end);
>>
>> +struct inode *simple_new_inode(struct super_block *sb)
>> +{
>> + struct inode *inode = new_inode(sb);
>> + if (inode) {
>> + inode->i_ino = get_next_ino();
>> + inode->i_atime = inode->i_mtime =
>> + inode->i_ctime = current_time(inode);
>> + }
>> + return inode;
>> +}
>> +EXPORT_SYMBOL(simple_new_inode);
^ permalink raw reply
* Re: [PATCH 1/8] apparmor: just use vfs_kern_mount to make .null
From: Emanuele Giuseppe Esposito @ 2020-04-20 14:00 UTC (permalink / raw)
To: Luis Chamberlain, Goldwyn Rodrigues
Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
linux-s390, Christoph Hellwig, Andrew Donnellan, Matthew Garrett,
linux-efi, Arnd Bergmann, Daniel Borkmann, Christian Borntraeger,
linux-rdma, Mark Fasheh, Anton Vorontsov, John Fastabend,
James Morris, Ard Biesheuvel, Jason Gunthorpe, Doug Ledford,
Yonghong Song, Ian Kent, Andrii Nakryiko, Alexey Dobriyan,
Serge E. Hallyn, Robert Richter, Thomas Zimmermann, Vasily Gorbik,
Tony Luck, Kees Cook, James E.J. Bottomley, autofs,
Maarten Lankhorst, Mike Marciniszyn, Maxime Ripard, linux-fsdevel,
Manoj N. Kumar, Uma Krishnan, Jakub Kicinski, KP Singh,
Trond Myklebust, Matthew R. Ochs, David S. Miller, Felipe Balbi,
linux-nfs, Iurii Zaikin, linux-scsi, Martin K. Petersen, linux-mm,
Greg Kroah-Hartman, Dennis Dalessandro, Miklos Szeredi,
linux-kernel, Anna Schumaker, linux-security-module, Chuck Lever,
Jeremy Kerr, Daniel Vetter, Colin Cross, Frederic Barrat,
Paolo Bonzini, Andrew Morton, Mike Kravetz, linuxppc-dev,
Martin KaFai Lau, Joel Becker, Alexander Viro
In-Reply-To: <20200416064405.GP11244@42.do-not-panic.com>
On 4/16/20 8:44 AM, Luis Chamberlain wrote:
> On Tue, Apr 14, 2020 at 02:42:55PM +0200, Emanuele Giuseppe Esposito wrote:
>> aa_mk_null_file is using simple_pin_fs/simple_release_fs with local
>> variables as arguments, for what would amount to a simple
>> vfs_kern_mount/mntput pair if everything was inlined. Just use
>> the normal filesystem API since the reference counting is not needed
>> here.
>
> *Why* is refcounting not needed here?
The refcount is a local variable and is always 0 on entry and exit, so
it is not necessary to have refcounting across function invocations,
such as what simple_pin_fs and simple_release_fs provide.
Thank you,
Emanuele
>
> Luis
>
>>
>> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
>> ---
>> security/apparmor/apparmorfs.c | 12 ++++++------
>> 1 file changed, 6 insertions(+), 6 deletions(-)
>>
>> diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
>> index 280741fc0f5f..828bb1eb77ea 100644
>> --- a/security/apparmor/apparmorfs.c
>> +++ b/security/apparmor/apparmorfs.c
>> @@ -2525,14 +2525,14 @@ struct path aa_null;
>>
>> static int aa_mk_null_file(struct dentry *parent)
>> {
>> - struct vfsmount *mount = NULL;
>> + struct file_system_type *type = parent->d_sb->s_type;
>> + struct vfsmount *mount;
>> struct dentry *dentry;
>> struct inode *inode;
>> - int count = 0;
>> - int error = simple_pin_fs(parent->d_sb->s_type, &mount, &count);
>>
>> - if (error)
>> - return error;
>> + mount = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL);
>> + if (IS_ERR(mount))
>> + return PTR_ERR(mount);
>>
>> inode_lock(d_inode(parent));
>> dentry = lookup_one_len(NULL_FILE_NAME, parent, strlen(NULL_FILE_NAME));
>> @@ -2561,7 +2561,7 @@ static int aa_mk_null_file(struct dentry *parent)
>> dput(dentry);
>> out:
>> inode_unlock(d_inode(parent));
>> - simple_release_fs(&mount, &count);
>> + mntput(mount);
>> return error;
>> }
>>
>> --
>> 2.25.2
>>
>
^ permalink raw reply
* Re: [PATCH 0/8] Simplefs: group and simplify linux fs code
From: Emanuele Giuseppe Esposito @ 2020-04-20 14:01 UTC (permalink / raw)
To: Luis Chamberlain
Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
linux-s390, Christoph Hellwig, Andrew Donnellan, Matthew Garrett,
linux-efi, Arnd Bergmann, Daniel Borkmann, Christian Borntraeger,
linux-rdma, Mark Fasheh, Anton Vorontsov, John Fastabend,
James Morris, Ard Biesheuvel, Jason Gunthorpe, Doug Ledford,
Yonghong Song, Ian Kent, Andrii Nakryiko, Alexey Dobriyan,
Serge E. Hallyn, Robert Richter, Thomas Zimmermann, Vasily Gorbik,
Tony Luck, Kees Cook, James E.J. Bottomley, autofs,
Maarten Lankhorst, Mike Marciniszyn, Maxime Ripard, linux-fsdevel,
Manoj N. Kumar, Uma Krishnan, Jakub Kicinski, KP Singh,
Trond Myklebust, Matthew R. Ochs, David S. Miller, Felipe Balbi,
linux-nfs, Iurii Zaikin, linux-scsi, Martin K. Petersen, linux-mm,
Greg Kroah-Hartman, Dennis Dalessandro, Miklos Szeredi,
linux-kernel, Anna Schumaker, linux-security-module, Chuck Lever,
Jeremy Kerr, Daniel Vetter, Colin Cross, Frederic Barrat,
Paolo Bonzini, Andrew Morton, Mike Kravetz, linuxppc-dev,
Martin KaFai Lau, Joel Becker, Alexander Viro
In-Reply-To: <20200416065922.GS11244@42.do-not-panic.com>
On 4/16/20 8:59 AM, Luis Chamberlain wrote:
> On Tue, Apr 14, 2020 at 02:42:54PM +0200, Emanuele Giuseppe Esposito wrote:
>> This series of patches introduce wrappers for functions,
>> arguments simplification in functions calls and most importantly
>> groups duplicated code in a single header, simplefs, to avoid redundancy
>> in the linux fs, especially debugfs and tracefs.
>
> The general goal seems worthy, but here I don't see explained why hasn't
> this gone through libfs, and what the intention was long term. For
> instance, you added some other generalizations which you have found. It
> was not clear that this was the goal here, to expand on these paths.
>
> What if common code on fs is found which are not part of debugfs and
> tracefs, how does one decide if to move to libfs or simplefs?
The idea of simplefs (that I will also explain better in the cover
letter and commit messages) is that not only it groups common code, but
also introduces a new struct simple_fs that simplifies parameter
passing. This means all fs that use these functions and the struct
should include linux/simplefs.h, while all common functions that take a
simple_fs struct will be added in simplefs.c
Thank you for all the feedback, I will incorporate it and send a new
patch series soon.
Emanuele
^ permalink raw reply
* Re: [PATCH 6/8] simplefs: add file creation functions
From: Greg Kroah-Hartman @ 2020-04-20 14:28 UTC (permalink / raw)
To: Emanuele Giuseppe Esposito
Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
ocfs2-devel, Christoph Hellwig, Andrew Donnellan, Matthew Garrett,
linux-efi, Arnd Bergmann, Daniel Borkmann, Christian Borntraeger,
linux-rdma, Mark Fasheh, Anton Vorontsov, John Fastabend,
James Morris, Ard Biesheuvel, Jason Gunthorpe, Doug Ledford,
oprofile-list, Yonghong Song, Ian Kent, Andrii Nakryiko,
Alexey Dobriyan, Serge E. Hallyn, Robert Richter,
Thomas Zimmermann, Vasily Gorbik, Tony Luck, Kees Cook,
James E.J. Bottomley, autofs, Maarten Lankhorst, Mike Marciniszyn,
Maxime Ripard, linux-fsdevel, Manoj N. Kumar, Uma Krishnan,
Jakub Kicinski, KP Singh, Trond Myklebust, Matthew R. Ochs,
David S. Miller, Felipe Balbi, linux-nfs, Iurii Zaikin,
linux-scsi, Martin K. Petersen, linux-mm, linux-s390,
Dennis Dalessandro, Miklos Szeredi, linux-security-module,
linux-kernel, Anna Schumaker, Luis Chamberlain, Chuck Lever,
Jeremy Kerr, Daniel Vetter, Colin Cross, Frederic Barrat,
Paolo Bonzini, Andrew Morton, Mike Kravetz, linuxppc-dev,
Martin KaFai Lau, Joel Becker, Alexander Viro
In-Reply-To: <f371bcc0-266a-cb0b-3bde-fed336b8c9b5@redhat.com>
On Mon, Apr 20, 2020 at 03:57:48PM +0200, Emanuele Giuseppe Esposito wrote:
>
>
> On 4/14/20 2:56 PM, Greg Kroah-Hartman wrote:
> > On Tue, Apr 14, 2020 at 02:43:00PM +0200, Emanuele Giuseppe Esposito wrote:
> > > A bunch of code is duplicated between debugfs and tracefs, unify it to the
> > > simplefs library.
> > >
> > > The code is very similar, except that dentry and inode creation are unified
> > > into a single function (unlike start_creating in debugfs and tracefs, which
> > > only takes care of dentries). This adds an output parameter to the creation
> > > functions, but pushes all error recovery into fs/simplefs.c.
> > >
> > > Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
> > > ---
> > > fs/simplefs.c | 150 +++++++++++++++++++++++++++++++++++++++
> > > include/linux/simplefs.h | 19 +++++
> > > 2 files changed, 169 insertions(+)
> >
> > What's wrong with libfs, isn't that supposed to be for these types of
> > "common" filesystem interactions?
> >
> > Why create a whole "new" fs for this?
>
> I assume you meant a new file. These new functions are used only by a few
> filesystems, and I didn't want to include them in vmlinux unconditionally,
> so I introduced simplefs.c and CONFIG_SIMPLEFS instead of extending libfs.c.
> In this way only fs that need this code like debugfs and tracefs will load
> it.
Nothing "loads it", why not just make these libfs functions instead? As
the difference between the two is not obvious at all, please don't make
things confusing.
thanks,
greg k-h
^ permalink raw reply
* Re: [PATCH 6/8] simplefs: add file creation functions
From: Paolo Bonzini @ 2020-04-20 14:33 UTC (permalink / raw)
To: Greg Kroah-Hartman, Emanuele Giuseppe Esposito
Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
ocfs2-devel, Christoph Hellwig, Andrew Donnellan, Matthew Garrett,
linux-efi, Arnd Bergmann, Daniel Borkmann, Christian Borntraeger,
linux-rdma, Mark Fasheh, Anton Vorontsov, John Fastabend,
James Morris, Ard Biesheuvel, Jason Gunthorpe, Doug Ledford,
oprofile-list, Yonghong Song, Ian Kent, Andrii Nakryiko,
Alexey Dobriyan, Serge E. Hallyn, Robert Richter, Daniel Vetter,
Vasily Gorbik, Tony Luck, Kees Cook, James E.J. Bottomley, autofs,
Maarten Lankhorst, Mike Marciniszyn, Maxime Ripard, linux-fsdevel,
Manoj N. Kumar, Uma Krishnan, Jakub Kicinski, KP Singh,
Trond Myklebust, Matthew R. Ochs, David S. Miller, Felipe Balbi,
linux-nfs, Iurii Zaikin, linux-scsi, Martin K. Petersen, linux-mm,
linux-s390, Dennis Dalessandro, Miklos Szeredi,
linux-security-module, linux-kernel, Anna Schumaker,
Luis Chamberlain, Chuck Lever, Jeremy Kerr, Thomas Zimmermann,
Colin Cross, Frederic Barrat, Andrew Morton, Mike Kravetz,
linuxppc-dev, Martin KaFai Lau, Joel Becker, Alexander Viro
In-Reply-To: <20200420142842.GA4125486@kroah.com>
On 20/04/20 16:28, Greg Kroah-Hartman wrote:
>> I assume you meant a new file. These new functions are used only by a few
>> filesystems, and I didn't want to include them in vmlinux unconditionally,
>> so I introduced simplefs.c and CONFIG_SIMPLEFS instead of extending libfs.c.
