* [PATCH 08/13] powerpc/memcpy: Add memcpy_mcsafe for pmem
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
In-Reply-To: <cover.1561020760.git.santosh@fossix.org>
From: Balbir Singh <bsingharora@gmail.com>
The pmem infrastructure uses memcpy_mcsafe in the pmem
layer so as to convert machine check exceptions into
a return value on failure in case a machine check
exception is encountered during the memcpy.
This patch largely borrows from the copyuser_power7
logic and does not add the VMX optimizations, largely
to keep the patch simple. If needed those optimizations
can be folded in.
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
Acked-by: Nicholas Piggin <npiggin@gmail.com>
[arbab@linux.ibm.com: Added symbol export]
---
arch/powerpc/include/asm/string.h | 2 +
arch/powerpc/lib/Makefile | 2 +-
arch/powerpc/lib/memcpy_mcsafe_64.S | 215 ++++++++++++++++++++++++++++
3 files changed, 218 insertions(+), 1 deletion(-)
create mode 100644 arch/powerpc/lib/memcpy_mcsafe_64.S
diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h
index 9bf6dffb4090..b72692702f35 100644
--- a/arch/powerpc/include/asm/string.h
+++ b/arch/powerpc/include/asm/string.h
@@ -53,7 +53,9 @@ void *__memmove(void *to, const void *from, __kernel_size_t n);
#ifndef CONFIG_KASAN
#define __HAVE_ARCH_MEMSET32
#define __HAVE_ARCH_MEMSET64
+#define __HAVE_ARCH_MEMCPY_MCSAFE
+extern int memcpy_mcsafe(void *dst, const void *src, __kernel_size_t sz);
extern void *__memset16(uint16_t *, uint16_t v, __kernel_size_t);
extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t);
extern void *__memset64(uint64_t *, uint64_t v, __kernel_size_t);
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index c55f9c27bf79..529d6536eb4a 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -39,7 +39,7 @@ obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
memcpy_power7.o
obj64-y += copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
- memcpy_64.o pmem.o
+ memcpy_64.o pmem.o memcpy_mcsafe_64.o
obj64-$(CONFIG_SMP) += locks.o
obj64-$(CONFIG_ALTIVEC) += vmx-helper.o
diff --git a/arch/powerpc/lib/memcpy_mcsafe_64.S b/arch/powerpc/lib/memcpy_mcsafe_64.S
new file mode 100644
index 000000000000..50f865db0338
--- /dev/null
+++ b/arch/powerpc/lib/memcpy_mcsafe_64.S
@@ -0,0 +1,215 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) IBM Corporation, 2011
+ * Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com>
+ * Author - Balbir Singh <bsingharora@gmail.com>
+ */
+#include <asm/ppc_asm.h>
+#include <asm/errno.h>
+#include <asm/export.h>
+
+ .macro err1
+100:
+ EX_TABLE(100b,.Ldo_err1)
+ .endm
+
+ .macro err2
+200:
+ EX_TABLE(200b,.Ldo_err2)
+ .endm
+
+.Ldo_err2:
+ ld r22,STK_REG(R22)(r1)
+ ld r21,STK_REG(R21)(r1)
+ ld r20,STK_REG(R20)(r1)
+ ld r19,STK_REG(R19)(r1)
+ ld r18,STK_REG(R18)(r1)
+ ld r17,STK_REG(R17)(r1)
+ ld r16,STK_REG(R16)(r1)
+ ld r15,STK_REG(R15)(r1)
+ ld r14,STK_REG(R14)(r1)
+ addi r1,r1,STACKFRAMESIZE
+.Ldo_err1:
+ li r3,-EFAULT
+ blr
+
+
+_GLOBAL(memcpy_mcsafe)
+ cmpldi r5,16
+ blt .Lshort_copy
+
+.Lcopy:
+ /* Get the source 8B aligned */
+ neg r6,r4
+ mtocrf 0x01,r6
+ clrldi r6,r6,(64-3)
+
+ bf cr7*4+3,1f
+err1; lbz r0,0(r4)
+ addi r4,r4,1
+err1; stb r0,0(r3)
+ addi r3,r3,1
+
+1: bf cr7*4+2,2f
+err1; lhz r0,0(r4)
+ addi r4,r4,2
+err1; sth r0,0(r3)
+ addi r3,r3,2
+
+2: bf cr7*4+1,3f
+err1; lwz r0,0(r4)
+ addi r4,r4,4
+err1; stw r0,0(r3)
+ addi r3,r3,4
+
+3: sub r5,r5,r6
+ cmpldi r5,128
+ blt 5f
+
+ mflr r0
+ stdu r1,-STACKFRAMESIZE(r1)
+ std r14,STK_REG(R14)(r1)
+ std r15,STK_REG(R15)(r1)
+ std r16,STK_REG(R16)(r1)
+ std r17,STK_REG(R17)(r1)
+ std r18,STK_REG(R18)(r1)
+ std r19,STK_REG(R19)(r1)
+ std r20,STK_REG(R20)(r1)
+ std r21,STK_REG(R21)(r1)
+ std r22,STK_REG(R22)(r1)
+ std r0,STACKFRAMESIZE+16(r1)
+
+ srdi r6,r5,7
+ mtctr r6
+
+ /* Now do cacheline (128B) sized loads and stores. */
+ .align 5
+4:
+err2; ld r0,0(r4)
+err2; ld r6,8(r4)
+err2; ld r7,16(r4)
+err2; ld r8,24(r4)
+err2; ld r9,32(r4)
+err2; ld r10,40(r4)
+err2; ld r11,48(r4)
+err2; ld r12,56(r4)
+err2; ld r14,64(r4)
+err2; ld r15,72(r4)
+err2; ld r16,80(r4)
+err2; ld r17,88(r4)
+err2; ld r18,96(r4)
+err2; ld r19,104(r4)
+err2; ld r20,112(r4)
+err2; ld r21,120(r4)
+ addi r4,r4,128
+err2; std r0,0(r3)
+err2; std r6,8(r3)
+err2; std r7,16(r3)
+err2; std r8,24(r3)
+err2; std r9,32(r3)
+err2; std r10,40(r3)
+err2; std r11,48(r3)
+err2; std r12,56(r3)
+err2; std r14,64(r3)
+err2; std r15,72(r3)
+err2; std r16,80(r3)
+err2; std r17,88(r3)
+err2; std r18,96(r3)
+err2; std r19,104(r3)
+err2; std r20,112(r3)
+err2; std r21,120(r3)
+ addi r3,r3,128
+ bdnz 4b
+
+ clrldi r5,r5,(64-7)
+
+ ld r14,STK_REG(R14)(r1)
+ ld r15,STK_REG(R15)(r1)
+ ld r16,STK_REG(R16)(r1)
+ ld r17,STK_REG(R17)(r1)
+ ld r18,STK_REG(R18)(r1)
+ ld r19,STK_REG(R19)(r1)
+ ld r20,STK_REG(R20)(r1)
+ ld r21,STK_REG(R21)(r1)
+ ld r22,STK_REG(R22)(r1)
+ addi r1,r1,STACKFRAMESIZE
+
+ /* Up to 127B to go */
+5: srdi r6,r5,4
+ mtocrf 0x01,r6
+
+6: bf cr7*4+1,7f
+err1; ld r0,0(r4)
+err1; ld r6,8(r4)
+err1; ld r7,16(r4)
+err1; ld r8,24(r4)
+err1; ld r9,32(r4)
+err1; ld r10,40(r4)
+err1; ld r11,48(r4)
+err1; ld r12,56(r4)
+ addi r4,r4,64
+err1; std r0,0(r3)
+err1; std r6,8(r3)
+err1; std r7,16(r3)
+err1; std r8,24(r3)
+err1; std r9,32(r3)
+err1; std r10,40(r3)
+err1; std r11,48(r3)
+err1; std r12,56(r3)
+ addi r3,r3,64
+
+ /* Up to 63B to go */
+7: bf cr7*4+2,8f
+err1; ld r0,0(r4)
+err1; ld r6,8(r4)
+err1; ld r7,16(r4)
+err1; ld r8,24(r4)
+ addi r4,r4,32
+err1; std r0,0(r3)
+err1; std r6,8(r3)
+err1; std r7,16(r3)
+err1; std r8,24(r3)
+ addi r3,r3,32
+
+ /* Up to 31B to go */
+8: bf cr7*4+3,9f
+err1; ld r0,0(r4)
+err1; ld r6,8(r4)
+ addi r4,r4,16
+err1; std r0,0(r3)
+err1; std r6,8(r3)
+ addi r3,r3,16
+
+9: clrldi r5,r5,(64-4)
+
+ /* Up to 15B to go */
+.Lshort_copy:
+ mtocrf 0x01,r5
+ bf cr7*4+0,12f
+err1; lwz r0,0(r4) /* Less chance of a reject with word ops */
+err1; lwz r6,4(r4)
+ addi r4,r4,8
+err1; stw r0,0(r3)
+err1; stw r6,4(r3)
+ addi r3,r3,8
+
+12: bf cr7*4+1,13f
+err1; lwz r0,0(r4)
+ addi r4,r4,4
+err1; stw r0,0(r3)
+ addi r3,r3,4
+
+13: bf cr7*4+2,14f
+err1; lhz r0,0(r4)
+ addi r4,r4,2
+err1; sth r0,0(r3)
+ addi r3,r3,2
+
+14: bf cr7*4+3,15f
+err1; lbz r0,0(r4)
+err1; stb r0,0(r3)
+
+15: li r3,0
+ blr
+
+EXPORT_SYMBOL_GPL(memcpy_mcsafe);
--
2.20.1
^ permalink raw reply related
* [PATCH 07/13] powerpc/mce: Add fixup address to UE events
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
In-Reply-To: <cover.1561020760.git.santosh@fossix.org>
From: Reza Arbab <arbab@linux.ibm.com>
If the instruction causing a UE has an exception table entry with fixup
address, save it in the machine_check_event struct.
If a machine check notifier callback returns NOTIFY_STOP to indicate it
has handled the error, set nip to continue execution from the fixup
address.
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/include/asm/mce.h | 5 +++--
arch/powerpc/kernel/mce.c | 16 +++++++++++++++-
2 files changed, 18 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 240dd1fdfe35..9d9661747adf 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -122,11 +122,12 @@ struct machine_check_event {
enum MCE_UeErrorType ue_error_type:8;
u8 effective_address_provided;
u8 physical_address_provided;
+ u8 fixup_address_provided;
u8 process_event;
- u8 reserved_1[4];
+ u8 reserved_1[3];
u64 effective_address;
u64 physical_address;
- u8 reserved_2[8];
+ u64 fixup_address;
} ue_error;
struct {
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 2616f1f71734..8afda1ab7358 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -15,10 +15,12 @@
#include <linux/percpu.h>
#include <linux/export.h>
#include <linux/irq_work.h>
+#include <linux/extable.h>
#include <asm/machdep.h>
#include <asm/mce.h>
#include <asm/nmi.h>
+#include <asm/extable.h>
static DEFINE_PER_CPU(int, mce_nest_count);
static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event);
@@ -151,6 +153,8 @@ void save_mce_event(struct pt_regs *regs, long handled,
mce->u.link_error.effective_address_provided = true;
mce->u.link_error.effective_address = addr;
} else if (mce->error_type == MCE_ERROR_TYPE_UE) {
+ const struct exception_table_entry *entry;
+
mce->u.ue_error.effective_address_provided = true;
mce->u.ue_error.effective_address = addr;
if (phys_addr != ULONG_MAX) {
@@ -158,6 +162,12 @@ void save_mce_event(struct pt_regs *regs, long handled,
mce->u.ue_error.physical_address = phys_addr;
}
+ entry = search_exception_tables(regs->nip);
+ if (entry) {
+ mce->u.ue_error.fixup_address_provided = true;
+ mce->u.ue_error.fixup_address = extable_fixup(entry);
+ }
+
mce->u.ue_error.process_event = true;
}
return;
@@ -666,8 +676,12 @@ long machine_check_notify(struct pt_regs *regs)
rc = blocking_notifier_call_chain(&mce_notifier_list, 0, evt);
if (rc & NOTIFY_STOP_MASK) {
- if (evt->error_type == MCE_ERROR_TYPE_UE)
+ if (evt->error_type == MCE_ERROR_TYPE_UE) {
+ if (evt->u.ue_error.fixup_address_provided)
+ regs->nip = evt->u.ue_error.fixup_address;
+
evt->u.ue_error.process_event = false;
+ }
evt->disposition = MCE_DISPOSITION_RECOVERED;
regs->msr |= MSR_RI;
--
2.20.1
^ permalink raw reply related
* [PATCH 06/13] powerpc/mce: Do not process notifier-handled UE events
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
In-Reply-To: <cover.1561020760.git.santosh@fossix.org>
From: Reza Arbab <arbab@linux.ibm.com>
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/include/asm/mce.h | 3 ++-
arch/powerpc/kernel/mce.c | 9 +++++++++
2 files changed, 11 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 948bef579086..240dd1fdfe35 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -122,7 +122,8 @@ struct machine_check_event {
enum MCE_UeErrorType ue_error_type:8;
u8 effective_address_provided;
u8 physical_address_provided;
- u8 reserved_1[5];
+ u8 process_event;
+ u8 reserved_1[4];
u64 effective_address;
u64 physical_address;
u8 reserved_2[8];
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 912efe58e0b1..2616f1f71734 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -157,6 +157,8 @@ void save_mce_event(struct pt_regs *regs, long handled,
mce->u.ue_error.physical_address_provided = true;
mce->u.ue_error.physical_address = phys_addr;
}
+
+ mce->u.ue_error.process_event = true;
}
return;
}
@@ -241,6 +243,10 @@ void machine_check_queue_event(void)
if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
return;
+ if (evt.error_type == MCE_ERROR_TYPE_UE &&
+ !evt.u.ue_error.process_event)
+ return;
+
index = __this_cpu_inc_return(mce_queue_count) - 1;
/* If queue is full, just return for now. */
if (index >= MAX_MC_EVT) {
@@ -660,6 +666,9 @@ long machine_check_notify(struct pt_regs *regs)
rc = blocking_notifier_call_chain(&mce_notifier_list, 0, evt);
if (rc & NOTIFY_STOP_MASK) {
+ if (evt->error_type == MCE_ERROR_TYPE_UE)
+ evt->u.ue_error.process_event = false;
+
evt->disposition = MCE_DISPOSITION_RECOVERED;
regs->msr |= MSR_RI;
--
2.20.1
^ permalink raw reply related
* [PATCH 05/13] powerpc/mce: Allow notifier callback to handle MCE
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
In-Reply-To: <cover.1561020760.git.santosh@fossix.org>
From: Reza Arbab <arbab@linux.ibm.com>
If a notifier returns NOTIFY_STOP, consider the MCE handled, just as we
do when machine_check_early() returns 1.
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/include/asm/asm-prototypes.h | 2 +-
arch/powerpc/kernel/exceptions-64s.S | 3 +++
arch/powerpc/kernel/mce.c | 28 ++++++++++++++++-------
3 files changed, 24 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index f66f26ef3ce0..49ee8f08de2a 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -72,7 +72,7 @@ void machine_check_exception(struct pt_regs *regs);
void emulation_assist_interrupt(struct pt_regs *regs);
long do_slb_fault(struct pt_regs *regs, unsigned long ea);
void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err);
-void machine_check_notify(struct pt_regs *regs);
+long machine_check_notify(struct pt_regs *regs);
/* signals, syscalls and interrupts */
long sys_swapcontext(struct ucontext __user *old_ctx,
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 2e56014fca21..c83e38a403fd 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -460,6 +460,9 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
addi r3,r1,STACK_FRAME_OVERHEAD
bl machine_check_notify
+ ld r11,RESULT(r1)
+ or r3,r3,r11
+ std r3,RESULT(r1)
ld r12,_MSR(r1)
BEGIN_FTR_SECTION
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 0ab171b41ede..912efe58e0b1 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -647,16 +647,28 @@ long hmi_exception_realmode(struct pt_regs *regs)
return 1;
}
-void machine_check_notify(struct pt_regs *regs)
+long machine_check_notify(struct pt_regs *regs)
{
- struct machine_check_event evt;
+ int index = __this_cpu_read(mce_nest_count) - 1;
+ struct machine_check_event *evt;
+ int rc;
- if (!get_mce_event(&evt, MCE_EVENT_DONTRELEASE))
- return;
+ if (index < 0 || index >= MAX_MC_EVT)
+ return 0;
+
+ evt = this_cpu_ptr(&mce_event[index]);
- blocking_notifier_call_chain(&mce_notifier_list, 0, &evt);
+ rc = blocking_notifier_call_chain(&mce_notifier_list, 0, evt);
+ if (rc & NOTIFY_STOP_MASK) {
+ evt->disposition = MCE_DISPOSITION_RECOVERED;
+ regs->msr |= MSR_RI;
- if (evt.error_type == MCE_ERROR_TYPE_UE &&
- evt.u.ue_error.physical_address_provided)
- machine_check_ue_event(&evt);
+ return 1;
+ }
+
+ if (evt->error_type == MCE_ERROR_TYPE_UE &&
+ evt->u.ue_error.physical_address_provided)
+ machine_check_ue_event(evt);
+
+ return 0;
}
--
2.20.1
^ permalink raw reply related
* [PATCH 04/13] powerpc/mce: Move machine_check_ue_event() call
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
In-Reply-To: <cover.1561020760.git.santosh@fossix.org>
From: Reza Arbab <arbab@linux.ibm.com>
Move the call site of machine_check_ue_event() slightly later in the MCE
codepath. No functional change intended--this is prep for a later patch
to conditionally skip the call.
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/kernel/mce.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 24d350a934e4..0ab171b41ede 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -156,7 +156,6 @@ void save_mce_event(struct pt_regs *regs, long handled,
if (phys_addr != ULONG_MAX) {
mce->u.ue_error.physical_address_provided = true;
mce->u.ue_error.physical_address = phys_addr;
- machine_check_ue_event(mce);
}
}
return;
@@ -656,4 +655,8 @@ void machine_check_notify(struct pt_regs *regs)
return;
blocking_notifier_call_chain(&mce_notifier_list, 0, &evt);
+
+ if (evt.error_type == MCE_ERROR_TYPE_UE &&
+ evt.u.ue_error.physical_address_provided)
+ machine_check_ue_event(&evt);
}
--
2.20.1
^ permalink raw reply related
* [PATCH 03/13] powerpc/mce: Add MCE notification chain
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
In-Reply-To: <cover.1561020760.git.santosh@fossix.org>
From: Reza Arbab <arbab@linux.ibm.com>
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/include/asm/asm-prototypes.h | 1 +
arch/powerpc/include/asm/mce.h | 4 ++++
arch/powerpc/kernel/exceptions-64s.S | 4 ++++
arch/powerpc/kernel/mce.c | 22 ++++++++++++++++++++++
4 files changed, 31 insertions(+)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index ec1c97a8e8cb..f66f26ef3ce0 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -72,6 +72,7 @@ void machine_check_exception(struct pt_regs *regs);
void emulation_assist_interrupt(struct pt_regs *regs);
long do_slb_fault(struct pt_regs *regs, unsigned long ea);
void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err);
+void machine_check_notify(struct pt_regs *regs);
/* signals, syscalls and interrupts */
long sys_swapcontext(struct ucontext __user *old_ctx,
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 94888a7025b3..948bef579086 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -214,4 +214,8 @@ unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr,
#ifdef CONFIG_PPC_BOOK3S_64
void flush_and_reload_slb(void);
#endif /* CONFIG_PPC_BOOK3S_64 */
+
+int mce_register_notifier(struct notifier_block *nb);
+int mce_unregister_notifier(struct notifier_block *nb);
+
#endif /* __ASM_PPC64_MCE_H__ */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 6b86055e5251..2e56014fca21 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -457,6 +457,10 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
addi r3,r1,STACK_FRAME_OVERHEAD
bl machine_check_early
std r3,RESULT(r1) /* Save result */
+
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl machine_check_notify
+
ld r12,_MSR(r1)
BEGIN_FTR_SECTION
b 4f
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index e78c4f18ea0a..24d350a934e4 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -42,6 +42,18 @@ static struct irq_work mce_event_process_work = {
DECLARE_WORK(mce_ue_event_work, machine_process_ue_event);
+static BLOCKING_NOTIFIER_HEAD(mce_notifier_list);
+
+int mce_register_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&mce_notifier_list, nb);
+}
+
+int mce_unregister_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&mce_notifier_list, nb);
+}
+
static void mce_set_error_info(struct machine_check_event *mce,
struct mce_error_info *mce_err)
{
@@ -635,3 +647,13 @@ long hmi_exception_realmode(struct pt_regs *regs)
return 1;
}
+
+void machine_check_notify(struct pt_regs *regs)
+{
+ struct machine_check_event evt;
+
+ if (!get_mce_event(&evt, MCE_EVENT_DONTRELEASE))
+ return;
+
+ blocking_notifier_call_chain(&mce_notifier_list, 0, &evt);
+}
--
2.20.1
^ permalink raw reply related
* [PATCH 02/13] powerpc/mce: Bug fixes for MCE handling in kernel space
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
In-Reply-To: <cover.1561020760.git.santosh@fossix.org>
From: Balbir Singh <bsingharora@gmail.com>
The code currently assumes PAGE_SHIFT as the shift value of
the pfn, this works correctly (mostly) for user space pages,
but the correct thing to do is
1. Extract the shift value returned via the pte-walk API's
2. Use the shift value to access the instruction address.
Note, the final physical address still use PAGE_SHIFT for
computation. handle_ierror() is not modified and handle_derror()
is modified just for extracting the correct instruction
address.
This is largely due to __find_linux_pte() returning pfn's
shifted by pdshift. The code is much more generic and can
handle shift values returned.
Fixes: ba41e1e1ccb9 ("powerpc/mce: Hookup derror (load/store) UE errors")
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
[arbab@linux.ibm.com: Fixup pseries_do_memory_failure()]
---
arch/powerpc/include/asm/mce.h | 3 ++-
arch/powerpc/kernel/mce_power.c | 26 ++++++++++++++++----------
arch/powerpc/platforms/pseries/ras.c | 6 ++++--
3 files changed, 22 insertions(+), 13 deletions(-)
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index a4c6a74ad2fb..94888a7025b3 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -209,7 +209,8 @@ extern void release_mce_event(void);
extern void machine_check_queue_event(void);
extern void machine_check_print_event_info(struct machine_check_event *evt,
bool user_mode, bool in_guest);
-unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr);
+unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr,
+ unsigned int *shift);
#ifdef CONFIG_PPC_BOOK3S_64
void flush_and_reload_slb(void);
#endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index e39536aad30d..04666c0b40a8 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -23,7 +23,8 @@
* Convert an address related to an mm to a PFN. NOTE: we are in real
* mode, we could potentially race with page table updates.
*/
-unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
+unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr,
+ unsigned int *shift)
{
pte_t *ptep;
unsigned long flags;
@@ -36,13 +37,15 @@ unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
local_irq_save(flags);
if (mm == current->mm)
- ptep = find_current_mm_pte(mm->pgd, addr, NULL, NULL);
+ ptep = find_current_mm_pte(mm->pgd, addr, NULL, shift);
else
- ptep = find_init_mm_pte(addr, NULL);
+ ptep = find_init_mm_pte(addr, shift);
local_irq_restore(flags);
if (!ptep || pte_special(*ptep))
return ULONG_MAX;
- return pte_pfn(*ptep);
+ if (!*shift)
+ *shift = PAGE_SHIFT;
+ return (pte_val(*ptep) & PTE_RPN_MASK) >> *shift;
}
/* flush SLBs and reload */
@@ -358,15 +361,16 @@ static int mce_find_instr_ea_and_pfn(struct pt_regs *regs, uint64_t *addr,
unsigned long pfn, instr_addr;
struct instruction_op op;
struct pt_regs tmp = *regs;
+ unsigned int shift;
- pfn = addr_to_pfn(regs, regs->nip);
+ pfn = addr_to_pfn(regs, regs->nip, &shift);
if (pfn != ULONG_MAX) {
- instr_addr = (pfn << PAGE_SHIFT) + (regs->nip & ~PAGE_MASK);
+ instr_addr = (pfn << shift) + (regs->nip & ((1 << shift) - 1));
instr = *(unsigned int *)(instr_addr);
if (!analyse_instr(&op, &tmp, instr)) {
- pfn = addr_to_pfn(regs, op.ea);
+ pfn = addr_to_pfn(regs, op.ea, &shift);
*addr = op.ea;
- *phys_addr = (pfn << PAGE_SHIFT);
+ *phys_addr = (pfn << shift);
return 0;
}
/*
@@ -442,12 +446,14 @@ static int mce_handle_ierror(struct pt_regs *regs,
if (mce_err->sync_error &&
table[i].error_type == MCE_ERROR_TYPE_UE) {
unsigned long pfn;
+ unsigned int shift;
if (get_paca()->in_mce < MAX_MCE_DEPTH) {
- pfn = addr_to_pfn(regs, regs->nip);
+ pfn = addr_to_pfn(regs, regs->nip,
+ &shift);
if (pfn != ULONG_MAX) {
*phys_addr =
- (pfn << PAGE_SHIFT);
+ (pfn << shift);
}
}
}
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index f16fdd0f71f7..5e43283d3300 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -740,12 +740,14 @@ static void pseries_do_memory_failure(struct pt_regs *regs,
paddr = be64_to_cpu(mce_log->logical_address);
} else if (mce_log->sub_err_type & UE_EFFECTIVE_ADDR_PROVIDED) {
unsigned long pfn;
+ unsigned int shift;
pfn = addr_to_pfn(regs,
- be64_to_cpu(mce_log->effective_address));
+ be64_to_cpu(mce_log->effective_address),
+ &shift);
if (pfn == ULONG_MAX)
return;
- paddr = pfn << PAGE_SHIFT;
+ paddr = pfn << shift;
} else {
return;
}
--
2.20.1
^ permalink raw reply related
* [PATCH 00/13] powerpc: implement machine check safe memcpy
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
During a memcpy from a pmem device, if a machine check exception is
generated we end up in a panic. In case of fsdax read, this should
only result in a -EIO. Avoid MCE by implementing memcpy_mcsafe.