>> In this way only fs that need this code like debugfs and tracefs will load
>> it.
> Nothing "loads it", why not just make these libfs functions instead? As
> the difference between the two is not obvious at all, please don't make
> things confusing.
I think Emanuele meant "will link it" not "will load it".
Emanuele, you can just move everything to libfs.c and get rid of
CONFIG_SIMPLEFS too. "Do less" is not an offer you want to turn down!
Thanks,
Paolo
^ permalink raw reply
* Re: [PATCH v3 0/4] Clean up hugetlb boot command line processing
From: Mike Kravetz @ 2020-04-20 18:20 UTC (permalink / raw)
To: Qian Cai
Cc: linux-doc, Catalin Marinas, Dave Hansen, Heiko Carstens, Peter Xu,
Linux-MM, Paul Mackerras, sparclinux, linux-riscv, Will Deacon,
Mina Almasry, linux-s390, Jonathan Corbet, Christian Borntraeger,
Ingo Molnar, Longpeng, Albert Ou, Vasily Gorbik, Paul Walmsley,
Thomas Gleixner, linux-arm-kernel, Nitesh Narayan Lal,
Randy Dunlap, LKML, Palmer Dabbelt, Andrew Morton, linuxppc-dev,
David S.Miller
In-Reply-To: <5E312000-05D8-4C5D-A7C0-DDDE1842CB0E@lca.pw>
On 4/20/20 8:34 AM, Qian Cai wrote:
>
>
>> On Apr 17, 2020, at 2:50 PM, Mike Kravetz <mike.kravetz@oracle.com> wrote:
>>
>> 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
>
> Reverted this series fixed many undefined behaviors on arm64 with the config,
>
> https://raw.githubusercontent.com/cailca/linux-mm/master/arm64.config
>
> [ 54.172683][ T1] UBSAN: shift-out-of-bounds in ./include/linux/hugetlb.h:555:34
> [ 54.180411][ T1] shift exponent 4294967285 is too large for 64-bit type 'unsigned long'
> [ 54.188885][ T1] CPU: 130 PID: 1 Comm: swapper/0 Not tainted 5.7.0-rc2-next-20200420 #1
> [ 54.197284][ T1] Hardware name: HPE Apollo 70 /C01_APACHE_MB , BIOS L50_5.13_1.11 06/18/2019
> [ 54.207888][ T1] Call trace:
> [ 54.211100][ T1] dump_backtrace+0x0/0x224
> [ 54.215565][ T1] show_stack+0x20/0x2c
> [ 54.219651][ T1] dump_stack+0xfc/0x184
> [ 54.223829][ T1] __ubsan_handle_shift_out_of_bounds+0x304/0x344
> [ 54.230204][ T1] hugetlb_add_hstate+0x3ec/0x414
> huge_page_size at include/linux/hugetlb.h:555
> (inlined by) hugetlb_add_hstate at mm/hugetlb.c:3301
> [ 54.235191][ T1] hugetlbpage_init+0x14/0x30
> [ 54.239824][ T1] do_one_initcall+0x6c/0x144
> [ 54.244446][ T1] do_initcall_level+0x158/0x1c4
> [ 54.249336][ T1] do_initcalls+0x68/0xb0
> [ 54.253597][ T1] do_basic_setup+0x28/0x30
> [ 54.258049][ T1] kernel_init_freeable+0x19c/0x228
> [ 54.263188][ T1] kernel_init+0x14/0x208
> [ 54.267473][ T1] ret_from_fork+0x10/0x18
While rearranging the code (patch 3 in series), I made the incorrect
assumption that CONT_XXX_SIZE == (1UL << CONT_XXX_SHIFT). However,
this is not the case. Does the following patch fix these issues?
From b75cb4a0852e208bee8c4eb347dc076fcaa88859 Mon Sep 17 00:00:00 2001
From: Mike Kravetz <mike.kravetz@oracle.com>
Date: Mon, 20 Apr 2020 10:41:18 -0700
Subject: [PATCH] arm64/hugetlb: fix hugetlb initialization
When calling hugetlb_add_hstate() to initialize a new hugetlb size,
be sure to use correct huge pages size order.
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
---
arch/arm64/mm/hugetlbpage.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 9ca840527296..a02411a1f19a 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -453,11 +453,11 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma,
static int __init hugetlbpage_init(void)
{
#ifdef CONFIG_ARM64_4K_PAGES
- hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+ hugetlb_add_hstate(ilog2(PUD_SIZE) - PAGE_SHIFT);
#endif
- hugetlb_add_hstate(CONT_PMD_SHIFT - PAGE_SHIFT);
- hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
- hugetlb_add_hstate(CONT_PTE_SHIFT - PAGE_SHIFT);
+ hugetlb_add_hstate(ilog2(CONT_PMD_SIZE) - PAGE_SHIFT);
+ hugetlb_add_hstate(ilog2(PMD_SIZE) - PAGE_SHIFT);
+ hugetlb_add_hstate(ilog2(CONT_PTE_SIZE) - PAGE_SHIFT);
return 0;
}
--
2.25.2
^ permalink raw reply related
* [PATCH 1/5] drivers/powerpc: Replace _ALIGN_UP() by ALIGN()
From: Christophe Leroy @ 2020-04-20 18:36 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: alsa-devel, kvm, linux-kernel, dri-devel, linux-fbdev,
linuxppc-dev
_ALIGN_UP() is specific to powerpc
ALIGN() is generic and does the same
Replace _ALIGN_UP() by ALIGN()
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
drivers/ps3/ps3-lpm.c | 6 +++---
drivers/vfio/pci/vfio_pci_nvlink2.c | 2 +-
drivers/video/fbdev/ps3fb.c | 4 ++--
sound/ppc/snd_ps3.c | 2 +-
4 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/drivers/ps3/ps3-lpm.c b/drivers/ps3/ps3-lpm.c
index 83c45659bc9d..064b5884ba13 100644
--- a/drivers/ps3/ps3-lpm.c
+++ b/drivers/ps3/ps3-lpm.c
@@ -1096,8 +1096,8 @@ int ps3_lpm_open(enum ps3_lpm_tb_type tb_type, void *tb_cache,
lpm_priv->tb_cache_internal = NULL;
lpm_priv->tb_cache = NULL;
} else if (tb_cache) {
- if (tb_cache != (void *)_ALIGN_UP((unsigned long)tb_cache, 128)
- || tb_cache_size != _ALIGN_UP(tb_cache_size, 128)) {
+ if (tb_cache != (void *)ALIGN((unsigned long)tb_cache, 128)
+ || tb_cache_size != ALIGN(tb_cache_size, 128)) {
dev_err(sbd_core(), "%s:%u: unaligned tb_cache\n",
__func__, __LINE__);
result = -EINVAL;
@@ -1116,7 +1116,7 @@ int ps3_lpm_open(enum ps3_lpm_tb_type tb_type, void *tb_cache,
result = -ENOMEM;
goto fail_malloc;
}
- lpm_priv->tb_cache = (void *)_ALIGN_UP(
+ lpm_priv->tb_cache = (void *)ALIGN(
(unsigned long)lpm_priv->tb_cache_internal, 128);
}
diff --git a/drivers/vfio/pci/vfio_pci_nvlink2.c b/drivers/vfio/pci/vfio_pci_nvlink2.c
index ed20d73cc27c..65c61710c0e9 100644
--- a/drivers/vfio/pci/vfio_pci_nvlink2.c
+++ b/drivers/vfio/pci/vfio_pci_nvlink2.c
@@ -67,7 +67,7 @@ static size_t vfio_pci_nvgpu_rw(struct vfio_pci_device *vdev,
*
* This is not fast path anyway.
*/
- sizealigned = _ALIGN_UP(posoff + count, PAGE_SIZE);
+ sizealigned = ALIGN(posoff + count, PAGE_SIZE);
ptr = ioremap_cache(data->gpu_hpa + posaligned, sizealigned);
if (!ptr)
return -EFAULT;
diff --git a/drivers/video/fbdev/ps3fb.c b/drivers/video/fbdev/ps3fb.c
index 834f63edf700..9df78fb77267 100644
--- a/drivers/video/fbdev/ps3fb.c
+++ b/drivers/video/fbdev/ps3fb.c
@@ -44,7 +44,7 @@
#define GPU_CMD_BUF_SIZE (2 * 1024 * 1024)
#define GPU_FB_START (64 * 1024)
#define GPU_IOIF (0x0d000000UL)
-#define GPU_ALIGN_UP(x) _ALIGN_UP((x), 64)
+#define GPU_ALIGN_UP(x) ALIGN((x), 64)
#define GPU_MAX_LINE_LENGTH (65536 - 64)
#define GPU_INTR_STATUS_VSYNC_0 0 /* vsync on head A */
@@ -1015,7 +1015,7 @@ static int ps3fb_probe(struct ps3_system_bus_device *dev)
}
#endif
- max_ps3fb_size = _ALIGN_UP(GPU_IOIF, 256*1024*1024) - GPU_IOIF;
+ max_ps3fb_size = ALIGN(GPU_IOIF, 256*1024*1024) - GPU_IOIF;
if (ps3fb_videomemory.size > max_ps3fb_size) {
dev_info(&dev->core, "Limiting ps3fb mem size to %lu bytes\n",
max_ps3fb_size);
diff --git a/sound/ppc/snd_ps3.c b/sound/ppc/snd_ps3.c
index 6d2a33b8faa0..b8161a08f2ca 100644
--- a/sound/ppc/snd_ps3.c
+++ b/sound/ppc/snd_ps3.c
@@ -926,7 +926,7 @@ static int snd_ps3_driver_probe(struct ps3_system_bus_device *dev)
PAGE_SHIFT, /* use system page size */
0, /* dma type; not used */
NULL,
- _ALIGN_UP(SND_PS3_DMA_REGION_SIZE, PAGE_SIZE));
+ ALIGN(SND_PS3_DMA_REGION_SIZE, PAGE_SIZE));
dev->d_region->ioid = PS3_AUDIO_IOID;
ret = ps3_dma_region_create(dev->d_region);
--
2.25.0
^ permalink raw reply related
* [PATCH 3/5] powerpc: Replace _ALIGN_UP() by ALIGN()
From: Christophe Leroy @ 2020-04-20 18:36 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: alsa-devel, kvm, linux-kernel, dri-devel, linux-fbdev,
linuxppc-dev
In-Reply-To: <a5945463f86c984151962a475a3ee56a2893e85d.1587407777.git.christophe.leroy@c-s.fr>
_ALIGN_UP() is specific to powerpc
ALIGN() is generic and does the same
Replace _ALIGN_UP() by ALIGN()
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/iommu.h | 4 ++--
arch/powerpc/kernel/head_booke.h | 2 +-
arch/powerpc/kernel/nvram_64.c | 4 ++--
arch/powerpc/kernel/pci_64.c | 2 +-
arch/powerpc/kernel/prom.c | 4 ++--
arch/powerpc/kernel/prom_init.c | 8 ++++----
arch/powerpc/kvm/book3s_64_vio_hv.c | 2 +-
arch/powerpc/mm/book3s64/hash_tlb.c | 2 +-
arch/powerpc/mm/book3s64/radix_pgtable.c | 2 +-
arch/powerpc/mm/slice.c | 2 +-
arch/powerpc/platforms/cell/iommu.c | 6 +++---
arch/powerpc/platforms/powermac/bootx_init.c | 10 +++++-----
arch/powerpc/platforms/powernv/pci-ioda.c | 8 ++++----
arch/powerpc/platforms/ps3/mm.c | 16 ++++++++--------
arch/powerpc/platforms/ps3/setup.c | 2 +-
15 files changed, 37 insertions(+), 37 deletions(-)
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 350101e11ddb..5032f1593299 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -22,11 +22,11 @@
#define IOMMU_PAGE_SHIFT_4K 12
#define IOMMU_PAGE_SIZE_4K (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K)
#define IOMMU_PAGE_MASK_4K (~((1 << IOMMU_PAGE_SHIFT_4K) - 1))
-#define IOMMU_PAGE_ALIGN_4K(addr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE_4K)
+#define IOMMU_PAGE_ALIGN_4K(addr) ALIGN(addr, IOMMU_PAGE_SIZE_4K)
#define IOMMU_PAGE_SIZE(tblptr) (ASM_CONST(1) << (tblptr)->it_page_shift)
#define IOMMU_PAGE_MASK(tblptr) (~((1 << (tblptr)->it_page_shift) - 1))
-#define IOMMU_PAGE_ALIGN(addr, tblptr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE(tblptr))