Before this patch series:
```
bash-4.4# mount -o dax /dev/pmem0 /mnt/pmem/
[ 7621.714094] Disabling lock debugging due to kernel taint
[ 7621.714099] MCE: CPU0: machine check (Severe) Host UE Load/Store [Not recovered]
[ 7621.714104] MCE: CPU0: NIP: [c000000000088978] memcpy_power7+0x418/0x7e0
[ 7621.714107] MCE: CPU0: Hardware error
[ 7621.714112] opal: Hardware platform error: Unrecoverable Machine Check exception
[ 7621.714118] CPU: 0 PID: 1368 Comm: mount Tainted: G M 5.2.0-rc5-00239-g241e39004581 #50
[ 7621.714123] NIP: c000000000088978 LR: c0000000008e16f8 CTR: 00000000000001de
[ 7621.714129] REGS: c0000000fffbfd70 TRAP: 0200 Tainted: G M (5.2.0-rc5-00239-g241e39004581)
[ 7621.714131] MSR: 9000000002209033 <SF,HV,VEC,EE,ME,IR,DR,RI,LE> CR: 24428840 XER: 00040000
[ 7621.714160] CFAR: c0000000000889a8 DAR: deadbeefdeadbeef DSISR: 00008000 IRQMASK: 0
[ 7621.714171] GPR00: 000000000e000000 c0000000f0b8b1e0 c0000000012cf100 c0000000ed8e1100
[ 7621.714186] GPR04: c000020000001100 0000000000010000 0000000000000200 03fffffff1272000
[ 7621.714201] GPR08: 0000000080000000 0000000000000010 0000000000000020 0000000000000030
[ 7621.714216] GPR12: 0000000000000040 00007fffb8c6d390 0000000000000050 0000000000000060
[ 7621.714232] GPR16: 0000000000000070 0000000000000000 0000000000000001 c0000000f0b8b960
[ 7621.714247] GPR20: 0000000000000001 c0000000f0b8b940 0000000000000001 0000000000010000
[ 7621.714262] GPR24: c000000001382560 c00c0000003b6380 c00c0000003b6380 0000000000010000
[ 7621.714277] GPR28: 0000000000000000 0000000000010000 c000020000000000 0000000000010000
[ 7621.714294] NIP [c000000000088978] memcpy_power7+0x418/0x7e0
[ 7621.714298] LR [c0000000008e16f8] pmem_do_bvec+0xf8/0x430
... <snip> ...
```
After this patch series:
```
bash-4.4# mount -o dax /dev/pmem0 /mnt/pmem/
[25302.883978] Buffer I/O error on dev pmem0, logical block 0, async page read
[25303.020816] EXT4-fs (pmem0): DAX enabled. Warning: EXPERIMENTAL, use at your own risk
[25303.021236] EXT4-fs (pmem0): Can't read superblock on 2nd try
[25303.152515] EXT4-fs (pmem0): DAX enabled. Warning: EXPERIMENTAL, use at your own risk
[25303.284031] EXT4-fs (pmem0): DAX enabled. Warning: EXPERIMENTAL, use at your own risk
[25304.084100] UDF-fs: bad mount option "dax" or missing value
mount: /mnt/pmem: wrong fs type, bad option, bad superblock on /dev/pmem0, missing codepage or helper program, or other error.
```
MCE is injected on a pmem address using mambo.
---
Balbir Singh (2):
powerpc/mce: Bug fixes for MCE handling in kernel space
powerpc/memcpy: Add memcpy_mcsafe for pmem
Reza Arbab (9):
powerpc/mce: Make machine_check_ue_event() static
powerpc/mce: Add MCE notification chain
powerpc/mce: Move machine_check_ue_event() call
powerpc/mce: Allow notifier callback to handle MCE
powerpc/mce: Do not process notifier-handled UE events
powerpc/mce: Add fixup address to UE events
powerpc/mce: Handle memcpy_mcsafe()
powerpc/mce: Enable MCE notifiers in external modules
powerpc/64s: Save r13 in machine_check_common_early
Santosh Sivaraj (2):
powerpc/memcpy_mcsafe: return remaining bytes
powerpc: add machine check safe copy_to_user
arch/powerpc/Kconfig | 1 +
arch/powerpc/include/asm/asm-prototypes.h | 1 +
arch/powerpc/include/asm/mce.h | 13 +-
arch/powerpc/include/asm/string.h | 2 +
arch/powerpc/include/asm/uaccess.h | 12 ++
arch/powerpc/kernel/exceptions-64s.S | 14 ++
arch/powerpc/kernel/mce.c | 102 +++++++++-
arch/powerpc/kernel/mce_power.c | 26 ++-
arch/powerpc/lib/Makefile | 2 +-
arch/powerpc/lib/memcpy_mcsafe_64.S | 226 ++++++++++++++++++++++
arch/powerpc/platforms/pseries/ras.c | 6 +-
11 files changed, 386 insertions(+), 19 deletions(-)
create mode 100644 arch/powerpc/lib/memcpy_mcsafe_64.S
--
2.20.1
^ permalink raw reply
* [PATCH 01/13] powerpc/mce: Make machine_check_ue_event() static
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
In-Reply-To: <cover.1561020760.git.santosh@fossix.org>
From: Reza Arbab <arbab@linux.ibm.com>
The function doesn't get used outside this file, so make it static.
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/kernel/mce.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index b18df633eae9..e78c4f18ea0a 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -33,7 +33,7 @@ static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT],
mce_ue_event_queue);
static void machine_check_process_queued_event(struct irq_work *work);
-void machine_check_ue_event(struct machine_check_event *evt);
+static void machine_check_ue_event(struct machine_check_event *evt);
static void machine_process_ue_event(struct work_struct *work);
static struct irq_work mce_event_process_work = {
@@ -203,7 +203,7 @@ void release_mce_event(void)
/*
* Queue up the MCE event which then can be handled later.
*/
-void machine_check_ue_event(struct machine_check_event *evt)
+static void machine_check_ue_event(struct machine_check_event *evt)
{
int index;
--
2.20.1
^ permalink raw reply related
* Re: [PATCH 2/4] powerpc/powernv: remove the unused tunneling exports
From: Oliver O'Halloran @ 2019-06-21 1:47 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Andrew Donnellan, Linux Kernel Mailing List, Paul Mackerras,
Frederic Barrat, linuxppc-dev
In-Reply-To: <20190523074924.19659-3-hch@lst.de>
On Thu, May 23, 2019 at 5:51 PM Christoph Hellwig <hch@lst.de> wrote:
>
> These have been unused ever since they've been added to the kernel.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
> arch/powerpc/include/asm/pnv-pci.h | 4 --
> arch/powerpc/platforms/powernv/pci-ioda.c | 4 +-
> arch/powerpc/platforms/powernv/pci.c | 71 -----------------------
> arch/powerpc/platforms/powernv/pci.h | 1 -
> 4 files changed, 3 insertions(+), 77 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h
> index 9fcb0bc462c6..1ab4b0111abc 100644
> --- a/arch/powerpc/include/asm/pnv-pci.h
> +++ b/arch/powerpc/include/asm/pnv-pci.h
> @@ -27,12 +27,8 @@ extern int pnv_pci_get_power_state(uint64_t id, uint8_t *state);
> extern int pnv_pci_set_power_state(uint64_t id, uint8_t state,
> struct opal_msg *msg);
>
> -extern int pnv_pci_enable_tunnel(struct pci_dev *dev, uint64_t *asnind);
> -extern int pnv_pci_disable_tunnel(struct pci_dev *dev);
> extern int pnv_pci_set_tunnel_bar(struct pci_dev *dev, uint64_t addr,
> int enable);
> -extern int pnv_pci_get_as_notify_info(struct task_struct *task, u32 *lpid,
> - u32 *pid, u32 *tid);
IIRC as-notify was for CAPI which has an in-tree driver (cxl). Fred or
Andrew (+cc), what's going on with this? Will it ever see the light of
day?
> int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode);
> int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
> unsigned int virq);
> diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
> index 126602b4e399..6b0caa2d0425 100644
> --- a/arch/powerpc/platforms/powernv/pci-ioda.c
> +++ b/arch/powerpc/platforms/powernv/pci-ioda.c
> @@ -54,6 +54,8 @@
> static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_NVLINK",
> "NPU_OCAPI" };
>
> +static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
> +
> void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
> const char *fmt, ...)
> {
> @@ -2360,7 +2362,7 @@ static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group,
> return 0;
> }
>
> -void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable)
> +static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable)
> {
> uint16_t window_id = (pe->pe_number << 1 ) + 1;
> int64_t rc;
> diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
> index 8d28f2932c3b..fc69f5611020 100644
> --- a/arch/powerpc/platforms/powernv/pci.c
> +++ b/arch/powerpc/platforms/powernv/pci.c
> @@ -868,54 +868,6 @@ struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev)
> }
> EXPORT_SYMBOL(pnv_pci_get_phb_node);
>
> -int pnv_pci_enable_tunnel(struct pci_dev *dev, u64 *asnind)
> -{
> - struct device_node *np;
> - const __be32 *prop;
> - struct pnv_ioda_pe *pe;
> - uint16_t window_id;
> - int rc;
> -
> - if (!radix_enabled())
> - return -ENXIO;
> -
> - if (!(np = pnv_pci_get_phb_node(dev)))
> - return -ENXIO;
> -
> - prop = of_get_property(np, "ibm,phb-indications", NULL);
> - of_node_put(np);
> -
> - if (!prop || !prop[1])
> - return -ENXIO;
> -
> - *asnind = (u64)be32_to_cpu(prop[1]);
> - pe = pnv_ioda_get_pe(dev);
> - if (!pe)
> - return -ENODEV;
> -
> - /* Increase real window size to accept as_notify messages. */
> - window_id = (pe->pe_number << 1 ) + 1;
> - rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, pe->pe_number,
> - window_id, pe->tce_bypass_base,
> - (uint64_t)1 << 48);
> - return opal_error_code(rc);
> -}
> -EXPORT_SYMBOL_GPL(pnv_pci_enable_tunnel);
> -
> -int pnv_pci_disable_tunnel(struct pci_dev *dev)
> -{
> - struct pnv_ioda_pe *pe;
> -
> - pe = pnv_ioda_get_pe(dev);
> - if (!pe)
> - return -ENODEV;
> -
> - /* Restore default real window size. */
> - pnv_pci_ioda2_set_bypass(pe, true);
> - return 0;
> -}
> -EXPORT_SYMBOL_GPL(pnv_pci_disable_tunnel);
> -
> int pnv_pci_set_tunnel_bar(struct pci_dev *dev, u64 addr, int enable)
> {
> __be64 val;
> @@ -970,29 +922,6 @@ int pnv_pci_set_tunnel_bar(struct pci_dev *dev, u64 addr, int enable)
> }
> EXPORT_SYMBOL_GPL(pnv_pci_set_tunnel_bar);
>
> -#ifdef CONFIG_PPC64 /* for thread.tidr */
> -int pnv_pci_get_as_notify_info(struct task_struct *task, u32 *lpid, u32 *pid,
> - u32 *tid)
> -{
> - struct mm_struct *mm = NULL;
> -
> - if (task == NULL)
> - return -EINVAL;
> -
> - mm = get_task_mm(task);
> - if (mm == NULL)
> - return -EINVAL;
> -
> - *pid = mm->context.id;
> - mmput(mm);
> -
> - *tid = task->thread.tidr;
> - *lpid = mfspr(SPRN_LPID);
> - return 0;
> -}
> -EXPORT_SYMBOL_GPL(pnv_pci_get_as_notify_info);
> -#endif
> -
> void pnv_pci_shutdown(void)
> {
> struct pci_controller *hose;
> diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
> index 4f11c077af62..469c24463247 100644
> --- a/arch/powerpc/platforms/powernv/pci.h
> +++ b/arch/powerpc/platforms/powernv/pci.h
> @@ -195,7 +195,6 @@ extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
> extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
> extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev);
> extern void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq);
> -extern void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
> extern unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
> __u64 window_size, __u32 levels);
> extern int pnv_eeh_post_init(void);
> --
> 2.20.1
>
^ permalink raw reply
* Re: [PATCH 4/4] powerpc/powernv: remove the unused vas_win_paste_addr and vas_win_id functions
From: Oliver O'Halloran @ 2019-06-21 1:40 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Linux Kernel Mailing List, Paul Mackerras, sukadev, linuxppc-dev
In-Reply-To: <20190523074924.19659-5-hch@lst.de>
On Thu, May 23, 2019 at 5:56 PM Christoph Hellwig <hch@lst.de> wrote:
>
> These two function have never been used since they were added to the
> kernel.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
> arch/powerpc/include/asm/vas.h | 10 ----------
> arch/powerpc/platforms/powernv/vas-window.c | 19 -------------------
> arch/powerpc/platforms/powernv/vas.h | 20 --------------------
> 3 files changed, 49 deletions(-)
Sukadev (+cc), what's the reason this is not being used?