+#define IOMMU_PAGE_ALIGN(addr, tblptr) ALIGN(addr, IOMMU_PAGE_SIZE(tblptr))
/* Boot time flags */
extern int iommu_is_off;
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index bd2e5ed8dd50..18f87bf9e32b 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -534,7 +534,7 @@ struct exception_regs {
};
/* ensure this structure is always sized to a multiple of the stack alignment */
-#define STACK_EXC_LVL_FRAME_SIZE _ALIGN_UP(sizeof (struct exception_regs), 16)
+#define STACK_EXC_LVL_FRAME_SIZE ALIGN(sizeof (struct exception_regs), 16)
#endif /* __ASSEMBLY__ */
#endif /* __HEAD_BOOKE_H__ */
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index fb4f61096613..314780e8ef78 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -854,8 +854,8 @@ loff_t __init nvram_create_partition(const char *name, int sig,
BUILD_BUG_ON(NVRAM_BLOCK_LEN != 16);
/* Convert sizes from bytes to blocks */
- req_size = _ALIGN_UP(req_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN;
- min_size = _ALIGN_UP(min_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN;
+ req_size = ALIGN(req_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN;
+ min_size = ALIGN(min_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN;
/* If no minimum size specified, make it the same as the
* requested size
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index e5d05af5a9af..ff8e3fbdf663 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -131,7 +131,7 @@ static int pcibios_map_phb_io_space(struct pci_controller *hose)
unsigned long io_virt_offset;
phys_page = ALIGN_DOWN(hose->io_base_phys, PAGE_SIZE);
- size_page = _ALIGN_UP(hose->pci_io_size, PAGE_SIZE);
+ size_page = ALIGN(hose->pci_io_size, PAGE_SIZE);
/* Make sure IO area address is clear */
hose->io_base_alloc = NULL;
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 10b5d5eafd34..1dcf0e214a22 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -97,7 +97,7 @@ static inline int overlaps_initrd(unsigned long start, unsigned long size)
return 0;
return (start + size) > ALIGN_DOWN(initrd_start, PAGE_SIZE) &&
- start <= _ALIGN_UP(initrd_end, PAGE_SIZE);
+ start <= ALIGN(initrd_end, PAGE_SIZE);
#else
return 0;
#endif
@@ -624,7 +624,7 @@ static void __init early_reserve_mem(void)
/* Then reserve the initrd, if any */
if (initrd_start && (initrd_end > initrd_start)) {
memblock_reserve(ALIGN_DOWN(__pa(initrd_start), PAGE_SIZE),
- _ALIGN_UP(initrd_end, PAGE_SIZE) -
+ ALIGN(initrd_end, PAGE_SIZE) -
ALIGN_DOWN(initrd_start, PAGE_SIZE));
}
#endif /* CONFIG_BLK_DEV_INITRD */
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 4cf5958eebd4..3a5a7db4564f 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1449,18 +1449,18 @@ static unsigned long __init alloc_up(unsigned long size, unsigned long align)
unsigned long addr = 0;
if (align)
- base = _ALIGN_UP(base, align);
+ base = ALIGN(base, align);
prom_debug("%s(%lx, %lx)\n", __func__, size, align);
if (ram_top == 0)
prom_panic("alloc_up() called with mem not initialized\n");
if (align)
- base = _ALIGN_UP(alloc_bottom, align);
+ base = ALIGN(alloc_bottom, align);
else
base = alloc_bottom;
for(; (base + size) <= alloc_top;
- base = _ALIGN_UP(base + 0x100000, align)) {
+ base = ALIGN(base + 0x100000, align)) {
prom_debug(" trying: 0x%lx\n\r", base);
addr = (unsigned long)prom_claim(base, size, 0);
if (addr != PROM_ERROR && addr != 0)
@@ -1587,7 +1587,7 @@ static void __init reserve_mem(u64 base, u64 size)
* dumb and just copy this entire array to the boot params
*/
base = ALIGN_DOWN(base, PAGE_SIZE);
- top = _ALIGN_UP(top, PAGE_SIZE);
+ top = ALIGN(top, PAGE_SIZE);
size = top - base;
if (cnt >= (MEM_RESERVE_MAP_SIZE - 1))
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 6fcaf1fa8e02..2d231eb5884a 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -208,7 +208,7 @@ static long kvmppc_rm_ioba_validate(struct kvmppc_spapr_tce_table *stt,
idx = (ioba >> stt->page_shift) - stt->offset;
sttpage = idx / TCES_PER_PAGE;
- sttpages = _ALIGN_UP(idx % TCES_PER_PAGE + npages, TCES_PER_PAGE) /
+ sttpages = ALIGN(idx % TCES_PER_PAGE + npages, TCES_PER_PAGE) /
TCES_PER_PAGE;
for (i = sttpage; i < sttpage + sttpages; ++i)
if (!stt->pages[i])
diff --git a/arch/powerpc/mm/book3s64/hash_tlb.c b/arch/powerpc/mm/book3s64/hash_tlb.c
index 2242d022b620..081940b85e24 100644
--- a/arch/powerpc/mm/book3s64/hash_tlb.c
+++ b/arch/powerpc/mm/book3s64/hash_tlb.c
@@ -197,7 +197,7 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
unsigned long flags;
start = ALIGN_DOWN(start, PAGE_SIZE);
- end = _ALIGN_UP(end, PAGE_SIZE);
+ end = ALIGN(end, PAGE_SIZE);
BUG_ON(!mm->pgd);
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 8f9edf07063a..4bdfc8dff87d 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -261,7 +261,7 @@ static int __meminit create_physical_mapping(unsigned long start,
pgprot_t prot;
int psize;
- start = _ALIGN_UP(start, PAGE_SIZE);
+ start = ALIGN(start, PAGE_SIZE);
for (addr = start; addr < end; addr += mapping_size) {
unsigned long gap, previous_size;
int rc;
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index dffe1a45b6ed..82b45b1cb973 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -478,7 +478,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
/* If hint, make sure it matches our alignment restrictions */
if (!fixed && addr) {
- addr = _ALIGN_UP(addr, page_size);
+ addr = ALIGN(addr, page_size);
slice_dbg(" aligned addr=%lx\n", addr);
/* Ignore hint if it's too large or overlaps a VMA */
if (addr > high_limit - len || addr < mmap_min_addr ||
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index ca9ffc1c8685..2124831cf57c 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -943,7 +943,7 @@ static int __init cell_iommu_fixed_mapping_init(void)
fbase = max(fbase, dbase + dsize);
}
- fbase = _ALIGN_UP(fbase, 1 << IO_SEGMENT_SHIFT);
+ fbase = ALIGN(fbase, 1 << IO_SEGMENT_SHIFT);
fsize = memblock_phys_mem_size();
if ((fbase + fsize) <= 0x800000000ul)
@@ -963,8 +963,8 @@ static int __init cell_iommu_fixed_mapping_init(void)
hend = hbase + htab_size_bytes;
/* The window must start and end on a segment boundary */
- if ((hbase != _ALIGN_UP(hbase, 1 << IO_SEGMENT_SHIFT)) ||
- (hend != _ALIGN_UP(hend, 1 << IO_SEGMENT_SHIFT))) {
+ if ((hbase != ALIGN(hbase, 1 << IO_SEGMENT_SHIFT)) ||
+ (hend != ALIGN(hend, 1 << IO_SEGMENT_SHIFT))) {
pr_debug("iommu: hash window not segment aligned\n");
return -1;
}
diff --git a/arch/powerpc/platforms/powermac/bootx_init.c b/arch/powerpc/platforms/powermac/bootx_init.c
index af309ee99114..c3374a90952f 100644
--- a/arch/powerpc/platforms/powermac/bootx_init.c
+++ b/arch/powerpc/platforms/powermac/bootx_init.c
@@ -108,7 +108,7 @@ static void * __init bootx_early_getprop(unsigned long base,
#define dt_push_token(token, mem) \
do { \
- *(mem) = _ALIGN_UP(*(mem),4); \
+ *(mem) = ALIGN(*(mem),4); \
*((u32 *)*(mem)) = token; \
*(mem) += 4; \
} while(0)
@@ -150,7 +150,7 @@ static void __init bootx_dt_add_prop(char *name, void *data, int size,
/* push property content */
if (size && data) {
memcpy((void *)*mem_end, data, size);
- *mem_end = _ALIGN_UP(*mem_end + size, 4);
+ *mem_end = ALIGN(*mem_end + size, 4);
}
}
@@ -303,7 +303,7 @@ static void __init bootx_scan_dt_build_struct(unsigned long base,
*lp++ = *p;
}
*lp = 0;
- *mem_end = _ALIGN_UP((unsigned long)lp + 1, 4);
+ *mem_end = ALIGN((unsigned long)lp + 1, 4);
/* get and store all properties */
while (*ppp) {
@@ -356,11 +356,11 @@ static unsigned long __init bootx_flatten_dt(unsigned long start)
/* Start using memory after the big blob passed by BootX, get
* some space for the header
*/
- mem_start = mem_end = _ALIGN_UP(((unsigned long)bi) + start, 4);
+ mem_start = mem_end = ALIGN(((unsigned long)bi) + start, 4);
DBG("Boot params header at: %x\n", mem_start);
hdr = (struct boot_param_header *)mem_start;
mem_end += sizeof(struct boot_param_header);
- rsvmap = (u64 *)(_ALIGN_UP(mem_end, 8));
+ rsvmap = (u64 *)(ALIGN(mem_end, 8));
hdr->off_mem_rsvmap = ((unsigned long)rsvmap) - mem_start;
mem_end = ((unsigned long)rsvmap) + 8 * sizeof(u64);
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 276b011cd45d..d1a16ebc31bb 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -265,7 +265,7 @@ static void pnv_ioda_reserve_dev_m64_pe(struct pci_dev *pdev,
continue;
start = ALIGN_DOWN(r->start - base, sgsz);
- end = _ALIGN_UP(r->end - base, sgsz);
+ end = ALIGN(r->end - base, sgsz);
for (segno = start / sgsz; segno < end / sgsz; segno++) {
if (pe_bitmap)
set_bit(segno, pe_bitmap);
@@ -361,7 +361,7 @@ static struct pnv_ioda_pe *pnv_ioda_pick_m64_pe(struct pci_bus *bus, bool all)
return NULL;
/* Allocate bitmap */
- size = _ALIGN_UP(phb->ioda.total_pe_num / 8, sizeof(unsigned long));
+ size = ALIGN(phb->ioda.total_pe_num / 8, sizeof(unsigned long));
pe_alloc = kzalloc(size, GFP_KERNEL);
if (!pe_alloc) {
pr_warn("%s: Out of memory !\n",
@@ -2537,7 +2537,7 @@ unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
direct_table_size = 1UL << table_shift;
for ( ; levels; --levels) {
- bytes += _ALIGN_UP(tce_table_size, direct_table_size);
+ bytes += ALIGN(tce_table_size, direct_table_size);
tce_table_size /= direct_table_size;
tce_table_size <<= 3;