IIRC the VAS hardware on P9 had some issues, but I don't know any of
the details.
> diff --git a/arch/powerpc/include/asm/vas.h b/arch/powerpc/include/asm/vas.h
> index 771456227496..9b5b7261df7b 100644
> --- a/arch/powerpc/include/asm/vas.h
> +++ b/arch/powerpc/include/asm/vas.h
> @@ -167,14 +167,4 @@ int vas_copy_crb(void *crb, int offset);
> */
> int vas_paste_crb(struct vas_window *win, int offset, bool re);
>
> -/*
> - * Return a system-wide unique id for the VAS window @win.
> - */
> -extern u32 vas_win_id(struct vas_window *win);
> -
> -/*
> - * Return the power bus paste address associated with @win so the caller
> - * can map that address into their address space.
> - */
> -extern u64 vas_win_paste_addr(struct vas_window *win);
> #endif /* __ASM_POWERPC_VAS_H */
> diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
> index e59e0e60e5b5..e48c44cb3a16 100644
> --- a/arch/powerpc/platforms/powernv/vas-window.c
> +++ b/arch/powerpc/platforms/powernv/vas-window.c
> @@ -44,16 +44,6 @@ static void compute_paste_address(struct vas_window *window, u64 *addr, int *len
> pr_debug("Txwin #%d: Paste addr 0x%llx\n", winid, *addr);
> }
>
> -u64 vas_win_paste_addr(struct vas_window *win)
> -{
> - u64 addr;
> -
> - compute_paste_address(win, &addr, NULL);
> -
> - return addr;
> -}
> -EXPORT_SYMBOL(vas_win_paste_addr);
> -
> static inline void get_hvwc_mmio_bar(struct vas_window *window,
> u64 *start, int *len)
> {
> @@ -1268,12 +1258,3 @@ int vas_win_close(struct vas_window *window)
> return 0;
> }
> EXPORT_SYMBOL_GPL(vas_win_close);
> -
> -/*
> - * Return a system-wide unique window id for the window @win.
> - */
> -u32 vas_win_id(struct vas_window *win)
> -{
> - return encode_pswid(win->vinst->vas_id, win->winid);
> -}
> -EXPORT_SYMBOL_GPL(vas_win_id);
> diff --git a/arch/powerpc/platforms/powernv/vas.h b/arch/powerpc/platforms/powernv/vas.h
> index f5493dbdd7ff..551affaddd59 100644
> --- a/arch/powerpc/platforms/powernv/vas.h
> +++ b/arch/powerpc/platforms/powernv/vas.h
> @@ -448,26 +448,6 @@ static inline u64 read_hvwc_reg(struct vas_window *win,
> return in_be64(win->hvwc_map+reg);
> }
>
> -/*
> - * Encode/decode the Partition Send Window ID (PSWID) for a window in
> - * a way that we can uniquely identify any window in the system. i.e.
> - * we should be able to locate the 'struct vas_window' given the PSWID.
> - *
> - * Bits Usage
> - * 0:7 VAS id (8 bits)
> - * 8:15 Unused, 0 (3 bits)
> - * 16:31 Window id (16 bits)
> - */
> -static inline u32 encode_pswid(int vasid, int winid)
> -{
> - u32 pswid = 0;
> -
> - pswid |= vasid << (31 - 7);
> - pswid |= winid;
> -
> - return pswid;
> -}
> -
> static inline void decode_pswid(u32 pswid, int *vasid, int *winid)
> {
> if (vasid)
> --
> 2.20.1
>
^ permalink raw reply
* Re: [PATCH v2] ocxl: Allow contexts to be attached with a NULL mm
From: Andrew Donnellan @ 2019-06-21 0:22 UTC (permalink / raw)
To: Alastair D'Silva, alastair
Cc: Arnd Bergmann, linux-kernel, Nicholas Piggin, Masahiro Yamada,
Paul Mackerras, Suraj Jitindar Singh, Greg Kroah-Hartman,
Frederic Barrat, Andrew Morton, linuxppc-dev, Thomas Gleixner
In-Reply-To: <20190620041203.12274-1-alastair@au1.ibm.com>
On 20/6/19 2:12 pm, Alastair D'Silva wrote:
> From: Alastair D'Silva <alastair@d-silva.org>
>
> If an OpenCAPI context is to be used directly by a kernel driver, there
> may not be a suitable mm to use.
>
> The patch makes the mm parameter to ocxl_context_attach optional.
>
> Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
Acked-by: Andrew Donnellan <ajd@linux.ibm.com>
> ---
> arch/powerpc/mm/book3s64/radix_tlb.c | 5 +++++
> drivers/misc/ocxl/context.c | 9 ++++++---
> drivers/misc/ocxl/link.c | 28 ++++++++++++++++++++++++----
> 3 files changed, 35 insertions(+), 7 deletions(-)
>
> diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
> index bb9835681315..ce8a77fae6a7 100644
> --- a/arch/powerpc/mm/book3s64/radix_tlb.c
> +++ b/arch/powerpc/mm/book3s64/radix_tlb.c
> @@ -666,6 +666,11 @@ EXPORT_SYMBOL(radix__flush_tlb_page);
> #define radix__flush_all_mm radix__local_flush_all_mm
> #endif /* CONFIG_SMP */
>
> +/*
> + * If kernel TLBIs ever become local rather than global, then
> + * drivers/misc/ocxl/link.c:ocxl_link_add_pe will need some work, as it
> + * assumes kernel TLBIs are global.
> + */
> void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
> {
> _tlbie_pid(0, RIC_FLUSH_ALL);
> diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c
> index bab9c9364184..994563a078eb 100644
> --- a/drivers/misc/ocxl/context.c
> +++ b/drivers/misc/ocxl/context.c
> @@ -69,6 +69,7 @@ static void xsl_fault_error(void *data, u64 addr, u64 dsisr)
> int ocxl_context_attach(struct ocxl_context *ctx, u64 amr, struct mm_struct *mm)
> {
> int rc;
> + unsigned long pidr = 0;
>
> // Locks both status & tidr
> mutex_lock(&ctx->status_mutex);
> @@ -77,9 +78,11 @@ int ocxl_context_attach(struct ocxl_context *ctx, u64 amr, struct mm_struct *mm)
> goto out;
> }
>
> - rc = ocxl_link_add_pe(ctx->afu->fn->link, ctx->pasid,
> - mm->context.id, ctx->tidr, amr, mm,
> - xsl_fault_error, ctx);
> + if (mm)
> + pidr = mm->context.id;
> +
> + rc = ocxl_link_add_pe(ctx->afu->fn->link, ctx->pasid, pidr, ctx->tidr,
> + amr, mm, xsl_fault_error, ctx);
> if (rc)
> goto out;
>
> diff --git a/drivers/misc/ocxl/link.c b/drivers/misc/ocxl/link.c
> index cce5b0d64505..58d111afd9f6 100644
> --- a/drivers/misc/ocxl/link.c
> +++ b/drivers/misc/ocxl/link.c
> @@ -224,6 +224,17 @@ static irqreturn_t xsl_fault_handler(int irq, void *data)
> ack_irq(spa, ADDRESS_ERROR);
> return IRQ_HANDLED;
> }
> +
> + if (!pe_data->mm) {
> + /*
> + * translation fault from a kernel context - an OpenCAPI
> + * device tried to access a bad kernel address
> + */
> + rcu_read_unlock();
> + pr_warn("Unresolved OpenCAPI xsl fault in kernel context\n");
> + ack_irq(spa, ADDRESS_ERROR);
> + return IRQ_HANDLED;
> + }
> WARN_ON(pe_data->mm->context.id != pid);
>
> if (mmget_not_zero(pe_data->mm)) {
> @@ -523,7 +534,13 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,
> pe->amr = cpu_to_be64(amr);
> pe->software_state = cpu_to_be32(SPA_PE_VALID);
>
> - mm_context_add_copro(mm);
> + /*
> + * For user contexts, register a copro so that TLBIs are seen
> + * by the nest MMU. If we have a kernel context, TLBIs are
> + * already global.
> + */
> + if (mm)
> + mm_context_add_copro(mm);
> /*
> * Barrier is to make sure PE is visible in the SPA before it
> * is used by the device. It also helps with the global TLBI
> @@ -546,7 +563,8 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,
> * have a reference on mm_users. Incrementing mm_count solves
> * the problem.
> */
> - mmgrab(mm);
> + if (mm)
> + mmgrab(mm);
> trace_ocxl_context_add(current->pid, spa->spa_mem, pasid, pidr, tidr);
> unlock:
> mutex_unlock(&spa->spa_lock);
> @@ -652,8 +670,10 @@ int ocxl_link_remove_pe(void *link_handle, int pasid)
> if (!pe_data) {
> WARN(1, "Couldn't find pe data when removing PE\n");
> } else {
> - mm_context_remove_copro(pe_data->mm);
> - mmdrop(pe_data->mm);
> + if (pe_data->mm) {
> + mm_context_remove_copro(pe_data->mm);
> + mmdrop(pe_data->mm);
> + }
> kfree_rcu(pe_data, rcu);
> }
> unlock:
>
--
Andrew Donnellan OzLabs, ADL Canberra
ajd@linux.ibm.com IBM Australia Limited
^ permalink raw reply
* [PATCH v3 6/6] drivers/base/memory.c: Get rid of find_memory_block_hinted()
From: David Hildenbrand @ 2019-06-20 18:31 UTC (permalink / raw)
To: linux-kernel
Cc: Stephen Rothwell, Pavel Tatashin, David Hildenbrand,
mike.travis@hpe.com, Greg Kroah-Hartman, Rafael J. Wysocki,
linux-mm, linux-acpi, Dan Williams, linuxppc-dev, Andrew Morton
In-Reply-To: <20190620183139.4352-1-david@redhat.com>
No longer needed, let's remove it. Also, drop the "hint" parameter
completely from "find_memory_block_by_id", as nobody needs it anymore.
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: "mike.travis@hpe.com" <mike.travis@hpe.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
drivers/base/memory.c | 37 +++++++++++--------------------------
include/linux/memory.h | 2 --
2 files changed, 11 insertions(+), 28 deletions(-)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 0204384b4d1d..195dbcb8e8a8 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -588,30 +588,13 @@ int __weak arch_get_memory_phys_device(unsigned long start_pfn)
return 0;
}
-/*
- * A reference for the returned object is held and the reference for the
- * hinted object is released.
- */
-static struct memory_block *find_memory_block_by_id(unsigned long block_id,
- struct memory_block *hint)
+/* A reference for the returned memory block device is acquired. */
+static struct memory_block *find_memory_block_by_id(unsigned long block_id)
{
- struct device *hintdev = hint ? &hint->dev : NULL;
struct device *dev;
- dev = subsys_find_device_by_id(&memory_subsys, block_id, hintdev);
- if (hint)
- put_device(&hint->dev);
- if (!dev)
- return NULL;
- return to_memory_block(dev);
-}
-
-struct memory_block *find_memory_block_hinted(struct mem_section *section,
- struct memory_block *hint)
-{
- unsigned long block_id = base_memory_block_id(__section_nr(section));
-
- return find_memory_block_by_id(block_id, hint);
+ dev = subsys_find_device_by_id(&memory_subsys, block_id, NULL);
+ return dev ? to_memory_block(dev) : NULL;
}
/*
@@ -624,7 +607,9 @@ struct memory_block *find_memory_block_hinted(struct mem_section *section,
*/
struct memory_block *find_memory_block(struct mem_section *section)
{
- return find_memory_block_hinted(section, NULL);
+ unsigned long block_id = base_memory_block_id(__section_nr(section));
+
+ return find_memory_block_by_id(block_id);
}
static struct attribute *memory_memblk_attrs[] = {
@@ -675,7 +660,7 @@ static int init_memory_block(struct memory_block **memory,
unsigned long start_pfn;
int ret = 0;
- mem = find_memory_block_by_id(block_id, NULL);
+ mem = find_memory_block_by_id(block_id);
if (mem) {
put_device(&mem->dev);
return -EEXIST;
@@ -755,7 +740,7 @@ int create_memory_block_devices(unsigned long start, unsigned long size)
end_block_id = block_id;
for (block_id = start_block_id; block_id != end_block_id;
block_id++) {
- mem = find_memory_block_by_id(block_id, NULL);
+ mem = find_memory_block_by_id(block_id);
mem->section_count = 0;
unregister_memory(mem);
}
@@ -782,7 +767,7 @@ void remove_memory_block_devices(unsigned long start, unsigned long size)
mutex_lock(&mem_sysfs_mutex);
for (block_id = start_block_id; block_id != end_block_id; block_id++) {
- mem = find_memory_block_by_id(block_id, NULL);
+ mem = find_memory_block_by_id(block_id);
if (WARN_ON_ONCE(!mem))
continue;
mem->section_count = 0;
@@ -882,7 +867,7 @@ int walk_memory_blocks(unsigned long start, unsigned long size,
int ret = 0;
for (block_id = start_block_id; block_id <= end_block_id; block_id++) {
- mem = find_memory_block_by_id(block_id, NULL);
+ mem = find_memory_block_by_id(block_id);
if (!mem)
continue;
diff --git a/include/linux/memory.h b/include/linux/memory.h
index b3b388775a30..02e633f3ede0 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -116,8 +116,6 @@ void remove_memory_block_devices(unsigned long start, unsigned long size);
extern int memory_dev_init(void);
extern int memory_notify(unsigned long val, void *v);
extern int memory_isolate_notify(unsigned long val, void *v);
-extern struct memory_block *find_memory_block_hinted(struct mem_section *,
- struct memory_block *);
extern struct memory_block *find_memory_block(struct mem_section *);
typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *);
extern int walk_memory_blocks(unsigned long start, unsigned long size,
--
2.21.0
^ permalink raw reply related
* [PATCH v3 5/6] mm/memory_hotplug: Move and simplify walk_memory_blocks()
From: David Hildenbrand @ 2019-06-20 18:31 UTC (permalink / raw)
To: linux-kernel
Cc: Oscar Salvador, Stephen Rothwell, Michal Hocko, Pavel Tatashin,
David Hildenbrand, mike.travis@hpe.com, Greg Kroah-Hartman,
Rafael J. Wysocki, Wei Yang, linux-mm, linux-acpi, Andrew Banman,
Arun KS, Qian Cai, Dan Williams, linuxppc-dev, Andrew Morton
In-Reply-To: <20190620183139.4352-1-david@redhat.com>
Let's move walk_memory_blocks() to the place where memory block logic
resides and simplify it. While at it, add a type for the callback function.
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Andrew Banman <andrew.banman@hpe.com>
Cc: "mike.travis@hpe.com" <mike.travis@hpe.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Arun KS <arunks@codeaurora.org>
Cc: Qian Cai <cai@lca.pw>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
drivers/base/memory.c | 42 ++++++++++++++++++++++++++
include/linux/memory.h | 3 ++
include/linux/memory_hotplug.h | 2 --
mm/memory_hotplug.c | 55 ----------------------------------
4 files changed, 45 insertions(+), 57 deletions(-)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index c54e80fd25a8..0204384b4d1d 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -44,6 +44,11 @@ static inline unsigned long pfn_to_block_id(unsigned long pfn)
return base_memory_block_id(pfn_to_section_nr(pfn));
}
+static inline unsigned long phys_to_block_id(unsigned long phys)
+{
+ return pfn_to_block_id(PFN_DOWN(phys));
+}
+
static int memory_subsys_online(struct device *dev);
static int memory_subsys_offline(struct device *dev);
@@ -851,3 +856,40 @@ int __init memory_dev_init(void)
printk(KERN_ERR "%s() failed: %d\n", __func__, ret);
return ret;
}
+
+/**
+ * walk_memory_blocks - walk through all present memory blocks overlapped
+ * by the range [start, start + size)
+ *
+ * @start: start address of the memory range
+ * @size: size of the memory range
+ * @arg: argument passed to func
+ * @func: callback for each memory section walked
+ *
+ * This function walks through all present memory blocks overlapped by the
+ * range [start, start + size), calling func on each memory block.
+ *
+ * In case func() returns an error, walking is aborted and the error is
+ * returned.
+ */
+int walk_memory_blocks(unsigned long start, unsigned long size,
+ void *arg, walk_memory_blocks_func_t func)
+{
+ const unsigned long start_block_id = phys_to_block_id(start);
+ const unsigned long end_block_id = phys_to_block_id(start + size - 1);
+ struct memory_block *mem;
+ unsigned long block_id;
+ int ret = 0;
+
+ for (block_id = start_block_id; block_id <= end_block_id; block_id++) {
+ mem = find_memory_block_by_id(block_id, NULL);
+ if (!mem)
+ continue;
+
+ ret = func(mem, arg);
+ put_device(&mem->dev);
+ if (ret)
+ break;
+ }
+ return ret;
+}
diff --git a/include/linux/memory.h b/include/linux/memory.h
index f26a5417ec5d..b3b388775a30 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -119,6 +119,9 @@ extern int memory_isolate_notify(unsigned long val, void *v);
extern struct memory_block *find_memory_block_hinted(struct mem_section *,
struct memory_block *);
extern struct memory_block *find_memory_block(struct mem_section *);
+typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *);
+extern int walk_memory_blocks(unsigned long start, unsigned long size,
+ void *arg, walk_memory_blocks_func_t func);
#define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION<<PAGE_SHIFT)
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index d9fffc34949f..475aff8efbf8 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -340,8 +340,6 @@ static inline void __remove_memory(int nid, u64 start, u64 size) {}
#endif /* CONFIG_MEMORY_HOTREMOVE */
extern void __ref free_area_init_core_hotplug(int nid);
-extern int walk_memory_blocks(unsigned long start, unsigned long size,
- void *arg, int (*func)(struct memory_block *, void *));
extern int __add_memory(int nid, u64 start, u64 size);
extern int add_memory(int nid, u64 start, u64 size);
extern int add_memory_resource(int nid, struct resource *resource);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 122a7d31efdd..fc558e9ff939 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1661,62 +1661,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
{
return __offline_pages(start_pfn, start_pfn + nr_pages);
}
-#endif /* CONFIG_MEMORY_HOTREMOVE */
-/**
- * walk_memory_blocks - walk through all present memory blocks overlapped
- * by the range [start, start + size)
- *
- * @start: start address of the memory range
- * @size: size of the memory range
- * @arg: argument passed to func
- * @func: callback for each memory block walked
- *
- * This function walks through all present memory blocks overlapped by the
- * range [start, start + size), calling func on each memory block.
- *
- * Returns the return value of func.
- */
-int walk_memory_blocks(unsigned long start, unsigned long size,
- void *arg, int (*func)(struct memory_block *, void *))
-{
- const unsigned long start_pfn = PFN_DOWN(start);
- const unsigned long end_pfn = PFN_UP(start + size - 1);
- struct memory_block *mem = NULL;
- struct mem_section *section;
- unsigned long pfn, section_nr;
- int ret;
-
- for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
- section_nr = pfn_to_section_nr(pfn);
- if (!present_section_nr(section_nr))
- continue;
-
- section = __nr_to_section(section_nr);
- /* same memblock? */
- if (mem)
- if ((section_nr >= mem->start_section_nr) &&
- (section_nr <= mem->end_section_nr))
- continue;
-
- mem = find_memory_block_hinted(section, mem);
- if (!mem)
- continue;
-
- ret = func(mem, arg);
- if (ret) {
- kobject_put(&mem->dev.kobj);
- return ret;
- }
- }
-
- if (mem)
- kobject_put(&mem->dev.kobj);
-
- return 0;
-}
-
-#ifdef CONFIG_MEMORY_HOTREMOVE
static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
{
int ret = !is_memblock_offlined(mem);
--
2.21.0
^ permalink raw reply related
* [PATCH v3 4/6] mm/memory_hotplug: Rename walk_memory_range() and pass start+size instead of pfns
From: David Hildenbrand @ 2019-06-20 18:31 UTC (permalink / raw)
To: linux-kernel
Cc: Michal Hocko, David Hildenbrand, Wei Yang, linux-mm,
Paul Mackerras, Rashmica Gupta, Dan Williams, Michael Neuling,
linux-acpi, Len Brown, Pavel Tatashin, Anshuman Khandual,
Qian Cai, Thomas Gleixner, Oscar Salvador, Juergen Gross,
Greg Kroah-Hartman, Rafael J. Wysocki, Arun KS, Andrew Morton,
linuxppc-dev
In-Reply-To: <20190620183139.4352-1-david@redhat.com>
walk_memory_range() was once used to iterate over sections. Now, it
iterates over memory blocks. Rename the function, fixup the
documentation. Also, pass start+size instead of PFNs, which is what most
callers already have at hand. (we'll rework link_mem_sections() most
probably soon)
Follow-up patches wil rework, simplify, and move walk_memory_blocks() to
drivers/base/memory.c.
Note: walk_memory_blocks() only works correctly right now if the
start_pfn is aligned to a section start. This is the case right now,
but we'll generalize the function in a follow up patch so the semantics
match the documentation.
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Rashmica Gupta <rashmica.g@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Pavel Tatashin <pavel.tatashin@microsoft.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Arun KS <arunks@codeaurora.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
arch/powerpc/platforms/powernv/memtrace.c | 23 +++++++++++-----------
drivers/acpi/acpi_memhotplug.c | 19 ++++--------------
drivers/base/node.c | 5 +++--
include/linux/memory_hotplug.h | 2 +-
mm/memory_hotplug.c | 24 ++++++++++++-----------
5 files changed, 32 insertions(+), 41 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 5e53c1392d3b..eb2e75dac369 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -70,23 +70,23 @@ static int change_memblock_state(struct memory_block *mem, void *arg)
/* called with device_hotplug_lock held */
static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages)
{
- u64 end_pfn = start_pfn + nr_pages - 1;
+ const unsigned long start = PFN_PHYS(start_pfn);
+ const unsigned long size = PFN_PHYS(nr_pages);
- if (walk_memory_range(start_pfn, end_pfn, NULL,
- check_memblock_online))
+ if (walk_memory_blocks(start, size, NULL, check_memblock_online))
return false;
- walk_memory_range(start_pfn, end_pfn, (void *)MEM_GOING_OFFLINE,
- change_memblock_state);
+ walk_memory_blocks(start, size, (void *)MEM_GOING_OFFLINE,
+ change_memblock_state);
if (offline_pages(start_pfn, nr_pages)) {
- walk_memory_range(start_pfn, end_pfn, (void *)MEM_ONLINE,
- change_memblock_state);
+ walk_memory_blocks(start, size, (void *)MEM_ONLINE,
+ change_memblock_state);
return false;
}
- walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE,
- change_memblock_state);
+ walk_memory_blocks(start, size, (void *)MEM_OFFLINE,
+ change_memblock_state);
return true;
@@ -242,9 +242,8 @@ static int memtrace_online(void)
*/
if (!memhp_auto_online) {
lock_device_hotplug();
- walk_memory_range(PFN_DOWN(ent->start),
- PFN_UP(ent->start + ent->size - 1),
- NULL, online_mem_block);
+ walk_memory_blocks(ent->start, ent->size, NULL,
+ online_mem_block);
unlock_device_hotplug();
}
diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index db013dc21c02..e294f44a7850 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -155,16 +155,6 @@ static int acpi_memory_check_device(struct acpi_memory_device *mem_device)
return 0;
}
-static unsigned long acpi_meminfo_start_pfn(struct acpi_memory_info *info)
-{
- return PFN_DOWN(info->start_addr);
-}
-
-static unsigned long acpi_meminfo_end_pfn(struct acpi_memory_info *info)
-{
- return PFN_UP(info->start_addr + info->length-1);
-}
-
static int acpi_bind_memblk(struct memory_block *mem, void *arg)
{
return acpi_bind_one(&mem->dev, arg);
@@ -173,9 +163,8 @@ static int acpi_bind_memblk(struct memory_block *mem, void *arg)
static int acpi_bind_memory_blocks(struct acpi_memory_info *info,
struct acpi_device *adev)
{
- return walk_memory_range(acpi_meminfo_start_pfn(info),
- acpi_meminfo_end_pfn(info), adev,
- acpi_bind_memblk);
+ return walk_memory_blocks(info->start_addr, info->length, adev,
+ acpi_bind_memblk);
}
static int acpi_unbind_memblk(struct memory_block *mem, void *arg)
@@ -186,8 +175,8 @@ static int acpi_unbind_memblk(struct memory_block *mem, void *arg)
static void acpi_unbind_memory_blocks(struct acpi_memory_info *info)
{
- walk_memory_range(acpi_meminfo_start_pfn(info),
- acpi_meminfo_end_pfn(info), NULL, acpi_unbind_memblk);
+ walk_memory_blocks(info->start_addr, info->length, NULL,
+ acpi_unbind_memblk);
}
static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
diff --git a/drivers/base/node.c b/drivers/base/node.c
index e6364e3e3e31..d8c02e65df68 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -833,8 +833,9 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn)
{
- return walk_memory_range(start_pfn, end_pfn, (void *)&nid,
- register_mem_sect_under_node);
+ return walk_memory_blocks(PFN_PHYS(start_pfn),
+ PFN_PHYS(end_pfn - start_pfn), (void *)&nid,
+ register_mem_sect_under_node);
}
#ifdef CONFIG_HUGETLBFS
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 79e0add6a597..d9fffc34949f 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -340,7 +340,7 @@ static inline void __remove_memory(int nid, u64 start, u64 size) {}
#endif /* CONFIG_MEMORY_HOTREMOVE */
extern void __ref free_area_init_core_hotplug(int nid);
-extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
+extern int walk_memory_blocks(unsigned long start, unsigned long size,
void *arg, int (*func)(struct memory_block *, void *));
extern int __add_memory(int nid, u64 start, u64 size);
extern int add_memory(int nid, u64 start, u64 size);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a88c5f334e5a..122a7d31efdd 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1126,8 +1126,7 @@ int __ref add_memory_resource(int nid, struct resource *res)
/* online pages if requested */
if (memhp_auto_online)
- walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1),
- NULL, online_memory_block);
+ walk_memory_blocks(start, size, NULL, online_memory_block);
return ret;
error:
@@ -1665,20 +1664,24 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
#endif /* CONFIG_MEMORY_HOTREMOVE */
/**
- * walk_memory_range - walks through all mem sections in [start_pfn, end_pfn)
- * @start_pfn: start pfn of the memory range
- * @end_pfn: end pfn of the memory range
+ * walk_memory_blocks - walk through all present memory blocks overlapped
+ * by the range [start, start + size)
+ *
+ * @start: start address of the memory range
+ * @size: size of the memory range
* @arg: argument passed to func
- * @func: callback for each memory section walked
+ * @func: callback for each memory block walked
*
- * This function walks through all present mem sections in range
- * [start_pfn, end_pfn) and call func on each mem section.