@@ -3863,7 +3863,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
PNV_IODA1_DMA32_SEGSIZE;
/* Allocate aux data & arrays. We don't have IO ports on PHB3 */
- size = _ALIGN_UP(max_t(unsigned, phb->ioda.total_pe_num, 8) / 8,
+ size = ALIGN(max_t(unsigned, phb->ioda.total_pe_num, 8) / 8,
sizeof(unsigned long));
m64map_off = size;
size += phb->ioda.total_pe_num * sizeof(phb->ioda.m64_segmap[0]);
diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c
index 71ed37f7f475..b83f2c851b40 100644
--- a/arch/powerpc/platforms/ps3/mm.c
+++ b/arch/powerpc/platforms/ps3/mm.c
@@ -395,7 +395,7 @@ static struct dma_chunk * dma_find_chunk(struct ps3_dma_region *r,
{
struct dma_chunk *c;
unsigned long aligned_bus = ALIGN_DOWN(bus_addr, 1 << r->page_size);
- unsigned long aligned_len = _ALIGN_UP(len+bus_addr-aligned_bus,
+ unsigned long aligned_len = ALIGN(len+bus_addr-aligned_bus,
1 << r->page_size);
list_for_each_entry(c, &r->chunk_list.head, link) {
@@ -424,7 +424,7 @@ static struct dma_chunk *dma_find_chunk_lpar(struct ps3_dma_region *r,
{
struct dma_chunk *c;
unsigned long aligned_lpar = ALIGN_DOWN(lpar_addr, 1 << r->page_size);
- unsigned long aligned_len = _ALIGN_UP(len + lpar_addr - aligned_lpar,
+ unsigned long aligned_len = ALIGN(len + lpar_addr - aligned_lpar,
1 << r->page_size);
list_for_each_entry(c, &r->chunk_list.head, link) {
@@ -776,7 +776,7 @@ static int dma_sb_map_area(struct ps3_dma_region *r, unsigned long virt_addr,
unsigned long phys_addr = is_kernel_addr(virt_addr) ? __pa(virt_addr)
: virt_addr;
unsigned long aligned_phys = ALIGN_DOWN(phys_addr, 1 << r->page_size);
- unsigned long aligned_len = _ALIGN_UP(len + phys_addr - aligned_phys,
+ unsigned long aligned_len = ALIGN(len + phys_addr - aligned_phys,
1 << r->page_size);
*bus_addr = dma_sb_lpar_to_bus(r, ps3_mm_phys_to_lpar(phys_addr));
@@ -831,7 +831,7 @@ static int dma_ioc0_map_area(struct ps3_dma_region *r, unsigned long virt_addr,
unsigned long phys_addr = is_kernel_addr(virt_addr) ? __pa(virt_addr)
: virt_addr;
unsigned long aligned_phys = ALIGN_DOWN(phys_addr, 1 << r->page_size);
- unsigned long aligned_len = _ALIGN_UP(len + phys_addr - aligned_phys,
+ unsigned long aligned_len = ALIGN(len + phys_addr - aligned_phys,
1 << r->page_size);
DBG(KERN_ERR "%s: vaddr=%#lx, len=%#lx\n", __func__,
@@ -891,7 +891,7 @@ static int dma_sb_unmap_area(struct ps3_dma_region *r, dma_addr_t bus_addr,
if (!c) {
unsigned long aligned_bus = ALIGN_DOWN(bus_addr,
1 << r->page_size);
- unsigned long aligned_len = _ALIGN_UP(len + bus_addr
+ unsigned long aligned_len = ALIGN(len + bus_addr
- aligned_bus, 1 << r->page_size);
DBG("%s:%d: not found: bus_addr %llxh\n",
__func__, __LINE__, bus_addr);
@@ -928,7 +928,7 @@ static int dma_ioc0_unmap_area(struct ps3_dma_region *r,
if (!c) {
unsigned long aligned_bus = ALIGN_DOWN(bus_addr,
1 << r->page_size);
- unsigned long aligned_len = _ALIGN_UP(len + bus_addr
+ unsigned long aligned_len = ALIGN(len + bus_addr
- aligned_bus,
1 << r->page_size);
DBG("%s:%d: not found: bus_addr %llxh\n",
@@ -974,7 +974,7 @@ static int dma_sb_region_create_linear(struct ps3_dma_region *r)
pr_info("%s:%d: forcing 16M pages for linear map\n",
__func__, __LINE__);
r->page_size = PS3_DMA_16M;
- r->len = _ALIGN_UP(r->len, 1 << r->page_size);
+ r->len = ALIGN(r->len, 1 << r->page_size);
}
}
@@ -1125,7 +1125,7 @@ int ps3_dma_region_init(struct ps3_system_bus_device *dev,
r->offset = lpar_addr;
if (r->offset >= map.rm.size)
r->offset -= map.r1.offset;
- r->len = len ? len : _ALIGN_UP(map.total, 1 << r->page_size);
+ r->len = len ? len : ALIGN(map.total, 1 << r->page_size);
switch (dev->dev_type) {
case PS3_DEVICE_TYPE_SB:
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index b29368931c56..e9ae5dd03593 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -138,7 +138,7 @@ static int __init early_parse_ps3fb(char *p)
if (!p)
return 1;
- ps3fb_videomemory.size = _ALIGN_UP(memparse(p, &p),
+ ps3fb_videomemory.size = ALIGN(memparse(p, &p),
ps3fb_videomemory.align);
return 0;
}
--
2.25.0
^ permalink raw reply related
* [PATCH 5/5] powerpc: Remove _ALIGN_UP(), _ALIGN_DOWN() and _ALIGN()
From: Christophe Leroy @ 2020-04-20 18:36 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: alsa-devel, kvm, linux-kernel, dri-devel, linux-fbdev,
linuxppc-dev
In-Reply-To: <a5945463f86c984151962a475a3ee56a2893e85d.1587407777.git.christophe.leroy@c-s.fr>
These three powerpc macros have been replaced by
equivalent generic macros and are not used anymore.
Remove them.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/page.h | 7 -------
1 file changed, 7 deletions(-)
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 3ee8df0f66e0..a63fe6f3a0ff 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -249,13 +249,6 @@ static inline bool pfn_valid(unsigned long pfn)
#include <asm/page_32.h>
#endif
-/* align addr on a size boundary - adjust address up/down if needed */
-#define _ALIGN_UP(addr, size) __ALIGN_KERNEL(addr, size)
-#define _ALIGN_DOWN(addr, size) ((addr)&(~((typeof(addr))(size)-1)))
-
-/* align addr on a size boundary - adjust address up if needed */
-#define _ALIGN(addr,size) _ALIGN_UP(addr,size)
-
/*
* Don't compare things with KERNELBASE or PAGE_OFFSET to test for
* "kernelness", use is_kernel_addr() - it should do what you want.
--
2.25.0
^ permalink raw reply related
* [PATCH 4/5] powerpc: Replace _ALIGN() by ALIGN()
From: Christophe Leroy @ 2020-04-20 18:36 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: alsa-devel, kvm, linux-kernel, dri-devel, linux-fbdev,
linuxppc-dev
In-Reply-To: <a5945463f86c984151962a475a3ee56a2893e85d.1587407777.git.christophe.leroy@c-s.fr>
_ALIGN() is specific to powerpc
ALIGN() is generic and does the same
Replace _ALIGN() by ALIGN()
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/book3s/32/pgtable.h | 2 +-
arch/powerpc/include/asm/nohash/32/pgtable.h | 2 +-
arch/powerpc/kernel/prom_init.c | 8 ++++----
arch/powerpc/platforms/powermac/bootx_init.c | 4 ++--
4 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 53b5c93eaf5d..0d4bccb4b9f2 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -188,7 +188,7 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
* memory shall not share segments.
*/
#if defined(CONFIG_STRICT_KERNEL_RWX) && defined(CONFIG_MODULES)
-#define VMALLOC_START ((_ALIGN((long)high_memory, 256L << 20) + VMALLOC_OFFSET) & \
+#define VMALLOC_START ((ALIGN((long)high_memory, 256L << 20) + VMALLOC_OFFSET) & \
~(VMALLOC_OFFSET - 1))
#else
#define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 5b4d4c4297e1..4315d40906a0 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -110,7 +110,7 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
*/
#define VMALLOC_OFFSET (0x1000000) /* 16M */
#ifdef PPC_PIN_SIZE
-#define VMALLOC_START (((_ALIGN((long)high_memory, PPC_PIN_SIZE) + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
+#define VMALLOC_START (((ALIGN((long)high_memory, PPC_PIN_SIZE) + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
#else
#define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
#endif
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 3a5a7db4564f..e3a9fde51c4f 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -2426,7 +2426,7 @@ static void __init *make_room(unsigned long *mem_start, unsigned long *mem_end,
{
void *ret;
- *mem_start = _ALIGN(*mem_start, align);
+ *mem_start = ALIGN(*mem_start, align);
while ((*mem_start + needed) > *mem_end) {
unsigned long room, chunk;
@@ -2562,7 +2562,7 @@ static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start,
*lp++ = *p;
}
*lp = 0;
- *mem_start = _ALIGN((unsigned long)lp + 1, 4);
+ *mem_start = ALIGN((unsigned long)lp + 1, 4);
}
/* get it again for debugging */
@@ -2608,7 +2608,7 @@ static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start,
/* push property content */
valp = make_room(mem_start, mem_end, l, 4);
call_prom("getprop", 4, 1, node, pname, valp, l);
- *mem_start = _ALIGN(*mem_start, 4);
+ *mem_start = ALIGN(*mem_start, 4);
if (!prom_strcmp(pname, "phandle"))
has_phandle = 1;
@@ -2667,7 +2667,7 @@ static void __init flatten_device_tree(void)
prom_panic ("couldn't get device tree root\n");
/* Build header and make room for mem rsv map */
- mem_start = _ALIGN(mem_start, 4);
+ mem_start = ALIGN(mem_start, 4);
hdr = make_room(&mem_start, &mem_end,
sizeof(struct boot_param_header), 4);
dt_header_start = (unsigned long)hdr;
diff --git a/arch/powerpc/platforms/powermac/bootx_init.c b/arch/powerpc/platforms/powermac/bootx_init.c
index c3374a90952f..9d4ecd292255 100644
--- a/arch/powerpc/platforms/powermac/bootx_init.c
+++ b/arch/powerpc/platforms/powermac/bootx_init.c
@@ -386,7 +386,7 @@ static unsigned long __init bootx_flatten_dt(unsigned long start)
hdr->dt_strings_size = bootx_dt_strend - bootx_dt_strbase;
/* Build structure */
- mem_end = _ALIGN(mem_end, 16);
+ mem_end = ALIGN(mem_end, 16);
DBG("Building device tree structure at: %x\n", mem_end);
hdr->off_dt_struct = mem_end - mem_start;
bootx_scan_dt_build_struct(base, 4, &mem_end);
@@ -404,7 +404,7 @@ static unsigned long __init bootx_flatten_dt(unsigned long start)
* also bump mem_reserve_cnt to cause further reservations to
* fail since it's too late.