+ * This function walks through all present memory blocks overlapped by the
+ * range [start, start + size), calling func on each memory block.
*
* Returns the return value of func.
*/
-int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
+int walk_memory_blocks(unsigned long start, unsigned long size,
void *arg, int (*func)(struct memory_block *, void *))
{
+ const unsigned long start_pfn = PFN_DOWN(start);
+ const unsigned long end_pfn = PFN_UP(start + size - 1);
struct memory_block *mem = NULL;
struct mem_section *section;
unsigned long pfn, section_nr;
@@ -1824,8 +1827,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
* whether all memory blocks in question are offline and return error
* if this is not the case.
*/
- rc = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL,
- check_memblock_offlined_cb);
+ rc = walk_memory_blocks(start, size, NULL, check_memblock_offlined_cb);
if (rc)
goto done;
--
2.21.0
^ permalink raw reply related
* [PATCH v3 0/6] mm: Further memory block device cleanups
From: David Hildenbrand @ 2019-06-20 18:31 UTC (permalink / raw)
To: linux-kernel
Cc: Oscar Salvador, Michal Hocko, David Hildenbrand, Wei Yang,
Keith Busch, linux-mm, Arun KS, Rashmica Gupta, Thomas Gleixner,
Stephen Rothwell, Michael Neuling, Baoquan He, Rafael J. Wysocki,
Pavel Tatashin, linux-acpi, Len Brown, Pavel Tatashin,
Pavel Tatashin, Anshuman Khandual, mike.travis@hpe.com,
linuxppc-dev, Mike Rapoport, Qian Cai, Dan Williams,
Vlastimil Babka, Oscar Salvador, Juergen Gross, Andrew Banman,
Greg Kroah-Hartman, Rafael J. Wysocki, Johannes Weiner,
Paul Mackerras, Andrew Morton, Mel Gorman
@Andrew: Only patch 1, 4 and 6 changed compared to v1.
Some further cleanups around memory block devices. Especially, clean up
and simplify walk_memory_range(). Including some other minor cleanups.
Compiled + tested on x86 with DIMMs under QEMU. Compile-tested on ppc64.
v2 -> v3:
- "mm/memory_hotplug: Rename walk_memory_range() and pass start+size .."
-- Avoid warning on ppc.
- "drivers/base/memory.c: Get rid of find_memory_block_hinted()"
-- Fixup a comment regarding hinted devices.
v1 -> v2:
- "mm: Section numbers use the type "unsigned long""
-- "unsigned long i" -> "unsigned long nr", in one case -> "int i"
- "drivers/base/memory.c: Get rid of find_memory_block_hinted("
-- Fix compilation error
-- Get rid of the "hint" parameter completely
David Hildenbrand (6):
mm: Section numbers use the type "unsigned long"
drivers/base/memory: Use "unsigned long" for block ids
mm: Make register_mem_sect_under_node() static
mm/memory_hotplug: Rename walk_memory_range() and pass start+size
instead of pfns
mm/memory_hotplug: Move and simplify walk_memory_blocks()
drivers/base/memory.c: Get rid of find_memory_block_hinted()
arch/powerpc/platforms/powernv/memtrace.c | 23 ++---
drivers/acpi/acpi_memhotplug.c | 19 +---
drivers/base/memory.c | 120 +++++++++++++---------
drivers/base/node.c | 8 +-
include/linux/memory.h | 5 +-
include/linux/memory_hotplug.h | 2 -
include/linux/mmzone.h | 4 +-
include/linux/node.h | 7 --
mm/memory_hotplug.c | 57 +---------
mm/sparse.c | 12 +--
10 files changed, 106 insertions(+), 151 deletions(-)
--
2.21.0
^ permalink raw reply
* [PATCH v3 3/6] mm: Make register_mem_sect_under_node() static
From: David Hildenbrand @ 2019-06-20 18:31 UTC (permalink / raw)
To: linux-kernel
Cc: Keith Busch, David Hildenbrand, Greg Kroah-Hartman,
Rafael J. Wysocki, linux-mm, linux-acpi, Dan Williams,
linuxppc-dev, Andrew Morton, Oscar Salvador
In-Reply-To: <20190620183139.4352-1-david@redhat.com>
It is only used internally.
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Oscar Salvador <osalvador@suse.de>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
drivers/base/node.c | 3 ++-
include/linux/node.h | 7 -------
2 files changed, 2 insertions(+), 8 deletions(-)
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 9be88fd05147..e6364e3e3e31 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -752,7 +752,8 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
}
/* register memory section under specified node if it spans that node */
-int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg)
+static int register_mem_sect_under_node(struct memory_block *mem_blk,
+ void *arg)
{
int ret, nid = *(int *)arg;
unsigned long pfn, sect_start_pfn, sect_end_pfn;
diff --git a/include/linux/node.h b/include/linux/node.h
index 548c226966a2..4866f32a02d8 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -137,8 +137,6 @@ static inline int register_one_node(int nid)
extern void unregister_one_node(int nid);
extern int register_cpu_under_node(unsigned int cpu, unsigned int nid);
extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
-extern int register_mem_sect_under_node(struct memory_block *mem_blk,
- void *arg);
extern void unregister_memory_block_under_nodes(struct memory_block *mem_blk);
extern int register_memory_node_under_compute_node(unsigned int mem_nid,
@@ -170,11 +168,6 @@ static inline int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
{
return 0;
}
-static inline int register_mem_sect_under_node(struct memory_block *mem_blk,
- void *arg)
-{
- return 0;
-}
static inline void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
{
}
--
2.21.0
^ permalink raw reply related
* [PATCH v3 2/6] drivers/base/memory: Use "unsigned long" for block ids
From: David Hildenbrand @ 2019-06-20 18:31 UTC (permalink / raw)
To: linux-kernel
Cc: David Hildenbrand, Greg Kroah-Hartman, Rafael J. Wysocki,
linux-mm, linux-acpi, Dan Williams, linuxppc-dev, Andrew Morton
In-Reply-To: <20190620183139.4352-1-david@redhat.com>
Block ids are just shifted section numbers, so let's also use
"unsigned long" for them, too.
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
drivers/base/memory.c | 22 +++++++++++-----------
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 5947b5a5686d..c54e80fd25a8 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -34,12 +34,12 @@ static DEFINE_MUTEX(mem_sysfs_mutex);
static int sections_per_block;
-static inline int base_memory_block_id(unsigned long section_nr)
+static inline unsigned long base_memory_block_id(unsigned long section_nr)
{
return section_nr / sections_per_block;
}
-static inline int pfn_to_block_id(unsigned long pfn)
+static inline unsigned long pfn_to_block_id(unsigned long pfn)
{
return base_memory_block_id(pfn_to_section_nr(pfn));
}
@@ -587,7 +587,7 @@ int __weak arch_get_memory_phys_device(unsigned long start_pfn)
* A reference for the returned object is held and the reference for the
* hinted object is released.
*/
-static struct memory_block *find_memory_block_by_id(int block_id,
+static struct memory_block *find_memory_block_by_id(unsigned long block_id,
struct memory_block *hint)
{
struct device *hintdev = hint ? &hint->dev : NULL;
@@ -604,7 +604,7 @@ static struct memory_block *find_memory_block_by_id(int block_id,
struct memory_block *find_memory_block_hinted(struct mem_section *section,
struct memory_block *hint)
{
- int block_id = base_memory_block_id(__section_nr(section));
+ unsigned long block_id = base_memory_block_id(__section_nr(section));
return find_memory_block_by_id(block_id, hint);
}
@@ -663,8 +663,8 @@ int register_memory(struct memory_block *memory)
return ret;
}
-static int init_memory_block(struct memory_block **memory, int block_id,
- unsigned long state)
+static int init_memory_block(struct memory_block **memory,
+ unsigned long block_id, unsigned long state)
{
struct memory_block *mem;
unsigned long start_pfn;
@@ -729,8 +729,8 @@ static void unregister_memory(struct memory_block *memory)
*/
int create_memory_block_devices(unsigned long start, unsigned long size)
{
- const int start_block_id = pfn_to_block_id(PFN_DOWN(start));
- int end_block_id = pfn_to_block_id(PFN_DOWN(start + size));
+ const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start));
+ unsigned long end_block_id = pfn_to_block_id(PFN_DOWN(start + size));
struct memory_block *mem;
unsigned long block_id;
int ret = 0;
@@ -766,10 +766,10 @@ int create_memory_block_devices(unsigned long start, unsigned long size)
*/
void remove_memory_block_devices(unsigned long start, unsigned long size)
{
- const int start_block_id = pfn_to_block_id(PFN_DOWN(start));
- const int end_block_id = pfn_to_block_id(PFN_DOWN(start + size));
+ const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start));
+ const unsigned long end_block_id = pfn_to_block_id(PFN_DOWN(start + size));
struct memory_block *mem;
- int block_id;
+ unsigned long block_id;
if (WARN_ON_ONCE(!IS_ALIGNED(start, memory_block_size_bytes()) ||
!IS_ALIGNED(size, memory_block_size_bytes())))
--
2.21.0
^ permalink raw reply related
* [PATCH v3 1/6] mm: Section numbers use the type "unsigned long"
From: David Hildenbrand @ 2019-06-20 18:31 UTC (permalink / raw)
To: linux-kernel
Cc: Stephen Rothwell, Michal Hocko, Pavel Tatashin, Baoquan He,
David Hildenbrand, Greg Kroah-Hartman, Rafael J. Wysocki,
Mel Gorman, Wei Yang, linux-mm, linux-acpi, Mike Rapoport,
Arun KS, Johannes Weiner, Dan Williams, linuxppc-dev,
Andrew Morton, Vlastimil Babka, Oscar Salvador
In-Reply-To: <20190620183139.4352-1-david@redhat.com>
We are using a mixture of "int" and "unsigned long". Let's make this
consistent by using "unsigned long" everywhere. We'll do the same with
memory block ids next.
While at it, turn the "unsigned long i" in removable_show() into an
int - sections_per_block is an int.
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Arun KS <arunks@codeaurora.org>
Cc: Pavel Tatashin <pasha.tatashin@oracle.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Baoquan He <bhe@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
drivers/base/memory.c | 27 +++++++++++++--------------
include/linux/mmzone.h | 4 ++--
mm/sparse.c | 12 ++++++------
3 files changed, 21 insertions(+), 22 deletions(-)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 826dd76f662e..5947b5a5686d 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -34,7 +34,7 @@ static DEFINE_MUTEX(mem_sysfs_mutex);
static int sections_per_block;
-static inline int base_memory_block_id(int section_nr)
+static inline int base_memory_block_id(unsigned long section_nr)
{
return section_nr / sections_per_block;
}
@@ -131,9 +131,9 @@ static ssize_t phys_index_show(struct device *dev,
static ssize_t removable_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
- unsigned long i, pfn;
- int ret = 1;
struct memory_block *mem = to_memory_block(dev);
+ unsigned long pfn;
+ int ret = 1, i;
if (mem->state != MEM_ONLINE)
goto out;
@@ -691,15 +691,15 @@ static int init_memory_block(struct memory_block **memory, int block_id,
return ret;
}
-static int add_memory_block(int base_section_nr)
+static int add_memory_block(unsigned long base_section_nr)
{
+ int ret, section_count = 0;
struct memory_block *mem;
- int i, ret, section_count = 0;
+ unsigned long nr;
- for (i = base_section_nr;
- i < base_section_nr + sections_per_block;
- i++)
- if (present_section_nr(i))
+ for (nr = base_section_nr; nr < base_section_nr + sections_per_block;
+ nr++)
+ if (present_section_nr(nr))
section_count++;
if (section_count == 0)
@@ -822,10 +822,9 @@ static const struct attribute_group *memory_root_attr_groups[] = {
*/
int __init memory_dev_init(void)
{
- unsigned int i;
int ret;
int err;
- unsigned long block_sz;
+ unsigned long block_sz, nr;
ret = subsys_system_register(&memory_subsys, memory_root_attr_groups);
if (ret)
@@ -839,9 +838,9 @@ int __init memory_dev_init(void)
* during boot and have been initialized
*/
mutex_lock(&mem_sysfs_mutex);
- for (i = 0; i <= __highest_present_section_nr;
- i += sections_per_block) {
- err = add_memory_block(i);
+ for (nr = 0; nr <= __highest_present_section_nr;
+ nr += sections_per_block) {
+ err = add_memory_block(nr);
if (!ret)
ret = err;
}
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 427b79c39b3c..83b6aae16f13 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1220,7 +1220,7 @@ static inline struct mem_section *__nr_to_section(unsigned long nr)
return NULL;
return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
}
-extern int __section_nr(struct mem_section* ms);
+extern unsigned long __section_nr(struct mem_section *ms);
extern unsigned long usemap_size(void);
/*
@@ -1292,7 +1292,7 @@ static inline struct mem_section *__pfn_to_section(unsigned long pfn)
return __nr_to_section(pfn_to_section_nr(pfn));
}
-extern int __highest_present_section_nr;
+extern unsigned long __highest_present_section_nr;
#ifndef CONFIG_HAVE_ARCH_PFN_VALID
static inline int pfn_valid(unsigned long pfn)
diff --git a/mm/sparse.c b/mm/sparse.c
index 1552c855d62a..e8c57e039be8 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -102,7 +102,7 @@ static inline int sparse_index_init(unsigned long section_nr, int nid)
#endif
#ifdef CONFIG_SPARSEMEM_EXTREME
-int __section_nr(struct mem_section* ms)
+unsigned long __section_nr(struct mem_section *ms)
{
unsigned long root_nr;
struct mem_section *root = NULL;
@@ -121,9 +121,9 @@ int __section_nr(struct mem_section* ms)
return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
}
#else
-int __section_nr(struct mem_section* ms)
+unsigned long __section_nr(struct mem_section *ms)
{
- return (int)(ms - mem_section[0]);
+ return (unsigned long)(ms - mem_section[0]);
}
#endif
@@ -178,10 +178,10 @@ void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
* Keeping track of this gives us an easy way to break out of
* those loops early.
*/
-int __highest_present_section_nr;
+unsigned long __highest_present_section_nr;
static void section_mark_present(struct mem_section *ms)
{
- int section_nr = __section_nr(ms);
+ unsigned long section_nr = __section_nr(ms);
if (section_nr > __highest_present_section_nr)
__highest_present_section_nr = section_nr;
@@ -189,7 +189,7 @@ static void section_mark_present(struct mem_section *ms)
ms->section_mem_map |= SECTION_MARKED_PRESENT;
}
-static inline int next_present_section_nr(int section_nr)
+static inline unsigned long next_present_section_nr(unsigned long section_nr)
{
do {
section_nr++;
--
2.21.0
^ permalink raw reply related
* Re: [PATCH v2 6/6] drivers/base/memory.c: Get rid of find_memory_block_hinted()
From: David Hildenbrand @ 2019-06-20 18:25 UTC (permalink / raw)
To: linux-kernel
Cc: Stephen Rothwell, Pavel Tatashin, linux-mm, mike.travis@hpe.com,
Greg Kroah-Hartman, Rafael J. Wysocki, linux-acpi, Dan Williams,
linuxppc-dev, Andrew Morton
In-Reply-To: <20190620103520.23481-7-david@redhat.com>
On 20.06.19 12:35, David Hildenbrand wrote:
> No longer needed, let's remove it. Also, drop the "hint" parameter
> completely from "find_memory_block_by_id", as nobody needs it anymore.
>
> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> Cc: "Rafael J. Wysocki" <rafael@kernel.org>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Stephen Rothwell <sfr@canb.auug.org.au>
> Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
> Cc: "mike.travis@hpe.com" <mike.travis@hpe.com>
> Signed-off-by: David Hildenbrand <david@redhat.com>
> ---
> drivers/base/memory.c | 32 ++++++++++----------------------
> include/linux/memory.h | 2 --
> 2 files changed, 10 insertions(+), 24 deletions(-)
>
> diff --git a/drivers/base/memory.c b/drivers/base/memory.c
> index 0204384b4d1d..fefb64d3588e 100644
> --- a/drivers/base/memory.c
> +++ b/drivers/base/memory.c
> @@ -592,26 +592,12 @@ int __weak arch_get_memory_phys_device(unsigned long start_pfn)
> * A reference for the returned object is held and the reference for the
> * hinted object is released.
> */
I'll fixup this comment as well (yes, I desperately need vacation :) )
--
Thanks,
David / dhildenb
^ permalink raw reply
* Re: [PATCH 16/16] mm: pass get_user_pages_fast iterator arguments in a structure
From: Linus Torvalds @ 2019-06-20 17:21 UTC (permalink / raw)
To: Nicholas Piggin
Cc: Rich Felker, Yoshinori Sato, Linux-sh list, James Hogan,
the arch/x86 maintainers, Linux List Kernel Mailing,
David S. Miller, Linux-MM, Khalid Aziz, Paul Burton,
Andrey Konovalov, sparclinux, Paul Mackerras, linux-mips,
linuxppc-dev, Christoph Hellwig
In-Reply-To: <1561032202.0qfct43s2c.astroid@bobo.none>
On Thu, Jun 20, 2019 at 5:19 AM Nicholas Piggin <npiggin@gmail.com> wrote:
>
> The processor aliasing problem happens because the struct will
> be initialised with stores using one base register (e.g., stack
> register), and then same memory is loaded using a different
> register (e.g., parameter register).
Hmm. Honestly, I've never seen anything like that in any kernel profiles.
Compared to the problems I _do_ see (which is usually the obvious
cache misses, and locking), it must either be in the noise or it's
some problem specific to whatever CPU you are doing performance work
on?
I've occasionally seen pipeline hiccups in profiles, but it's usually
been either some serious glass jaw of the core, or it's been something
really stupid we did (or occasionally that the compiler did: one in
particular I remember was how there was a time when gcc would narrow
stores when it could, so if you set a bit in a word, it would do it
with a byte store, and then when you read the whole word afterwards
you'd get a major pipeline stall and it happened to show up in some
really hot paths).
Linus
^ permalink raw reply
* Re: [PATCH v2 4/6] mm/memory_hotplug: Rename walk_memory_range() and pass start+size instead of pfns
From: David Hildenbrand @ 2019-06-20 16:37 UTC (permalink / raw)
To: Nathan Chancellor
Cc: Michal Hocko, Wei Yang, linux-mm, Paul Mackerras, Rashmica Gupta,
Dan Williams, Michael Neuling, linux-acpi, Len Brown,
Pavel Tatashin, Anshuman Khandual, Qian Cai, Thomas Gleixner,
Oscar Salvador, Juergen Gross, Greg Kroah-Hartman,
Rafael J. Wysocki, linux-kernel, Arun KS, Andrew Morton,
linuxppc-dev
In-Reply-To: <20190620160507.GA34841@archlinux-epyc>
On 20.06.19 18:05, Nathan Chancellor wrote:
> On Thu, Jun 20, 2019 at 12:35:18PM +0200, David Hildenbrand wrote:
>> walk_memory_range() was once used to iterate over sections. Now, it
>> iterates over memory blocks. Rename the function, fixup the
>> documentation. Also, pass start+size instead of PFNs, which is what most
>> callers already have at hand. (we'll rework link_mem_sections() most
>> probably soon)
>>
>> Follow-up patches wil rework, simplify, and move walk_memory_blocks() to
>> drivers/base/memory.c.
>>
>> Note: walk_memory_blocks() only works correctly right now if the
>> start_pfn is aligned to a section start. This is the case right now,
>> but we'll generalize the function in a follow up patch so the semantics
>> match the documentation.
>>
>> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
>> Cc: Paul Mackerras <paulus@samba.org>
>> Cc: Michael Ellerman <mpe@ellerman.id.au>
>> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
>> Cc: Len Brown <lenb@kernel.org>
>> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
>> Cc: David Hildenbrand <david@redhat.com>
>> Cc: Rashmica Gupta <rashmica.g@gmail.com>
>> Cc: Andrew Morton <akpm@linux-foundation.org>
>> Cc: Pavel Tatashin <pavel.tatashin@microsoft.com>
>> Cc: Anshuman Khandual <anshuman.khandual@arm.com>
>> Cc: Michael Neuling <mikey@neuling.org>
>> Cc: Thomas Gleixner <tglx@linutronix.de>
>> Cc: Oscar Salvador <osalvador@suse.de>
>> Cc: Michal Hocko <mhocko@suse.com>
>> Cc: Wei Yang <richard.weiyang@gmail.com>
>> Cc: Juergen Gross <jgross@suse.com>
>> Cc: Qian Cai <cai@lca.pw>
>> Cc: Arun KS <arunks@codeaurora.org>
>> Signed-off-by: David Hildenbrand <david@redhat.com>
>> ---
>> arch/powerpc/platforms/powernv/memtrace.c | 22 ++++++++++-----------
>> drivers/acpi/acpi_memhotplug.c | 19 ++++--------------
>> drivers/base/node.c | 5 +++--
>> include/linux/memory_hotplug.h | 2 +-
>> mm/memory_hotplug.c | 24 ++++++++++++-----------
>> 5 files changed, 32 insertions(+), 40 deletions(-)
>>
>> diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
>> index 5e53c1392d3b..8c82c041afe6 100644
>> --- a/arch/powerpc/platforms/powernv/memtrace.c
>> +++ b/arch/powerpc/platforms/powernv/memtrace.c
>> @@ -70,23 +70,24 @@ static int change_memblock_state(struct memory_block *mem, void *arg)
>> /* called with device_hotplug_lock held */
>> static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages)
>> {
>> + const unsigned long start = PFN_PHYS(start_pfn);
>> + const unsigned long size = PFN_PHYS(nr_pages);
>> u64 end_pfn = start_pfn + nr_pages - 1;
>
> This variable should be removed:
>
> arch/powerpc/platforms/powernv/memtrace.c:75:6: warning: unused variable 'end_pfn' [-Wunused-variable]
> u64 end_pfn = start_pfn + nr_pages - 1;
> ^
> 1 warning generated.
>
> https://travis-ci.com/ClangBuiltLinux/continuous-integration/jobs/209576737
>
> Cheers,
> Nathan
>
Indeed, thanks!
--
Thanks,
David / dhildenb
^ permalink raw reply
* Re: [PATCH v2 4/6] mm/memory_hotplug: Rename walk_memory_range() and pass start+size instead of pfns
From: Nathan Chancellor @ 2019-06-20 16:05 UTC (permalink / raw)
To: David Hildenbrand
Cc: Michal Hocko, Wei Yang, linux-mm, Paul Mackerras, Rashmica Gupta,
Dan Williams, Michael Neuling, linux-acpi, Len Brown,
Pavel Tatashin, Anshuman Khandual, Qian Cai, Thomas Gleixner,
Oscar Salvador, Juergen Gross, Greg Kroah-Hartman,
Rafael J. Wysocki, linux-kernel, Arun KS, Andrew Morton,
linuxppc-dev
In-Reply-To: <20190620103520.23481-5-david@redhat.com>
On Thu, Jun 20, 2019 at 12:35:18PM +0200, David Hildenbrand wrote:
> walk_memory_range() was once used to iterate over sections. Now, it
> iterates over memory blocks. Rename the function, fixup the
> documentation. Also, pass start+size instead of PFNs, which is what most
> callers already have at hand. (we'll rework link_mem_sections() most
> probably soon)
>
> Follow-up patches wil rework, simplify, and move walk_memory_blocks() to
> drivers/base/memory.c.