*/
- mem_end = _ALIGN(mem_end, PAGE_SIZE);
+ mem_end = ALIGN(mem_end, PAGE_SIZE);
DBG("End of boot params: %x\n", mem_end);
rsvmap[0] = mem_start;
rsvmap[1] = mem_end;
--
2.25.0
^ permalink raw reply related
* [PATCH 2/5] powerpc: Replace _ALIGN_DOWN() by ALIGN_DOWN()
From: Christophe Leroy @ 2020-04-20 18:36 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: alsa-devel, kvm, linux-kernel, dri-devel, linux-fbdev,
linuxppc-dev
In-Reply-To: <a5945463f86c984151962a475a3ee56a2893e85d.1587407777.git.christophe.leroy@c-s.fr>
_ALIGN_DOWN() is specific to powerpc
ALIGN_DOWN() is generic and does the same
Replace _ALIGN_DOWN() by ALIGN_DOWN()
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/book3s/32/pgtable.h | 2 +-
arch/powerpc/include/asm/nohash/32/pgtable.h | 2 +-
arch/powerpc/kernel/pci_64.c | 2 +-
arch/powerpc/kernel/prom.c | 6 +++---
arch/powerpc/kernel/prom_init.c | 8 ++++----
arch/powerpc/mm/book3s64/hash_tlb.c | 4 ++--
arch/powerpc/mm/init_64.c | 4 ++--
arch/powerpc/platforms/powernv/opal-fadump.c | 2 +-
arch/powerpc/platforms/powernv/pci-ioda.c | 2 +-
arch/powerpc/platforms/ps3/mm.c | 14 +++++++-------
arch/powerpc/platforms/pseries/rtas-fadump.c | 2 +-
11 files changed, 24 insertions(+), 24 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 7549393c4c43..53b5c93eaf5d 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -195,7 +195,7 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
#endif
#ifdef CONFIG_KASAN_VMALLOC
-#define VMALLOC_END _ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
+#define VMALLOC_END ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
#else
#define VMALLOC_END ioremap_bot
#endif
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index b04ba257fddb..5b4d4c4297e1 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -116,7 +116,7 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
#endif
#ifdef CONFIG_KASAN_VMALLOC
-#define VMALLOC_END _ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
+#define VMALLOC_END ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
#else
#define VMALLOC_END ioremap_bot
#endif
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index f83d1f69b1dd..e5d05af5a9af 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -130,7 +130,7 @@ static int pcibios_map_phb_io_space(struct pci_controller *hose)
unsigned long size_page;
unsigned long io_virt_offset;
- phys_page = _ALIGN_DOWN(hose->io_base_phys, PAGE_SIZE);
+ phys_page = ALIGN_DOWN(hose->io_base_phys, PAGE_SIZE);
size_page = _ALIGN_UP(hose->pci_io_size, PAGE_SIZE);
/* Make sure IO area address is clear */
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 6620f37abe73..10b5d5eafd34 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -96,7 +96,7 @@ static inline int overlaps_initrd(unsigned long start, unsigned long size)
if (!initrd_start)
return 0;
- return (start + size) > _ALIGN_DOWN(initrd_start, PAGE_SIZE) &&
+ return (start + size) > ALIGN_DOWN(initrd_start, PAGE_SIZE) &&
start <= _ALIGN_UP(initrd_end, PAGE_SIZE);
#else
return 0;
@@ -623,9 +623,9 @@ static void __init early_reserve_mem(void)
#ifdef CONFIG_BLK_DEV_INITRD
/* Then reserve the initrd, if any */
if (initrd_start && (initrd_end > initrd_start)) {
- memblock_reserve(_ALIGN_DOWN(__pa(initrd_start), PAGE_SIZE),
+ memblock_reserve(ALIGN_DOWN(__pa(initrd_start), PAGE_SIZE),
_ALIGN_UP(initrd_end, PAGE_SIZE) -
- _ALIGN_DOWN(initrd_start, PAGE_SIZE));
+ ALIGN_DOWN(initrd_start, PAGE_SIZE));
}
#endif /* CONFIG_BLK_DEV_INITRD */
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 806be751c336..4cf5958eebd4 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1500,7 +1500,7 @@ static unsigned long __init alloc_down(unsigned long size, unsigned long align,
if (highmem) {
/* Carve out storage for the TCE table. */
- addr = _ALIGN_DOWN(alloc_top_high - size, align);
+ addr = ALIGN_DOWN(alloc_top_high - size, align);
if (addr <= alloc_bottom)
return 0;
/* Will we bump into the RMO ? If yes, check out that we
@@ -1518,9 +1518,9 @@ static unsigned long __init alloc_down(unsigned long size, unsigned long align,
goto bail;
}
- base = _ALIGN_DOWN(alloc_top - size, align);
+ base = ALIGN_DOWN(alloc_top - size, align);
for (; base > alloc_bottom;
- base = _ALIGN_DOWN(base - 0x100000, align)) {
+ base = ALIGN_DOWN(base - 0x100000, align)) {
prom_debug(" trying: 0x%lx\n\r", base);
addr = (unsigned long)prom_claim(base, size, 0);
if (addr != PROM_ERROR && addr != 0)
@@ -1586,7 +1586,7 @@ static void __init reserve_mem(u64 base, u64 size)
* have our terminator with "size" set to 0 since we are
* dumb and just copy this entire array to the boot params
*/
- base = _ALIGN_DOWN(base, PAGE_SIZE);
+ base = ALIGN_DOWN(base, PAGE_SIZE);
top = _ALIGN_UP(top, PAGE_SIZE);
size = top - base;
diff --git a/arch/powerpc/mm/book3s64/hash_tlb.c b/arch/powerpc/mm/book3s64/hash_tlb.c
index 4a70d8dd39cd..2242d022b620 100644
--- a/arch/powerpc/mm/book3s64/hash_tlb.c
+++ b/arch/powerpc/mm/book3s64/hash_tlb.c
@@ -196,7 +196,7 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
int hugepage_shift;
unsigned long flags;
- start = _ALIGN_DOWN(start, PAGE_SIZE);
+ start = ALIGN_DOWN(start, PAGE_SIZE);
end = _ALIGN_UP(end, PAGE_SIZE);
BUG_ON(!mm->pgd);
@@ -238,7 +238,7 @@ void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr)
pte_t *start_pte;
unsigned long flags;
- addr = _ALIGN_DOWN(addr, PMD_SIZE);
+ addr = ALIGN_DOWN(addr, PMD_SIZE);
/*
* Note: Normally, we should only ever use a batch within a
* PTE locked section. This violates the rule, but will work
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 4002ced3596f..c7ce4ec5060e 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -203,7 +203,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
/* Align to the page size of the linear mapping. */
- start = _ALIGN_DOWN(start, page_size);
+ start = ALIGN_DOWN(start, page_size);
pr_debug("vmemmap_populate %lx..%lx, node %d\n", start, end, node);
@@ -292,7 +292,7 @@ void __ref vmemmap_free(unsigned long start, unsigned long end,
unsigned long alt_start = ~0, alt_end = ~0;
unsigned long base_pfn;
- start = _ALIGN_DOWN(start, page_size);
+ start = ALIGN_DOWN(start, page_size);
if (altmap) {
alt_start = altmap->base_pfn;
alt_end = altmap->base_pfn + altmap->reserve +
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c
index d361d37d975f..9a360ced663b 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.c
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -671,7 +671,7 @@ void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
* Firmware supports 32-bit field for size. Align it to PAGE_SIZE
* and request firmware to copy multiple kernel boot memory regions.
*/
- fadump_conf->max_copy_size = _ALIGN_DOWN(U32_MAX, PAGE_SIZE);
+ fadump_conf->max_copy_size = ALIGN_DOWN(U32_MAX, PAGE_SIZE);
/*
* Check if dump has been initiated on last reboot.
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 57d3a6af1d52..276b011cd45d 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -264,7 +264,7 @@ static void pnv_ioda_reserve_dev_m64_pe(struct pci_dev *pdev,
if (!r->parent || !pnv_pci_is_m64(phb, r))
continue;
- start = _ALIGN_DOWN(r->start - base, sgsz);
+ start = ALIGN_DOWN(r->start - base, sgsz);
end = _ALIGN_UP(r->end - base, sgsz);
for (segno = start / sgsz; segno < end / sgsz; segno++) {
if (pe_bitmap)
diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c
index 423be34f0f5f..71ed37f7f475 100644
--- a/arch/powerpc/platforms/ps3/mm.c
+++ b/arch/powerpc/platforms/ps3/mm.c
@@ -263,7 +263,7 @@ static int ps3_mm_region_create(struct mem_region *r, unsigned long size)
int result;
u64 muid;
- r->size = _ALIGN_DOWN(size, 1 << PAGE_SHIFT_16M);
+ r->size = ALIGN_DOWN(size, 1 << PAGE_SHIFT_16M);
DBG("%s:%d requested %lxh\n", __func__, __LINE__, size);
DBG("%s:%d actual %llxh\n", __func__, __LINE__, r->size);
@@ -394,7 +394,7 @@ static struct dma_chunk * dma_find_chunk(struct ps3_dma_region *r,
unsigned long bus_addr, unsigned long len)
{
struct dma_chunk *c;
- unsigned long aligned_bus = _ALIGN_DOWN(bus_addr, 1 << r->page_size);
+ unsigned long aligned_bus = ALIGN_DOWN(bus_addr, 1 << r->page_size);
unsigned long aligned_len = _ALIGN_UP(len+bus_addr-aligned_bus,
1 << r->page_size);
@@ -423,7 +423,7 @@ static struct dma_chunk *dma_find_chunk_lpar(struct ps3_dma_region *r,
unsigned long lpar_addr, unsigned long len)
{
struct dma_chunk *c;
- unsigned long aligned_lpar = _ALIGN_DOWN(lpar_addr, 1 << r->page_size);
+ unsigned long aligned_lpar = ALIGN_DOWN(lpar_addr, 1 << r->page_size);
unsigned long aligned_len = _ALIGN_UP(len + lpar_addr - aligned_lpar,
1 << r->page_size);
@@ -775,7 +775,7 @@ static int dma_sb_map_area(struct ps3_dma_region *r, unsigned long virt_addr,
struct dma_chunk *c;
unsigned long phys_addr = is_kernel_addr(virt_addr) ? __pa(virt_addr)
: virt_addr;
- unsigned long aligned_phys = _ALIGN_DOWN(phys_addr, 1 << r->page_size);
+ unsigned long aligned_phys = ALIGN_DOWN(phys_addr, 1 << r->page_size);
unsigned long aligned_len = _ALIGN_UP(len + phys_addr - aligned_phys,
1 << r->page_size);
*bus_addr = dma_sb_lpar_to_bus(r, ps3_mm_phys_to_lpar(phys_addr));
@@ -830,7 +830,7 @@ static int dma_ioc0_map_area(struct ps3_dma_region *r, unsigned long virt_addr,
struct dma_chunk *c;
unsigned long phys_addr = is_kernel_addr(virt_addr) ? __pa(virt_addr)
: virt_addr;
- unsigned long aligned_phys = _ALIGN_DOWN(phys_addr, 1 << r->page_size);
+ unsigned long aligned_phys = ALIGN_DOWN(phys_addr, 1 << r->page_size);
unsigned long aligned_len = _ALIGN_UP(len + phys_addr - aligned_phys,
1 << r->page_size);
@@ -889,7 +889,7 @@ static int dma_sb_unmap_area(struct ps3_dma_region *r, dma_addr_t bus_addr,
c = dma_find_chunk(r, bus_addr, len);
if (!c) {
- unsigned long aligned_bus = _ALIGN_DOWN(bus_addr,
+ unsigned long aligned_bus = ALIGN_DOWN(bus_addr,
1 << r->page_size);
unsigned long aligned_len = _ALIGN_UP(len + bus_addr
- aligned_bus, 1 << r->page_size);
@@ -926,7 +926,7 @@ static int dma_ioc0_unmap_area(struct ps3_dma_region *r,
c = dma_find_chunk(r, bus_addr, len);
if (!c) {
- unsigned long aligned_bus = _ALIGN_DOWN(bus_addr,
+ unsigned long aligned_bus = ALIGN_DOWN(bus_addr,
1 << r->page_size);
unsigned long aligned_len = _ALIGN_UP(len + bus_addr
- aligned_bus,
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.c b/arch/powerpc/platforms/pseries/rtas-fadump.c
index 70c3013fdd07..81343908ed33 100644
--- a/arch/powerpc/platforms/pseries/rtas-fadump.c
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.c
@@ -506,7 +506,7 @@ void __init rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node)
fadump_conf->fadump_supported = 1;
/* Firmware supports 64-bit value for size, align it to pagesize. */
- fadump_conf->max_copy_size = _ALIGN_DOWN(U64_MAX, PAGE_SIZE);
+ fadump_conf->max_copy_size = ALIGN_DOWN(U64_MAX, PAGE_SIZE);
/*
* The 'ibm,kernel-dump' rtas node is present only if there is
--
2.25.0
^ permalink raw reply related
* Re: [PATCH v3 3/4] hugetlbfs: remove hugetlb_add_hstate() warning for existing hstate
From: Anders Roxell @ 2020-04-20 19:41 UTC (permalink / raw)
To: Mike Kravetz
Cc: linux-doc, Catalin Marinas, Dave Hansen, Heiko Carstens, Peter Xu,
linux-mm, Paul Mackerras, sparclinux, linux-riscv, Will Deacon,
Mina Almasry, linux-s390, Jonathan Corbet, Christian Borntraeger,
Ingo Molnar, Longpeng, Albert Ou, Vasily Gorbik, Paul Walmsley,
Thomas Gleixner, Linux ARM, Nitesh Narayan Lal, Randy Dunlap,
Linux Kernel Mailing List, Palmer Dabbelt, Andrew Morton,
linuxppc-dev, David S . Miller
In-Reply-To: <20200417185049.275845-4-mike.kravetz@oracle.com>
On Fri, 17 Apr 2020 at 20:52, Mike Kravetz <mike.kravetz@oracle.com> wrote:
>
> The routine hugetlb_add_hstate prints a warning if the hstate already
> exists. This was originally done as part of kernel command line
> parsing. If 'hugepagesz=' was specified more than once, the warning
> pr_warn("hugepagesz= specified twice, ignoring\n");
> would be printed.
>
> Some architectures want to enable all huge page sizes. They would
> call hugetlb_add_hstate for all supported sizes. However, this was
> done after command line processing and as a result hstates could have
> already been created for some sizes. To make sure no warning were
> printed, there would often be code like:
> if (!size_to_hstate(size)
> hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT)
>
> The only time we want to print the warning is as the result of command
> line processing. So, remove the warning from hugetlb_add_hstate and
> add it to the single arch independent routine processing "hugepagesz=".
> After this, calls to size_to_hstate() in arch specific code can be
> removed and hugetlb_add_hstate can be called without worrying about
> warning messages.
>
> Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
> Acked-by: Mina Almasry <almasrymina@google.com>
When I build an arm64 kernel on today's next-20200420 and ran that in
qemu I got the following output [1]:
...
[ 311.326817][ T1] kobject: 'drivers' ((____ptrval____)):
kobject_add_internal: parent: 'coresight', set: '<NULL>'
[ 311.331513][ T1] kobject: 'drivers' ((____ptrval____)): kobject_uevent_env
[ 311.334514][ T1] kobject: 'drivers' ((____ptrval____)):
kobject_uevent_env: filter function caused the event to drop!
[ 311.340127][ T1] bus: 'coresight': registered
[ 311.342228][ T1] initcall coresight_init+0x0/0x64 returned 0
after 27343 usecs
[ 311.349740][ T1] calling debug_traps_init+0x0/0xa4 @ 1
[ 311.352138][ T1] initcall debug_traps_init+0x0/0xa4 returned 0
after 0 usecs
[ 311.355550][ T1] calling reserve_memblock_reserved_regions+0x0/0x374 @ 1
[ 311.364913][ T1] initcall
reserve_memblock_reserved_regions+0x0/0x374 returned 0 after 7812
usecs
[ 311.368937][ T1] calling aarch32_alloc_vdso_pages+0x0/0x1d0 @ 1
[ 311.371819][ T1] initcall aarch32_alloc_vdso_pages+0x0/0x1d0
returned 0 after 0 usecs
[ 311.375608][ T1] calling vdso_init+0x0/0x52c @ 1
[ 311.378092][ T1] initcall vdso_init+0x0/0x52c returned 0 after 0 usecs
[ 311.381386][ T1] calling arch_hw_breakpoint_init+0x0/0x178 @ 1
[ 311.384007][ T1] hw-breakpoint: found 6 breakpoint and 4
watchpoint registers.
[ 311.388120][ T1] initcall arch_hw_breakpoint_init+0x0/0x178
returned 0 after 3906 usecs
[ 311.391924][ T1] calling asids_update_limit+0x0/0x110 @ 1
[ 311.394390][ T1] ASID allocator initialised with 65536 entries
[ 311.397427][ T1] initcall asids_update_limit+0x0/0x110 returned
0 after 3906 usecs
[ 311.400749][ T1] calling hugetlbpage_init+0x0/0x7c @ 1
[ 311.403581][ T1] Unexpected kernel BRK exception at EL1
[ 311.405771][ T1] Internal error: ptrace BRK handler: f20003e8
[#1] PREEMPT SMP
[ 311.408759][ T1] Modules linked in:
[ 311.410514][ T1] CPU: 0 PID: 1 Comm: swapper/0 Tainted: G
T 5.7.0-rc2-next-20200420-03722-ge4ba9b47e4ed #1
[ 311.415175][ T1] Hardware name: linux,dummy-virt (DT)
[ 311.417466][ T1] pstate: 80400005 (Nzcv daif +PAN -UAO)
[ 311.419887][ T1] pc : hugetlb_add_hstate+0x68/0x4f0
[ 311.422171][ T1] lr : hugetlb_add_hstate+0x68/0x4f0
[ 311.424354][ T1] sp : ffff000069c07c60
[ 311.426124][ T1] x29: ffff000069c07c60 x28: ffff00006a7f8058
[ 311.428754][ T1] x27: 0000000000000000 x26: ffffa00013f56950
[ 311.431376][ T1] x25: ffffa000141b8000 x24: ffff00006a7f8040
[ 311.433987][ T1] x23: 1fffe0000d380fae x22: 00000000fffffff8
[ 311.436574][ T1] x21: 0000000100000000 x20: ffffa000141b8000
[ 311.439167][ T1] x19: ec632d51be3d2507 x18: 0000000000001a68
[ 311.441763][ T1] x17: 00000000000013e0 x16: 0000000000001a94
[ 311.444386][ T1] x15: 0000000000001a68 x14: 6573752036303933
[ 311.447034][ T1] x13: 2072657466612030 x12: 00000000000025b0
[ 311.449639][ T1] x11: 00000000f1f1f1f1 x10: 0000000041b58ab3
[ 311.452238][ T1] x9 : ffffa000139a833c x8 : 1ffff40002bf2c23
[ 311.454849][ T1] x7 : ffff940002bf2c23 x6 : ffffa00015f9611b
[ 311.457480][ T1] x5 : ffff00006a7f8040 x4 : 0000000000000000
[ 311.460124][ T1] x3 : ffffa000139fd98c x2 : 00000000fffffff8
[ 311.462737][ T1] x1 : ffff00006a7f8040 x0 : 0000000000000000
[ 311.465322][ T1] Call trace:
[ 311.466818][ T1] hugetlb_add_hstate+0x68/0x4f0
[ 311.468934][ T1] hugetlbpage_init+0x34/0x7c
[ 311.470934][ T1] do_one_initcall+0x480/0xa40
[ 311.472996][ T1] kernel_init_freeable+0x7a0/0x968
[ 311.475224][ T1] kernel_init+0x20/0x1f8
[ 311.477078][ T1] ret_from_fork+0x10/0x18
[ 311.479053][ T1] Code: 972762be 7100fedf 54000069 97276197 (d4207d00)
[ 311.482106][ T1] _warn_unseeded_randomness: 18 callbacks suppressed
[ 311.482255][ T1] random: get_random_bytes called from
print_oops_end_marker+0x48/0x80 with crng_init=0
[ 311.482321][ T1] ---[ end trace 60df362baad50718 ]---
[ 311.491423][ T1] Kernel panic - not syncing: Fatal exception
[ 311.494038][ T1] ---[ end Kernel panic - not syncing: Fatal exception ]---
If I revert this patch I can't see the problem anymore...
Any idea what happens?
This is the kernel.config [1] I'm using, its from an allmodconfig kernel build
Cheers,
Anders
[1] https://people.linaro.org/~anders.roxell/output-next-20200420.log
[2] https://builds.tuxbuild.com/U7ufblLydTsSvle27GSPAA/kernel.config
> ---
> arch/arm64/mm/hugetlbpage.c | 16 ++++------------
> arch/powerpc/mm/hugetlbpage.c | 3 +--
> arch/riscv/mm/hugetlbpage.c | 2 +-
> arch/sparc/mm/init_64.c | 19 ++++---------------
> arch/x86/mm/hugetlbpage.c | 2 +-
> mm/hugetlb.c | 9 ++++++---
> 6 files changed, 17 insertions(+), 34 deletions(-)
>
> diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
> index f706b821aba6..21fa98b51e00 100644
> --- a/arch/arm64/mm/hugetlbpage.c
> +++ b/arch/arm64/mm/hugetlbpage.c
> @@ -441,22 +441,14 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma,
> clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
> }
>
> -static void __init add_huge_page_size(unsigned long size)
> -{
> - if (size_to_hstate(size))
> - return;
> -
> - hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT);
> -}
> -
> static int __init hugetlbpage_init(void)
> {
> #ifdef CONFIG_ARM64_4K_PAGES
> - add_huge_page_size(PUD_SIZE);
> + hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
> #endif
> - add_huge_page_size(CONT_PMD_SIZE);
> - add_huge_page_size(PMD_SIZE);
> - add_huge_page_size(CONT_PTE_SIZE);
> + hugetlb_add_hstate(CONT_PMD_SHIFT - PAGE_SHIFT);
> + hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
> + hugetlb_add_hstate(CONT_PTE_SHIFT - PAGE_SHIFT);
>
> return 0;
> }
> diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
> index 2c3fa0a7787b..4d5ed1093615 100644
> --- a/arch/powerpc/mm/hugetlbpage.c
> +++ b/arch/powerpc/mm/hugetlbpage.c
> @@ -584,8 +584,7 @@ static int __init add_huge_page_size(unsigned long long size)
> if (!arch_hugetlb_valid_size((unsigned long)size))
> return -EINVAL;
>
> - if (!size_to_hstate(size))
> - hugetlb_add_hstate(shift - PAGE_SHIFT);
> + hugetlb_add_hstate(shift - PAGE_SHIFT);
> return 0;
> }
>
> diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
> index 4e5d7e9f0eef..932dadfdca54 100644
> --- a/arch/riscv/mm/hugetlbpage.c
> +++ b/arch/riscv/mm/hugetlbpage.c
> @@ -26,7 +26,7 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
> static __init int gigantic_pages_init(void)
> {
> /* With CONTIG_ALLOC, we can allocate gigantic pages at runtime */
> - if (IS_ENABLED(CONFIG_64BIT) && !size_to_hstate(1UL << PUD_SHIFT))
> + if (IS_ENABLED(CONFIG_64BIT))
> hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
> return 0;
> }
> diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
> index 4618f96fd30f..ae819a16d07a 100644
> --- a/arch/sparc/mm/init_64.c
> +++ b/arch/sparc/mm/init_64.c
> @@ -325,23 +325,12 @@ static void __update_mmu_tsb_insert(struct mm_struct *mm, unsigned long tsb_inde
> }
>
> #ifdef CONFIG_HUGETLB_PAGE
> -static void __init add_huge_page_size(unsigned long size)
> -{
> - unsigned int order;
> -
> - if (size_to_hstate(size))
> - return;
> -
> - order = ilog2(size) - PAGE_SHIFT;
> - hugetlb_add_hstate(order);
> -}
> -
> static int __init hugetlbpage_init(void)
> {
> - add_huge_page_size(1UL << HPAGE_64K_SHIFT);
> - add_huge_page_size(1UL << HPAGE_SHIFT);
> - add_huge_page_size(1UL << HPAGE_256MB_SHIFT);
> - add_huge_page_size(1UL << HPAGE_2GB_SHIFT);
> + hugetlb_add_hstate(HPAGE_64K_SHIFT - PAGE_SHIFT);
> + hugetlb_add_hstate(HPAGE_SHIFT - PAGE_SHIFT);
> + hugetlb_add_hstate(HPAGE_256MB_SHIFT - PAGE_SHIFT);
> + hugetlb_add_hstate(HPAGE_2GB_SHIFT - PAGE_SHIFT);
>
> return 0;
> }
> diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
> index 937d640a89e3..cf5781142716 100644
> --- a/arch/x86/mm/hugetlbpage.c
> +++ b/arch/x86/mm/hugetlbpage.c
> @@ -195,7 +195,7 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
> static __init int gigantic_pages_init(void)
> {
> /* With compaction or CMA we can allocate gigantic pages at runtime */
> - if (boot_cpu_has(X86_FEATURE_GBPAGES) && !size_to_hstate(1UL << PUD_SHIFT))
> + if (boot_cpu_has(X86_FEATURE_GBPAGES))
> hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
> return 0;
> }
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index b2d276408cec..0e6eb755ae94 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -3222,8 +3222,7 @@ static int __init hugetlb_init(void)
> }
>
> default_hstate_size = HPAGE_SIZE;
> - if (!size_to_hstate(default_hstate_size))
> - hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
> + hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
> }
> default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size));
> if (default_hstate_max_huge_pages) {
> @@ -3268,7 +3267,6 @@ void __init hugetlb_add_hstate(unsigned int order)
> unsigned long i;
>
> if (size_to_hstate(PAGE_SIZE << order)) {
> - pr_warn("hugepagesz= specified twice, ignoring\n");
> return;
> }
> BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE);
> @@ -3343,6 +3341,11 @@ static int __init hugepagesz_setup(char *s)
> return 0;
> }
>
> + if (size_to_hstate(size)) {
> + pr_warn("HugeTLB: hugepagesz %s specified twice, ignoring\n", s);
> + return 0;
> + }
> +
> hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT);
> return 1;
> }
> --
> 2.25.2
>
^ permalink raw reply
* Re: crash in cpuidle_enter_state with 5.7-rc1
From: Michal Suchánek @ 2020-04-20 19:41 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev
In-Reply-To: <20200420065030.GL25468@kitsune.suse.cz>
On Mon, Apr 20, 2020 at 08:50:30AM +0200, Michal Suchánek wrote:
> Hello,
>
> On Mon, Apr 20, 2020 at 04:15:39PM +1000, Michael Ellerman wrote:
> > Michal Suchánek <msuchanek@suse.de> writes:
...
> >
> >
> > And I've just hit it with your config on a machine here, but the crash
> > is different:
> That does not look like it.
> You don't have this part in the stack trace:
> > [ 1.234899] [c000000007597420] [0000000000000000] 0x0
> > [ 1.234908] [c000000007597720] [0000000000000a6d] 0xa6d
> > [ 1.234919] [c000000007597a20] [0000000000000000] 0x0
> > [ 1.234931] [c000000007597d20] [0000000000000004] 0x4
> which is somewhat random but at least on such line is always present in
> the traces I get. Also I always get crash in cpuidle_enter_state
..
> > I'm going to guess it's STRICT_KERNEL_RWX that's at fault.
> I can try without that as well.
Can't reproduce without STRICT_KERNEL_RWX either.
Thanks
Michal
^ permalink raw reply
* Re: [PATCH v3 0/4] Clean up hugetlb boot command line processing
From: Will Deacon @ 2020-04-20 19:45 UTC (permalink / raw)
To: Mike Kravetz
Cc: linux-doc, Catalin Marinas, Dave Hansen, Heiko Carstens, Peter Xu,
Linux-MM, Paul Mackerras, sparclinux, linux-riscv, Mina Almasry,
linux-s390, Jonathan Corbet, Christian Borntraeger, Ingo Molnar,
Longpeng, Albert Ou, Vasily Gorbik, Qian Cai, Paul Walmsley,
Thomas Gleixner, linux-arm-kernel, Nitesh Narayan Lal,
Randy Dunlap, LKML, Palmer Dabbelt, Andrew Morton, linuxppc-dev,
David S.Miller
In-Reply-To: <4c36c6ce-3774-78fa-abc4-b7346bf24348@oracle.com>
On Mon, Apr 20, 2020 at 11:20:23AM -0700, Mike Kravetz wrote:
> On 4/20/20 8:34 AM, Qian Cai wrote:
> >
> >
> >> On Apr 17, 2020, at 2:50 PM, Mike Kravetz <mike.kravetz@oracle.com> wrote:
> >>
> >> 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
> >
> > Reverted this series fixed many undefined behaviors on arm64 with the config,
> >
> > https://raw.githubusercontent.com/cailca/linux-mm/master/arm64.config
> >
> > [ 54.172683][ T1] UBSAN: shift-out-of-bounds in ./include/linux/hugetlb.h:555:34
> > [ 54.180411][ T1] shift exponent 4294967285 is too large for 64-bit type 'unsigned long'
> > [ 54.188885][ T1] CPU: 130 PID: 1 Comm: swapper/0 Not tainted 5.7.0-rc2-next-20200420 #1
> > [ 54.197284][ T1] Hardware name: HPE Apollo 70 /C01_APACHE_MB , BIOS L50_5.13_1.11 06/18/2019
> > [ 54.207888][ T1] Call trace:
> > [ 54.211100][ T1] dump_backtrace+0x0/0x224
> > [ 54.215565][ T1] show_stack+0x20/0x2c
> > [ 54.219651][ T1] dump_stack+0xfc/0x184
> > [ 54.223829][ T1] __ubsan_handle_shift_out_of_bounds+0x304/0x344
> > [ 54.230204][ T1] hugetlb_add_hstate+0x3ec/0x414
> > huge_page_size at include/linux/hugetlb.h:555
> > (inlined by) hugetlb_add_hstate at mm/hugetlb.c:3301
> > [ 54.235191][ T1] hugetlbpage_init+0x14/0x30
> > [ 54.239824][ T1] do_one_initcall+0x6c/0x144
> > [ 54.244446][ T1] do_initcall_level+0x158/0x1c4
> > [ 54.249336][ T1] do_initcalls+0x68/0xb0
> > [ 54.253597][ T1] do_basic_setup+0x28/0x30
> > [ 54.258049][ T1] kernel_init_freeable+0x19c/0x228
> > [ 54.263188][ T1] kernel_init+0x14/0x208
> > [ 54.267473][ T1] ret_from_fork+0x10/0x18
>
> While rearranging the code (patch 3 in series), I made the incorrect
> assumption that CONT_XXX_SIZE == (1UL << CONT_XXX_SHIFT). However,
> this is not the case. Does the following patch fix these issues?
>
> From b75cb4a0852e208bee8c4eb347dc076fcaa88859 Mon Sep 17 00:00:00 2001
> From: Mike Kravetz <mike.kravetz@oracle.com>
> Date: Mon, 20 Apr 2020 10:41:18 -0700
> Subject: [PATCH] arm64/hugetlb: fix hugetlb initialization
>
> When calling hugetlb_add_hstate() to initialize a new hugetlb size,
> be sure to use correct huge pages size order.
>
> Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
> ---
> arch/arm64/mm/hugetlbpage.c | 8 ++++----
> 1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
> index 9ca840527296..a02411a1f19a 100644
> --- a/arch/arm64/mm/hugetlbpage.c
> +++ b/arch/arm64/mm/hugetlbpage.c
> @@ -453,11 +453,11 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma,
> static int __init hugetlbpage_init(void)
> {
> #ifdef CONFIG_ARM64_4K_PAGES
> - hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
> + hugetlb_add_hstate(ilog2(PUD_SIZE) - PAGE_SHIFT);
> #endif
> - hugetlb_add_hstate(CONT_PMD_SHIFT - PAGE_SHIFT);
> - hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
> - hugetlb_add_hstate(CONT_PTE_SHIFT - PAGE_SHIFT);
> + hugetlb_add_hstate(ilog2(CONT_PMD_SIZE) - PAGE_SHIFT);
> + hugetlb_add_hstate(ilog2(PMD_SIZE) - PAGE_SHIFT);
> + hugetlb_add_hstate(ilog2(CONT_PTE_SIZE) - PAGE_SHIFT);
Might be clearer to leave the non CONT_* definitions alone and instead
convert the CONT versions along the lines of:
hugetlb_add_hstate(CONT_PMD_SHIFT + PMD_SHIFT - PAGE_SHIFT);
(untested, but I think that's right...)
But that doesn't matter until Qian has confirmed that your patch fixes the
issue.
Will
^ permalink raw reply
* Re: [PATCH v7 0/7] powerpc: switch VDSO to C implementation
From: Arnd Bergmann @ 2020-04-20 19:57 UTC (permalink / raw)
To: Christophe Leroy
Cc: Nathan Lynch, linux-kernel@vger.kernel.org, Paul Mackerras,
Andy Lutomirski, Thomas Gleixner, Vincenzo Frascino, linuxppc-dev
In-Reply-To: <cover.1587401492.git.christophe.leroy@c-s.fr>
On Mon, Apr 20, 2020 at 6:56 PM Christophe Leroy
<christophe.leroy@c-s.fr> wrote:
>
> This is the seventh version of a series to switch powerpc VDSO to
> generic C implementation.
>
> Main changes since v6 are:
> - Added -fasynchronous-unwind-tables in CFLAGS
> - Split patch 2 in two parts
> - Split patch 5 (which was patch 4) in two parts
>
> This series applies on today's powerpc/merge branch.
>
> See the last two patches for details on changes and performance.
>
> Christophe Leroy (7):
> 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.
This all looks fine, but I'm a bit puzzled why you don't add a
clock_gettime64() implementation in the same series. Isn't
that the main purpose of doing all that work?
Without it, any 32-bit user space has to go through the system call
for time()/getttimeofday()/clock_gettime() when built with a
modern libc.
Arnd
^ permalink raw reply
* Re: [PATCH v3 0/4] Clean up hugetlb boot command line processing
From: Anders Roxell @ 2020-04-20 20:29 UTC (permalink / raw)
To: Mike Kravetz
Cc: linux-doc, Catalin Marinas, Dave Hansen, Heiko Carstens, Peter Xu,
Linux-MM, Paul Mackerras, sparclinux, linux-riscv, Will Deacon,
Mina Almasry, linux-s390, Jonathan Corbet, Christian Borntraeger,
Ingo Molnar, Longpeng, Albert Ou, Vasily Gorbik, Qian Cai,
Paul Walmsley, Thomas Gleixner, Linux ARM, Nitesh Narayan Lal,
Randy Dunlap, LKML, Palmer Dabbelt, Andrew Morton, linuxppc-dev,
David S.Miller
In-Reply-To: <4c36c6ce-3774-78fa-abc4-b7346bf24348@oracle.com>
On Mon, 20 Apr 2020 at 20:23, Mike Kravetz <mike.kravetz@oracle.com> wrote:
>
> On 4/20/20 8:34 AM, Qian Cai wrote:
> >
> >
> >> On Apr 17, 2020, at 2:50 PM, Mike Kravetz <mike.kravetz@oracle.com> wrote:
> >>
> >> 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
> >
> > Reverted this series fixed many undefined behaviors on arm64 with the config,
> >
> > https://raw.githubusercontent.com/cailca/linux-mm/master/arm64.config
> >
> > [ 54.172683][ T1] UBSAN: shift-out-of-bounds in ./include/linux/hugetlb.h:555:34
> > [ 54.180411][ T1] shift exponent 4294967285 is too large for 64-bit type 'unsigned long'
> > [ 54.188885][ T1] CPU: 130 PID: 1 Comm: swapper/0 Not tainted 5.7.0-rc2-next-20200420 #1
> > [ 54.197284][ T1] Hardware name: HPE Apollo 70 /C01_APACHE_MB , BIOS L50_5.13_1.11 06/18/2019
> > [ 54.207888][ T1] Call trace:
> > [ 54.211100][ T1] dump_backtrace+0x0/0x224
> > [ 54.215565][ T1] show_stack+0x20/0x2c
> > [ 54.219651][ T1] dump_stack+0xfc/0x184
> > [ 54.223829][ T1] __ubsan_handle_shift_out_of_bounds+0x304/0x344
> > [ 54.230204][ T1] hugetlb_add_hstate+0x3ec/0x414
> > huge_page_size at include/linux/hugetlb.h:555
> > (inlined by) hugetlb_add_hstate at mm/hugetlb.c:3301
> > [ 54.235191][ T1] hugetlbpage_init+0x14/0x30
> > [ 54.239824][ T1] do_one_initcall+0x6c/0x144
> > [ 54.244446][ T1] do_initcall_level+0x158/0x1c4
> > [ 54.249336][ T1] do_initcalls+0x68/0xb0
> > [ 54.253597][ T1] do_basic_setup+0x28/0x30
> > [ 54.258049][ T1] kernel_init_freeable+0x19c/0x228
> > [ 54.263188][ T1] kernel_init+0x14/0x208
> > [ 54.267473][ T1] ret_from_fork+0x10/0x18
>
> While rearranging the code (patch 3 in series), I made the incorrect
> assumption that CONT_XXX_SIZE == (1UL << CONT_XXX_SHIFT). However,
> this is not the case. Does the following patch fix these issues?
>
> From b75cb4a0852e208bee8c4eb347dc076fcaa88859 Mon Sep 17 00:00:00 2001
> From: Mike Kravetz <mike.kravetz@oracle.com>
> Date: Mon, 20 Apr 2020 10:41:18 -0700
> Subject: [PATCH] arm64/hugetlb: fix hugetlb initialization
>
> When calling hugetlb_add_hstate() to initialize a new hugetlb size,
> be sure to use correct huge pages size order.
>
> Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
> ---
> arch/arm64/mm/hugetlbpage.c | 8 ++++----
> 1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
> index 9ca840527296..a02411a1f19a 100644
> --- a/arch/arm64/mm/hugetlbpage.c
> +++ b/arch/arm64/mm/hugetlbpage.c
> @@ -453,11 +453,11 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma,
> static int __init hugetlbpage_init(void)
> {
> #ifdef CONFIG_ARM64_4K_PAGES
> - hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
> + hugetlb_add_hstate(ilog2(PUD_SIZE) - PAGE_SHIFT);
> #endif
> - hugetlb_add_hstate(CONT_PMD_SHIFT - PAGE_SHIFT);
> - hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
> - hugetlb_add_hstate(CONT_PTE_SHIFT - PAGE_SHIFT);
> + hugetlb_add_hstate(ilog2(CONT_PMD_SIZE) - PAGE_SHIFT);
> + hugetlb_add_hstate(ilog2(PMD_SIZE) - PAGE_SHIFT);
> + hugetlb_add_hstate(ilog2(CONT_PTE_SIZE) - PAGE_SHIFT);
>
> return 0;
> }
I build this for an arm64 kernel and ran it in qemu and it worked.
Cheers,
Anders
^ permalink raw reply
* Re: [RFC PATCH v1 40/50] arch/*/include/asm/stackprotector.h: Use get_random_canary() consistently
From: Will Deacon @ 2020-04-20 20:42 UTC (permalink / raw)
To: George Spelvin
Cc: Rich Felker, linux-sh, linux-mips, Max Filippov, Paul Mackerras,
H. Peter Anvin, Yoshinori Sato, x86, Russell King, Ingo Molnar,
Catalin Marinas, James Hogan, linux-xtensa, Borislav Petkov,
Thomas Gleixner, linux-arm-kernel, Chris Zankel, Paul Burton,
linux-kernel, Ralf Baechle, linuxppc-dev
In-Reply-To: <202003281643.02SGhM0T009250@sdf.org>
On Tue, Dec 10, 2019 at 12:35:14AM -0500, George Spelvin wrote:
> ... in boot_init_stack_canary().
>
> This is the archetypical example of where the extra security of
> get_random_bytes() is wasted. The canary is only important as
> long as it's stored in __stack_chk_guard.
>
> It's also a great example of code that has been copied around
> a lot and not updated.
>
> Remove the XOR with LINUX_VERSION_CODE as it's pointless; the inclusion
> of utsname() in init_std_data in the random seeding obviates it.
>
> The XOR with the TSC on x86 and mtfb() on powerPC were left in,
> as I haven't proved them redundant yet. For those, we call
> get_random_long(), xor, and mask manually.
>
> FUNCTIONAL CHANGE: mips and xtensa were changed from 64-bit
> get_random_long() to 56-bit get_random_canary() to match the
> others, in accordance with the logic in CANARY_MASK.
>
> (We could do 1 bit better and zero *one* of the two high bytes.)
>
> Signed-off-by: George Spelvin <lkml@sdf.org>
> Cc: Russell King <linux@armlinux.org.uk>
> Cc: linux-arm-kernel@lists.infradead.org
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Will Deacon <will@kernel.org>
> Cc: Ralf Baechle <ralf@linux-mips.org>
> Cc: Paul Burton <paulburton@kernel.org>
> Cc: James Hogan <jhogan@kernel.org>
> Cc: linux-mips@vger.kernel.org
> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> Cc: Paul Mackerras <paulus@samba.org>
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Cc: linuxppc-dev@lists.ozlabs.org
> Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
> Cc: Rich Felker <dalias@libc.org>
> Cc: linux-sh@vger.kernel.org
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Borislav Petkov <bp@alien8.de>
> Cc: "H. Peter Anvin" <hpa@zytor.com>
> Cc: x86@kernel.org
> Cc: Chris Zankel <chris@zankel.net>
> Cc: Max Filippov <jcmvbkbc@gmail.com>
> Cc: linux-xtensa@linux-xtensa.org
> ---
> arch/arm/include/asm/stackprotector.h | 9 +++------
> arch/arm64/include/asm/stackprotector.h | 8 ++------
> arch/mips/include/asm/stackprotector.h | 7 ++-----
> arch/powerpc/include/asm/stackprotector.h | 6 ++----
> arch/sh/include/asm/stackprotector.h | 8 ++------
> arch/x86/include/asm/stackprotector.h | 4 ++--
> arch/xtensa/include/asm/stackprotector.h | 7 ++-----
> 7 files changed, 15 insertions(+), 34 deletions(-)
Just found this kicking around in the depths of my inbox. Is the series
dead?
Will
^ permalink raw reply
* [PATCH V4 0/5] selftests/powerpc: Add NX-GZIP engine testcase
From: Raphael Moreira Zinsly @ 2020-04-20 20:55 UTC (permalink / raw)
To: linuxppc-dev, linux-crypto, dja; +Cc: abali, haren, herbert, rzinsly
This patch series are intended to test the POWER9 Nest
Accelerator (NX) GZIP engine that is being introduced by
https://lists.ozlabs.org/pipermail/linuxppc-dev/2020-March/205659.html
More information about how to access the NX can be found in that patch,
also a complete userspace library and more documentation can be found at:
https://github.com/libnxz/power-gzip
Changes in V4:
- Removed nx-helpers.h and moved relevant code to copy-paste.h.
- Removed nx-gzip.h and symlinked the vas-api.h uapi instead.
- Renamed inc to include and fixed warnings.
- Proper integrated the code to the selftests Makefile system
with help from Michael Ellerman.
Thanks,
Raphael
^ permalink raw reply
* [PATCH V4 1/5] selftests/powerpc: Add header files for GZIP engine test
From: Raphael Moreira Zinsly @ 2020-04-20 20:55 UTC (permalink / raw)
To: linuxppc-dev, linux-crypto, dja; +Cc: abali, haren, herbert, rzinsly
In-Reply-To: <20200420205538.25181-1-rzinsly@linux.ibm.com>
Add files to access the powerpc NX-GZIP engine in user space.
Signed-off-by: Bulent Abali <abali@us.ibm.com>
Signed-off-by: Raphael Moreira Zinsly <rzinsly@linux.ibm.com>
---
.../selftests/powerpc/nx-gzip/include/crb.h | 155 ++++++++++++++++++
.../selftests/powerpc/nx-gzip/include/nx.h | 38 +++++
.../powerpc/nx-gzip/include/vas-api.h | 1 +
3 files changed, 194 insertions(+)
create mode 100644 tools/testing/selftests/powerpc/nx-gzip/include/crb.h
create mode 100644 tools/testing/selftests/powerpc/nx-gzip/include/nx.h
create mode 120000 tools/testing/selftests/powerpc/nx-gzip/include/vas-api.h
diff --git a/tools/testing/selftests/powerpc/nx-gzip/include/crb.h b/tools/testing/selftests/powerpc/nx-gzip/include/crb.h
new file mode 100644
index 000000000000..ab101085fa7e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/include/crb.h
@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef __CRB_H
+#define __CRB_H
+#include <linux/types.h>
+#include "nx.h"
+
+/* CCW 842 CI/FC masks
+ * NX P8 workbook, section 4.3.1, figure 4-6
+ * "CI/FC Boundary by NX CT type"
+ */
+#define CCW_CI_842 (0x00003ff8)
+#define CCW_FC_842 (0x00000007)
+
+/* Chapter 6.5.8 Coprocessor-Completion Block (CCB) */
+
+#define CCB_VALUE (0x3fffffffffffffff)
+#define CCB_ADDRESS (0xfffffffffffffff8)
+#define CCB_CM (0x0000000000000007)
+#define CCB_CM0 (0x0000000000000004)
+#define CCB_CM12 (0x0000000000000003)
+
+#define CCB_CM0_ALL_COMPLETIONS (0x0)
+#define CCB_CM0_LAST_IN_CHAIN (0x4)
+#define CCB_CM12_STORE (0x0)
+#define CCB_CM12_INTERRUPT (0x1)
+
+#define CCB_SIZE (0x10)
+#define CCB_ALIGN CCB_SIZE
+
+struct coprocessor_completion_block {
+ __be64 value;
+ __be64 address;
+} __aligned(CCB_ALIGN);
+
+
+/* Chapter 6.5.7 Coprocessor-Status Block (CSB) */
+
+#define CSB_V (0x80)
+#define CSB_F (0x04)
+#define CSB_CH (0x03)
+#define CSB_CE_INCOMPLETE (0x80)
+#define CSB_CE_TERMINATION (0x40)
+#define CSB_CE_TPBC (0x20)
+
+#define CSB_CC_SUCCESS (0)
+#define CSB_CC_INVALID_ALIGN (1)
+#define CSB_CC_OPERAND_OVERLAP (2)
+#define CSB_CC_DATA_LENGTH (3)
+#define CSB_CC_TRANSLATION (5)
+#define CSB_CC_PROTECTION (6)
+#define CSB_CC_RD_EXTERNAL (7)
+#define CSB_CC_INVALID_OPERAND (8)
+#define CSB_CC_PRIVILEGE (9)
+#define CSB_CC_INTERNAL (10)
+#define CSB_CC_WR_EXTERNAL (12)
+#define CSB_CC_NOSPC (13)
+#define CSB_CC_EXCESSIVE_DDE (14)
+#define CSB_CC_WR_TRANSLATION (15)
+#define CSB_CC_WR_PROTECTION (16)
+#define CSB_CC_UNKNOWN_CODE (17)
+#define CSB_CC_ABORT (18)
+#define CSB_CC_TRANSPORT (20)
+#define CSB_CC_SEGMENTED_DDL (31)
+#define CSB_CC_PROGRESS_POINT (32)
+#define CSB_CC_DDE_OVERFLOW (33)
+#define CSB_CC_SESSION (34)
+#define CSB_CC_PROVISION (36)
+#define CSB_CC_CHAIN (37)
+#define CSB_CC_SEQUENCE (38)
+#define CSB_CC_HW (39)
+
+#define CSB_SIZE (0x10)
+#define CSB_ALIGN CSB_SIZE
+
+struct coprocessor_status_block {
+ __u8 flags;
+ __u8 cs;
+ __u8 cc;
+ __u8 ce;
+ __be32 count;
+ __be64 address;
+} __aligned(CSB_ALIGN);
+
+
+/* Chapter 6.5.10 Data-Descriptor List (DDL)
+ * each list contains one or more Data-Descriptor Entries (DDE)
+ */
+
+#define DDE_P (0x8000)
+
+#define DDE_SIZE (0x10)
+#define DDE_ALIGN DDE_SIZE
+
+struct data_descriptor_entry {
+ __be16 flags;
+ __u8 count;
+ __u8 index;
+ __be32 length;
+ __be64 address;
+} __aligned(DDE_ALIGN);
+
+
+/* Chapter 6.5.2 Coprocessor-Request Block (CRB) */
+
+#define CRB_SIZE (0x80)
+#define CRB_ALIGN (0x100) /* Errata: requires 256 alignment */
+
+
+/* Coprocessor Status Block field
+ * ADDRESS address of CSB
+ * C CCB is valid
+ * AT 0 = addrs are virtual, 1 = addrs are phys
+ * M enable perf monitor
+ */
+#define CRB_CSB_ADDRESS (0xfffffffffffffff0)
+#define CRB_CSB_C (0x0000000000000008)
+#define CRB_CSB_AT (0x0000000000000002)
+#define CRB_CSB_M (0x0000000000000001)
+
+struct coprocessor_request_block {
+ __be32 ccw;
+ __be32 flags;
+ __be64 csb_addr;
+
+ struct data_descriptor_entry source;
+ struct data_descriptor_entry target;
+
+ struct coprocessor_completion_block ccb;
+
+ __u8 reserved[48];
+
+ struct coprocessor_status_block csb;
+} __aligned(CRB_ALIGN);
+
+#define crb_csb_addr(c) __be64_to_cpu(c->csb_addr)
+#define crb_nx_fault_addr(c) __be64_to_cpu(c->stamp.nx.fault_storage_addr)
+#define crb_nx_flags(c) c->stamp.nx.flags
+#define crb_nx_fault_status(c) c->stamp.nx.fault_status
+#define crb_nx_pswid(c) c->stamp.nx.pswid
+
+
+/* RFC02167 Initiate Coprocessor Instructions document
+ * Chapter 8.2.1.1.1 RS
+ * Chapter 8.2.3 Coprocessor Directive
+ * Chapter 8.2.4 Execution
+ *
+ * The CCW must be converted to BE before passing to icswx()
+ */
+
+#define CCW_PS (0xff000000)
+#define CCW_CT (0x00ff0000)
+#define CCW_CD (0x0000ffff)
+#define CCW_CL (0x0000c000)
+
+#endif
diff --git a/tools/testing/selftests/powerpc/nx-gzip/include/nx.h b/tools/testing/selftests/powerpc/nx-gzip/include/nx.h
new file mode 100644
index 000000000000..78171b43464d
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/include/nx.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ * Copyright 2020 IBM Corp.
+ *
+ */
+#ifndef _NX_H
+#define _NX_H
+
+#include <stdbool.h>
+
+#define NX_FUNC_COMP_842 1
+#define NX_FUNC_COMP_GZIP 2
+
+#ifndef __aligned
+#define __aligned(x) __attribute__((aligned(x)))
+#endif
+
+struct nx842_func_args {
+ bool use_crc;
+ bool decompress; /* true decompress; false compress */
+ bool move_data;
+ int timeout; /* seconds */
+};
+
+struct nxbuf_t {
+ int len;
+ char *buf;
+};
+
+/* @function should be EFT (aka 842), GZIP etc */
+void *nx_function_begin(int function, int pri);
+
+int nx_function(void *handle, struct nxbuf_t *in, struct nxbuf_t *out,
+ void *arg);
+
+int nx_function_end(void *handle);
+
+#endif /* _NX_H */
diff --git a/tools/testing/selftests/powerpc/nx-gzip/include/vas-api.h b/tools/testing/selftests/powerpc/nx-gzip/include/vas-api.h
new file mode 120000
index 000000000000..77fb4c7236d0
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/include/vas-api.h
@@ -0,0 +1 @@
+../../../../../../arch/powerpc/include/uapi/asm/vas-api.h
\ No newline at end of file
--
2.21.0
^ permalink raw reply related
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