>
> Note: walk_memory_blocks() only works correctly right now if the
> start_pfn is aligned to a section start. This is the case right now,
> but we'll generalize the function in a follow up patch so the semantics
> match the documentation.
>
> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> Cc: Paul Mackerras <paulus@samba.org>
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
> Cc: Len Brown <lenb@kernel.org>
> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: Rashmica Gupta <rashmica.g@gmail.com>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Pavel Tatashin <pavel.tatashin@microsoft.com>
> Cc: Anshuman Khandual <anshuman.khandual@arm.com>
> Cc: Michael Neuling <mikey@neuling.org>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: Oscar Salvador <osalvador@suse.de>
> Cc: Michal Hocko <mhocko@suse.com>
> Cc: Wei Yang <richard.weiyang@gmail.com>
> Cc: Juergen Gross <jgross@suse.com>
> Cc: Qian Cai <cai@lca.pw>
> Cc: Arun KS <arunks@codeaurora.org>
> Signed-off-by: David Hildenbrand <david@redhat.com>
> ---
> arch/powerpc/platforms/powernv/memtrace.c | 22 ++++++++++-----------
> drivers/acpi/acpi_memhotplug.c | 19 ++++--------------
> drivers/base/node.c | 5 +++--
> include/linux/memory_hotplug.h | 2 +-
> mm/memory_hotplug.c | 24 ++++++++++++-----------
> 5 files changed, 32 insertions(+), 40 deletions(-)
>
> diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
> index 5e53c1392d3b..8c82c041afe6 100644
> --- a/arch/powerpc/platforms/powernv/memtrace.c
> +++ b/arch/powerpc/platforms/powernv/memtrace.c
> @@ -70,23 +70,24 @@ static int change_memblock_state(struct memory_block *mem, void *arg)
> /* called with device_hotplug_lock held */
> static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages)
> {
> + const unsigned long start = PFN_PHYS(start_pfn);
> + const unsigned long size = PFN_PHYS(nr_pages);
> u64 end_pfn = start_pfn + nr_pages - 1;
This variable should be removed:
arch/powerpc/platforms/powernv/memtrace.c:75:6: warning: unused variable 'end_pfn' [-Wunused-variable]
u64 end_pfn = start_pfn + nr_pages - 1;
^
1 warning generated.
https://travis-ci.com/ClangBuiltLinux/continuous-integration/jobs/209576737
Cheers,
Nathan
>
> - if (walk_memory_range(start_pfn, end_pfn, NULL,
> - check_memblock_online))
> + if (walk_memory_blocks(start, size, NULL, check_memblock_online))
> return false;
>
> - walk_memory_range(start_pfn, end_pfn, (void *)MEM_GOING_OFFLINE,
> - change_memblock_state);
> + walk_memory_blocks(start, size, (void *)MEM_GOING_OFFLINE,
> + change_memblock_state);
>
> if (offline_pages(start_pfn, nr_pages)) {
> - walk_memory_range(start_pfn, end_pfn, (void *)MEM_ONLINE,
> - change_memblock_state);
> + walk_memory_blocks(start, size, (void *)MEM_ONLINE,
> + change_memblock_state);
> return false;
> }
>
> - walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE,
> - change_memblock_state);
> + walk_memory_blocks(start, size, (void *)MEM_OFFLINE,
> + change_memblock_state);
>
>
> return true;
> @@ -242,9 +243,8 @@ static int memtrace_online(void)
> */
> if (!memhp_auto_online) {
> lock_device_hotplug();
> - walk_memory_range(PFN_DOWN(ent->start),
> - PFN_UP(ent->start + ent->size - 1),
> - NULL, online_mem_block);
> + walk_memory_blocks(ent->start, ent->size, NULL,
> + online_mem_block);
> unlock_device_hotplug();
> }
>
> diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
> index db013dc21c02..e294f44a7850 100644
> --- a/drivers/acpi/acpi_memhotplug.c
> +++ b/drivers/acpi/acpi_memhotplug.c
> @@ -155,16 +155,6 @@ static int acpi_memory_check_device(struct acpi_memory_device *mem_device)
> return 0;
> }
>
> -static unsigned long acpi_meminfo_start_pfn(struct acpi_memory_info *info)
> -{
> - return PFN_DOWN(info->start_addr);
> -}
> -
> -static unsigned long acpi_meminfo_end_pfn(struct acpi_memory_info *info)
> -{
> - return PFN_UP(info->start_addr + info->length-1);
> -}
> -
> static int acpi_bind_memblk(struct memory_block *mem, void *arg)
> {
> return acpi_bind_one(&mem->dev, arg);
> @@ -173,9 +163,8 @@ static int acpi_bind_memblk(struct memory_block *mem, void *arg)
> static int acpi_bind_memory_blocks(struct acpi_memory_info *info,
> struct acpi_device *adev)
> {
> - return walk_memory_range(acpi_meminfo_start_pfn(info),
> - acpi_meminfo_end_pfn(info), adev,
> - acpi_bind_memblk);
> + return walk_memory_blocks(info->start_addr, info->length, adev,
> + acpi_bind_memblk);
> }
>
> static int acpi_unbind_memblk(struct memory_block *mem, void *arg)
> @@ -186,8 +175,8 @@ static int acpi_unbind_memblk(struct memory_block *mem, void *arg)
>
> static void acpi_unbind_memory_blocks(struct acpi_memory_info *info)
> {
> - walk_memory_range(acpi_meminfo_start_pfn(info),
> - acpi_meminfo_end_pfn(info), NULL, acpi_unbind_memblk);
> + walk_memory_blocks(info->start_addr, info->length, NULL,
> + acpi_unbind_memblk);
> }
>
> static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
> diff --git a/drivers/base/node.c b/drivers/base/node.c
> index e6364e3e3e31..d8c02e65df68 100644
> --- a/drivers/base/node.c
> +++ b/drivers/base/node.c
> @@ -833,8 +833,9 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
>
> int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn)
> {
> - return walk_memory_range(start_pfn, end_pfn, (void *)&nid,
> - register_mem_sect_under_node);
> + return walk_memory_blocks(PFN_PHYS(start_pfn),
> + PFN_PHYS(end_pfn - start_pfn), (void *)&nid,
> + register_mem_sect_under_node);
> }
>
> #ifdef CONFIG_HUGETLBFS
> diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
> index 79e0add6a597..d9fffc34949f 100644
> --- a/include/linux/memory_hotplug.h
> +++ b/include/linux/memory_hotplug.h
> @@ -340,7 +340,7 @@ static inline void __remove_memory(int nid, u64 start, u64 size) {}
> #endif /* CONFIG_MEMORY_HOTREMOVE */
>
> extern void __ref free_area_init_core_hotplug(int nid);
> -extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
> +extern int walk_memory_blocks(unsigned long start, unsigned long size,
> void *arg, int (*func)(struct memory_block *, void *));
> extern int __add_memory(int nid, u64 start, u64 size);
> extern int add_memory(int nid, u64 start, u64 size);
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index a88c5f334e5a..122a7d31efdd 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -1126,8 +1126,7 @@ int __ref add_memory_resource(int nid, struct resource *res)
>
> /* online pages if requested */
> if (memhp_auto_online)
> - walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1),
> - NULL, online_memory_block);
> + walk_memory_blocks(start, size, NULL, online_memory_block);
>
> return ret;
> error:
> @@ -1665,20 +1664,24 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
> #endif /* CONFIG_MEMORY_HOTREMOVE */
>
> /**
> - * walk_memory_range - walks through all mem sections in [start_pfn, end_pfn)
> - * @start_pfn: start pfn of the memory range
> - * @end_pfn: end pfn of the memory range
> + * walk_memory_blocks - walk through all present memory blocks overlapped
> + * by the range [start, start + size)
> + *
> + * @start: start address of the memory range
> + * @size: size of the memory range
> * @arg: argument passed to func
> - * @func: callback for each memory section walked
> + * @func: callback for each memory block walked
> *
> - * This function walks through all present mem sections in range
> - * [start_pfn, end_pfn) and call func on each mem section.
> + * This function walks through all present memory blocks overlapped by the
> + * range [start, start + size), calling func on each memory block.
> *
> * Returns the return value of func.
> */
> -int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
> +int walk_memory_blocks(unsigned long start, unsigned long size,
> void *arg, int (*func)(struct memory_block *, void *))
> {
> + const unsigned long start_pfn = PFN_DOWN(start);
> + const unsigned long end_pfn = PFN_UP(start + size - 1);
> struct memory_block *mem = NULL;
> struct mem_section *section;
> unsigned long pfn, section_nr;
> @@ -1824,8 +1827,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
> * whether all memory blocks in question are offline and return error
> * if this is not the case.
> */
> - rc = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL,
> - check_memblock_offlined_cb);
> + rc = walk_memory_blocks(start, size, NULL, check_memblock_offlined_cb);
> if (rc)
> goto done;
>
> --
> 2.21.0
>
^ permalink raw reply
* Re: [PATCH] powerpc: enable a 30-bit ZONE_DMA for 32-bit pmac
From: Michael Ellerman @ 2019-06-20 13:49 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Christoph Hellwig, paulus
Cc: aaro.koskinen, linuxppc-dev, linux-kernel, Larry.Finger
In-Reply-To: <a5fc355e44fb5edea41274329f7c5d04a8dff6fc.camel@kernel.crashing.org>
Benjamin Herrenschmidt <benh@kernel.crashing.org> writes:
> On Wed, 2019-06-19 at 22:32 +1000, Michael Ellerman wrote:
>> Christoph Hellwig <hch@lst.de> writes:
>> > Any chance this could get picked up to fix the regression?
>>
>> Was hoping Ben would Ack it. He's still powermac maintainer :)
>>
>> I guess he OK'ed it in the other thread, will add it to my queue.
>
> Yeah ack. If I had written it myself, I would have made the DMA bits a
> variable and only set it down to 30 if I see that device in the DT
> early on, but I can't be bothered now, if it works, ship it :-)
OK, we can do that next release if someone's motivated.
> Note: The patch affects all ppc32, though I don't think it will cause
> any significant issue on those who don't need it.
Yeah. We could always hide it behind CONFIG_PPC_PMAC if it becomes a problem.
cheers
^ permalink raw reply
* Re: [PATCH 16/16] mm: pass get_user_pages_fast iterator arguments in a structure
From: Nicholas Piggin @ 2019-06-20 12:18 UTC (permalink / raw)
To: Linus Torvalds
Cc: Rich Felker, Yoshinori Sato, Linux-sh list, James Hogan,
the arch/x86 maintainers, Linux List Kernel Mailing,
David S. Miller, Linux-MM, Khalid Aziz, Paul Burton,
Andrey Konovalov, sparclinux, Paul Mackerras, linux-mips,
linuxppc-dev, Christoph Hellwig
In-Reply-To: <CAHk-=wjSo+TzkvYnAqrp=eFgzzc058DhSMTPr4-2quZTbGLfnw@mail.gmail.com>
Linus Torvalds's on June 12, 2019 11:09 am:
> On Tue, Jun 11, 2019 at 2:55 PM Nicholas Piggin <npiggin@gmail.com> wrote:
>>
>> What does this do for performance? I've found this pattern can be
>> bad for store aliasing detection.
>
> I wouldn't expect it to be noticeable, and the lack of argument
> reloading etc should make up for it. Plus inlining makes it a
> non-issue when that happens.
Maybe in isolation. Just seems like a strange pattern to sprinkle
around randomly, I wouldn't like it to proliferate.
I understand in some cases where a big set of parameters or
basically state gets sent around through a lot of interfaces.
Within one file to make lines a bit shorter or save a few bytes
isn't such a strong case.
>
> But I guess we could also at least look at using "restrict", if that
> ends up helping. Unlike the completely bogus type-based aliasing rules
> (that we disable because I think the C people were on some bad bad
> drugs when they came up with them), restricted pointers are a real
> thing that makes sense.
>
> That said, we haven't traditionally used it, and I don't know how much
> it helps gcc. Maybe gcc ignores it entirely? S
Ahh, it's not compiler store alias analysis I'm talking about, but
processor (but you raise an interesting point about compiler too,
would be nice if we could improve that in general).
The processor aliasing problem happens because the struct will
be initialised with stores using one base register (e.g., stack
register), and then same memory is loaded using a different
register (e.g., parameter register). Processor's static heuristics
for determining a load doesn't alias with an earlier store doesn't
do so well in that case.
Just about everywhere I've seen those kind of misspeculation and
flushes in the kernel has been this pattern, so I'm wary of it in
performance critical code.
Thanks,
Nick
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox