* [PATCH v3 15/16] cxl: Add driver to Kbuild and Makefiles
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
drivers/misc/cxl/Kconfig | 10 ++++++++++
drivers/misc/cxl/Makefile | 2 ++
2 files changed, 12 insertions(+)
diff --git a/drivers/misc/cxl/Kconfig b/drivers/misc/cxl/Kconfig
index 5cdd319..585d6e3 100644
--- a/drivers/misc/cxl/Kconfig
+++ b/drivers/misc/cxl/Kconfig
@@ -6,3 +6,13 @@ config CXL_BASE
bool
default n
select PPC_COPRO_BASE
+
+config CXL
+ tristate "Support for IBM Coherent Accelerators (CXL)"
+ depends on PPC_POWERNV && PCI_MSI
+ select CXL_BASE
+ default m
+ help
+ Select this option to enable userspace driver support for IBM
+ Coherent Accelerators (CXL). CXL is otherwise known as Coherent
+ Accelerator Processor Interface (CAPI).
diff --git a/drivers/misc/cxl/Makefile b/drivers/misc/cxl/Makefile
index e30ad0a..165e98f 100644
--- a/drivers/misc/cxl/Makefile
+++ b/drivers/misc/cxl/Makefile
@@ -1 +1,3 @@
+cxl-y += main.o file.o irq.o fault.o native.o context.o sysfs.o debugfs.o pci.o
+obj-$(CONFIG_CXL) += cxl.o
obj-$(CONFIG_CXL_BASE) += base.o
--
1.9.1
^ permalink raw reply related
* [PATCH v3 14/16] cxl: Userspace header file.
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
This defines structs and magic numbers required for userspace to interact with
the kernel cxl driver via /dev/cxl/afu0.0.
It adds this header file Kbuild so it's exported when doing make
headers_installs.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
include/uapi/Kbuild | 1 +
include/uapi/misc/Kbuild | 2 ++
include/uapi/misc/cxl.h | 86 ++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 89 insertions(+)
create mode 100644 include/uapi/misc/Kbuild
create mode 100644 include/uapi/misc/cxl.h
diff --git a/include/uapi/Kbuild b/include/uapi/Kbuild
index 81d2106..245aa6e 100644
--- a/include/uapi/Kbuild
+++ b/include/uapi/Kbuild
@@ -12,3 +12,4 @@ header-y += video/
header-y += drm/
header-y += xen/
header-y += scsi/
+header-y += misc/
diff --git a/include/uapi/misc/Kbuild b/include/uapi/misc/Kbuild
new file mode 100644
index 0000000..e96cae7
--- /dev/null
+++ b/include/uapi/misc/Kbuild
@@ -0,0 +1,2 @@
+# misc Header export list
+header-y += cxl.h
diff --git a/include/uapi/misc/cxl.h b/include/uapi/misc/cxl.h
new file mode 100644
index 0000000..0aaecf3
--- /dev/null
+++ b/include/uapi/misc/cxl.h
@@ -0,0 +1,86 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _UAPI_ASM_CXL_H
+#define _UAPI_ASM_CXL_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/* Structs for IOCTLS for userspace to talk to the kernel */
+struct cxl_ioctl_start_work {
+ __u64 flags;
+ __u64 wed;
+ __u64 amr;
+ __s16 num_interrupts;
+ __s16 reserved1;
+ __s32 reserved2;
+ __u64 reserved3;
+ __u64 reserved4;
+ __u64 reserved5;
+ __u64 reserved6;
+};
+#define CXL_START_WORK_AMR 0x0000000000000001ULL
+#define CXL_START_WORK_NUM_IRQS 0x0000000000000002ULL
+#define CXL_START_WORK_ALL (CXL_START_WORK_AMR |\
+ CXL_START_WORK_NUM_IRQS)
+
+/* IOCTL numbers */
+#define CXL_MAGIC 0xCA
+#define CXL_IOCTL_START_WORK _IOW(CXL_MAGIC, 0x00, struct cxl_ioctl_start_work)
+#define CXL_IOCTL_GET_PROCESS_ELEMENT _IOR(CXL_MAGIC, 0x01, int)
+
+/* Events from read() */
+#define CXL_READ_MIN_SIZE 0x1000 /* 4K */
+enum cxl_event_type {
+ CXL_EVENT_RESERVED = 0,
+ CXL_EVENT_AFU_INTERRUPT = 1,
+ CXL_EVENT_DATA_STORAGE = 2,
+ CXL_EVENT_AFU_ERROR = 3,
+};
+
+struct cxl_event_header {
+ __u16 type;
+ __u16 size;
+ __u16 process_element;
+ __u16 reserved1;
+};
+
+struct cxl_event_afu_interrupt {
+ __u16 flags;
+ __u16 irq; /* Raised AFU interrupt number */
+ __u32 reserved1;
+};
+
+struct cxl_event_data_storage {
+ __u16 flags;
+ __u16 reserved1;
+ __u32 reserved2;
+ __u64 addr;
+ __u64 dsisr;
+ __u64 reserved3;
+};
+
+struct cxl_event_afu_error {
+ __u16 flags;
+ __u16 reserved1;
+ __u32 reserved2;
+ __u64 err;
+};
+
+struct cxl_event {
+ struct cxl_event_header header;
+ union {
+ struct cxl_event_afu_interrupt irq;
+ struct cxl_event_data_storage fault;
+ struct cxl_event_afu_error afu_err;
+ };
+};
+
+#endif
--
1.9.1
^ permalink raw reply related
* [PATCH v3 13/16] cxl: Driver code for powernv PCIe based cards for userspace access
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
This is the core of the cxl driver.
It adds support for using cxl cards in the powernv environment only (ie POWER8
bare metal). It allows access to cxl accelerators by userspace using the
/dev/cxl/afuM.N char devices.
The kernel driver has no knowledge of the function implemented by the
accelerator. It provides services to userspace via the /dev/cxl/afuM.N
devices. When a program opens this device and runs the start work IOCTL, the
accelerator will have coherent access to that processes memory using the same
virtual addresses. That process may mmap the device to access any MMIO space
the accelerator provides. Also, reads on the device will allow interrupts to
be received. These services are further documented in a later patch in
Documentation/powerpc/cxl.txt.
Documentation of the cxl hardware architecture and userspace API is provided in
subsequent patches.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
drivers/misc/cxl/context.c | 173 ++++++++
drivers/misc/cxl/cxl.h | 622 ++++++++++++++++++++++++++++
drivers/misc/cxl/debugfs.c | 112 +++++
drivers/misc/cxl/fault.c | 299 ++++++++++++++
drivers/misc/cxl/file.c | 493 ++++++++++++++++++++++
drivers/misc/cxl/irq.c | 398 ++++++++++++++++++
drivers/misc/cxl/main.c | 234 +++++++++++
drivers/misc/cxl/native.c | 683 +++++++++++++++++++++++++++++++
drivers/misc/cxl/pci.c | 994 +++++++++++++++++++++++++++++++++++++++++++++
drivers/misc/cxl/sysfs.c | 360 ++++++++++++++++
10 files changed, 4368 insertions(+)
create mode 100644 drivers/misc/cxl/context.c
create mode 100644 drivers/misc/cxl/cxl.h
create mode 100644 drivers/misc/cxl/debugfs.c
create mode 100644 drivers/misc/cxl/fault.c
create mode 100644 drivers/misc/cxl/file.c
create mode 100644 drivers/misc/cxl/irq.c
create mode 100644 drivers/misc/cxl/main.c
create mode 100644 drivers/misc/cxl/native.c
create mode 100644 drivers/misc/cxl/pci.c
create mode 100644 drivers/misc/cxl/sysfs.c
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
new file mode 100644
index 0000000..db56218
--- /dev/null
+++ b/drivers/misc/cxl/context.c
@@ -0,0 +1,173 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/bitmap.h>
+#include <linux/sched.h>
+#include <linux/pid.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+#include <linux/idr.h>
+#include <asm/cputable.h>
+#include <asm/current.h>
+#include <asm/copro.h>
+
+#include "cxl.h"
+
+/*
+ * Allocates space for a CXL context.
+ */
+struct cxl_context *cxl_context_alloc(void)
+{
+ return kzalloc(sizeof(struct cxl_context), GFP_KERNEL);
+}
+
+/*
+ * Initialises a CXL context.
+ */
+int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master)
+{
+ int i;
+
+ spin_lock_init(&ctx->sst_lock);
+ ctx->sstp = NULL;
+ ctx->afu = afu;
+ ctx->master = master;
+ ctx->pid = get_pid(get_task_pid(current, PIDTYPE_PID));
+
+ INIT_WORK(&ctx->fault_work, cxl_handle_fault);
+
+ init_waitqueue_head(&ctx->wq);
+ spin_lock_init(&ctx->lock);
+
+ ctx->irq_bitmap = NULL;
+ ctx->pending_irq = false;
+ ctx->pending_fault = false;
+ ctx->pending_afu_err = false;
+
+ mutex_init(&ctx->status_mutex);
+
+ /* Don't need to lock just writing this */
+ ctx->status = OPENED;
+
+ idr_preload(GFP_KERNEL);
+ spin_lock(&afu->contexts_lock);
+ i = idr_alloc(&ctx->afu->contexts_idr, ctx, 0,
+ ctx->afu->num_procs, GFP_NOWAIT);
+ spin_unlock(&afu->contexts_lock);
+ idr_preload_end();
+ if (i < 0)
+ return i;
+
+ ctx->pe = i;
+ ctx->elem = &ctx->afu->spa[i];
+ ctx->pe_inserted = false;
+ return 0;
+}
+
+/*
+ * Map a per-context mmio space into the given vma.
+ */
+int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma)
+{
+ u64 len = vma->vm_end - vma->vm_start;
+ len = min(len, ctx->psn_size);
+
+ if (ctx->afu->current_model == CXL_MODEL_DEDICATED) {
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+ return vm_iomap_memory(vma, ctx->afu->psn_phys, ctx->afu->adapter->ps_size);
+ }
+
+ /* make sure there is a valid per process space for this AFU */
+ if ((ctx->master && !ctx->afu->psa) || (!ctx->afu->pp_psa)) {
+ pr_devel("AFU doesn't support mmio space\n");
+ return -EINVAL;
+ }
+
+ /* Can't mmap until the AFU is enabled */
+ if (!ctx->afu->enabled)
+ return -EBUSY;
+
+ pr_devel("%s: mmio physical: %llx pe: %i master:%i\n", __func__,
+ ctx->psn_phys, ctx->pe , ctx->master);
+
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+ return vm_iomap_memory(vma, ctx->psn_phys, len);
+}
+
+/*
+ * Detach a context from the hardware. This disables interrupts and doesn't
+ * return until all outstanding interrupts for this context have completed. The
+ * hardware should no longer access *ctx after this has returned.
+ */
+static void __detach_context(struct cxl_context *ctx)
+{
+ unsigned long flags;
+ enum cxl_context_status status;
+
+ mutex_lock(&ctx->status_mutex);
+ status = ctx->status;
+ ctx->status = CLOSED;
+ mutex_unlock(&ctx->status_mutex);
+ if (status != STARTED)
+ return;
+
+ WARN_ON(cxl_detach_process(ctx));
+ afu_release_irqs(ctx);
+ flush_work(&ctx->fault_work); /* Only needed for dedicated process */
+ wake_up_all(&ctx->wq);
+}
+
+/*
+ * Detach the given context from the AFU. This doesn't actually
+ * free the context but it should stop the context running in hardware
+ * (ie. prevent this context from generating any further interrupts
+ * so that it can be freed).
+ */
+void cxl_context_detach(struct cxl_context *ctx)
+{
+ __detach_context(ctx);
+}
+
+/*
+ * Detach all contexts on the given AFU.
+ */
+void cxl_context_detach_all(struct cxl_afu *afu)
+{
+ struct cxl_context *ctx;
+ int tmp;
+
+ rcu_read_lock();
+ idr_for_each_entry(&afu->contexts_idr, ctx, tmp)
+ __detach_context(ctx);
+ rcu_read_unlock();
+}
+
+void cxl_context_free(struct cxl_context *ctx)
+{
+ unsigned long flags;
+
+ spin_lock(&ctx->afu->contexts_lock);
+ idr_remove(&ctx->afu->contexts_idr, ctx->pe);
+ spin_unlock(&ctx->afu->contexts_lock);
+ synchronize_rcu();
+
+ spin_lock_irqsave(&ctx->sst_lock, flags);
+ free_page((u64)ctx->sstp);
+ ctx->sstp = NULL;
+ spin_unlock_irqrestore(&ctx->sst_lock, flags);
+
+ put_pid(ctx->pid);
+ kfree(ctx);
+}
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
new file mode 100644
index 0000000..4f7acad
--- /dev/null
+++ b/drivers/misc/cxl/cxl.h
@@ -0,0 +1,622 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _CXL_H_
+#define _CXL_H_
+
+#include <linux/interrupt.h>
+#include <linux/semaphore.h>
+#include <linux/device.h>
+#include <linux/types.h>
+#include <linux/cdev.h>
+#include <linux/pid.h>
+#include <linux/io.h>
+#include <linux/pci.h>
+#include <asm/cputable.h>
+#include <asm/mmu.h>
+#include <asm/reg.h>
+#include <misc/cxl.h>
+
+#include <uapi/misc/cxl.h>
+
+extern uint cxl_verbose;
+
+#define CXL_TIMEOUT 5
+
+/* Bump version each time a user API change is made, whether it is
+ * backwards compatible ot not.
+ */
+#define CXL_API_VERSION 1
+#define CXL_API_VERSION_COMPATIBLE 1
+
+/* Opaque types to avoid accidentally passing registers for the wrong MMIO
+ *
+ * At the end of the day, I'm not married to using typedef here, but it might
+ * (and has!) help avoid bugs like mixing up CXL_PSL_CtxTime and
+ * CXL_PSL_CtxTime_An, or calling cxl_p1n_write instead of cxl_p1_write.
+ *
+ * I'm quite happy if these are changed back to #defines before upstreaming, it
+ * should be little more than a regexp search+replace operation in this file.
+ */
+typedef struct {
+ const int x;
+} cxl_p1_reg_t;
+typedef struct {
+ const int x;
+} cxl_p1n_reg_t;
+typedef struct {
+ const int x;
+} cxl_p2n_reg_t;
+#define cxl_reg_off(reg) \
+ (reg.x)
+
+/* Memory maps. Ref CXL Appendix A */
+
+/* PSL Privilege 1 Memory Map */
+/* Configuration and Control area */
+static const cxl_p1_reg_t CXL_PSL_CtxTime = {0x0000};
+static const cxl_p1_reg_t CXL_PSL_ErrIVTE = {0x0008};
+static const cxl_p1_reg_t CXL_PSL_KEY1 = {0x0010};
+static const cxl_p1_reg_t CXL_PSL_KEY2 = {0x0018};
+static const cxl_p1_reg_t CXL_PSL_Control = {0x0020};
+/* Downloading */
+static const cxl_p1_reg_t CXL_PSL_DLCNTL = {0x0060};
+static const cxl_p1_reg_t CXL_PSL_DLADDR = {0x0068};
+
+/* PSL Lookaside Buffer Management Area */
+static const cxl_p1_reg_t CXL_PSL_LBISEL = {0x0080};
+static const cxl_p1_reg_t CXL_PSL_SLBIE = {0x0088};
+static const cxl_p1_reg_t CXL_PSL_SLBIA = {0x0090};
+static const cxl_p1_reg_t CXL_PSL_TLBIE = {0x00A0};
+static const cxl_p1_reg_t CXL_PSL_TLBIA = {0x00A8};
+static const cxl_p1_reg_t CXL_PSL_AFUSEL = {0x00B0};
+
+/* 0x00C0:7EFF Implementation dependent area */
+static const cxl_p1_reg_t CXL_PSL_FIR1 = {0x0100};
+static const cxl_p1_reg_t CXL_PSL_FIR2 = {0x0108};
+static const cxl_p1_reg_t CXL_PSL_VERSION = {0x0118};
+static const cxl_p1_reg_t CXL_PSL_RESLCKTO = {0x0128};
+static const cxl_p1_reg_t CXL_PSL_FIR_CNTL = {0x0148};
+static const cxl_p1_reg_t CXL_PSL_DSNDCTL = {0x0150};
+static const cxl_p1_reg_t CXL_PSL_SNWRALLOC = {0x0158};
+static const cxl_p1_reg_t CXL_PSL_TRACE = {0x0170};
+/* 0x7F00:7FFF Reserved PCIe MSI-X Pending Bit Array area */
+/* 0x8000:FFFF Reserved PCIe MSI-X Table Area */
+
+/* PSL Slice Privilege 1 Memory Map */
+/* Configuration Area */
+static const cxl_p1n_reg_t CXL_PSL_SR_An = {0x00};
+static const cxl_p1n_reg_t CXL_PSL_LPID_An = {0x08};
+static const cxl_p1n_reg_t CXL_PSL_AMBAR_An = {0x10};
+static const cxl_p1n_reg_t CXL_PSL_SPOffset_An = {0x18};
+static const cxl_p1n_reg_t CXL_PSL_ID_An = {0x20};
+static const cxl_p1n_reg_t CXL_PSL_SERR_An = {0x28};
+/* Memory Management and Lookaside Buffer Management */
+static const cxl_p1n_reg_t CXL_PSL_SDR_An = {0x30};
+static const cxl_p1n_reg_t CXL_PSL_AMOR_An = {0x38};
+/* Pointer Area */
+static const cxl_p1n_reg_t CXL_HAURP_An = {0x80};
+static const cxl_p1n_reg_t CXL_PSL_SPAP_An = {0x88};
+static const cxl_p1n_reg_t CXL_PSL_LLCMD_An = {0x90};
+/* Control Area */
+static const cxl_p1n_reg_t CXL_PSL_SCNTL_An = {0xA0};
+static const cxl_p1n_reg_t CXL_PSL_CtxTime_An = {0xA8};
+static const cxl_p1n_reg_t CXL_PSL_IVTE_Offset_An = {0xB0};
+static const cxl_p1n_reg_t CXL_PSL_IVTE_Limit_An = {0xB8};
+/* 0xC0:FF Implementation Dependent Area */
+static const cxl_p1n_reg_t CXL_PSL_FIR_SLICE_An = {0xC0};
+static const cxl_p1n_reg_t CXL_AFU_DEBUG_An = {0xC8};
+static const cxl_p1n_reg_t CXL_PSL_APCALLOC_A = {0xD0};
+static const cxl_p1n_reg_t CXL_PSL_COALLOC_A = {0xD8};
+static const cxl_p1n_reg_t CXL_PSL_RXCTL_A = {0xE0};
+static const cxl_p1n_reg_t CXL_PSL_SLICE_TRACE = {0xE8};
+
+/* PSL Slice Privilege 2 Memory Map */
+/* Configuration and Control Area */
+static const cxl_p2n_reg_t CXL_PSL_PID_TID_An = {0x000};
+static const cxl_p2n_reg_t CXL_CSRP_An = {0x008};
+static const cxl_p2n_reg_t CXL_AURP0_An = {0x010};
+static const cxl_p2n_reg_t CXL_AURP1_An = {0x018};
+static const cxl_p2n_reg_t CXL_SSTP0_An = {0x020};
+static const cxl_p2n_reg_t CXL_SSTP1_An = {0x028};
+static const cxl_p2n_reg_t CXL_PSL_AMR_An = {0x030};
+/* Segment Lookaside Buffer Management */
+static const cxl_p2n_reg_t CXL_SLBIE_An = {0x040};
+static const cxl_p2n_reg_t CXL_SLBIA_An = {0x048};
+static const cxl_p2n_reg_t CXL_SLBI_Select_An = {0x050};
+/* Interrupt Registers */
+static const cxl_p2n_reg_t CXL_PSL_DSISR_An = {0x060};
+static const cxl_p2n_reg_t CXL_PSL_DAR_An = {0x068};
+static const cxl_p2n_reg_t CXL_PSL_DSR_An = {0x070};
+static const cxl_p2n_reg_t CXL_PSL_TFC_An = {0x078};
+static const cxl_p2n_reg_t CXL_PSL_PEHandle_An = {0x080};
+static const cxl_p2n_reg_t CXL_PSL_ErrStat_An = {0x088};
+/* AFU Registers */
+static const cxl_p2n_reg_t CXL_AFU_Cntl_An = {0x090};
+static const cxl_p2n_reg_t CXL_AFU_ERR_An = {0x098};
+/* Work Element Descriptor */
+static const cxl_p2n_reg_t CXL_PSL_WED_An = {0x0A0};
+/* 0x0C0:FFF Implementation Dependent Area */
+
+#define CXL_PSL_SPAP_Addr 0x0ffffffffffff000ULL
+#define CXL_PSL_SPAP_Size 0x0000000000000ff0ULL
+#define CXL_PSL_SPAP_Size_Shift 4
+#define CXL_PSL_SPAP_V 0x0000000000000001ULL
+
+/****** CXL_PSL_DLCNTL *****************************************************/
+#define CXL_PSL_DLCNTL_D (0x1ull << (63-28))
+#define CXL_PSL_DLCNTL_C (0x1ull << (63-29))
+#define CXL_PSL_DLCNTL_E (0x1ull << (63-30))
+#define CXL_PSL_DLCNTL_S (0x1ull << (63-31))
+#define CXL_PSL_DLCNTL_CE (CXL_PSL_DLCNTL_C | CXL_PSL_DLCNTL_E)
+#define CXL_PSL_DLCNTL_DCES (CXL_PSL_DLCNTL_D | CXL_PSL_DLCNTL_CE | CXL_PSL_DLCNTL_S)
+
+/****** CXL_PSL_SR_An ******************************************************/
+#define CXL_PSL_SR_An_SF MSR_SF /* 64bit */
+#define CXL_PSL_SR_An_TA (1ull << (63-1)) /* Tags active, GA1: 0 */
+#define CXL_PSL_SR_An_HV MSR_HV /* Hypervisor, GA1: 0 */
+#define CXL_PSL_SR_An_PR MSR_PR /* Problem state, GA1: 1 */
+#define CXL_PSL_SR_An_ISL (1ull << (63-53)) /* Ignore Segment Large Page */
+#define CXL_PSL_SR_An_TC (1ull << (63-54)) /* Page Table secondary hash */
+#define CXL_PSL_SR_An_US (1ull << (63-56)) /* User state, GA1: X */
+#define CXL_PSL_SR_An_SC (1ull << (63-58)) /* Segment Table secondary hash */
+#define CXL_PSL_SR_An_R MSR_DR /* Relocate, GA1: 1 */
+#define CXL_PSL_SR_An_MP (1ull << (63-62)) /* Master Process */
+#define CXL_PSL_SR_An_LE (1ull << (63-63)) /* Little Endian */
+
+/****** CXL_PSL_LLCMD_An ****************************************************/
+#define CXL_LLCMD_TERMINATE 0x0001000000000000ULL
+#define CXL_LLCMD_REMOVE 0x0002000000000000ULL
+#define CXL_LLCMD_SUSPEND 0x0003000000000000ULL
+#define CXL_LLCMD_RESUME 0x0004000000000000ULL
+#define CXL_LLCMD_ADD 0x0005000000000000ULL
+#define CXL_LLCMD_UPDATE 0x0006000000000000ULL
+#define CXL_LLCMD_HANDLE_MASK 0x000000000000ffffULL
+
+/****** CXL_PSL_ID_An ****************************************************/
+#define CXL_PSL_ID_An_F (1ull << (63-31))
+#define CXL_PSL_ID_An_L (1ull << (63-30))
+
+/****** CXL_PSL_SCNTL_An ****************************************************/
+#define CXL_PSL_SCNTL_An_CR (0x1ull << (63-15))
+/* Programming Models: */
+#define CXL_PSL_SCNTL_An_PM_MASK (0xffffull << (63-31))
+#define CXL_PSL_SCNTL_An_PM_Shared (0x0000ull << (63-31))
+#define CXL_PSL_SCNTL_An_PM_OS (0x0001ull << (63-31))
+#define CXL_PSL_SCNTL_An_PM_Process (0x0002ull << (63-31))
+#define CXL_PSL_SCNTL_An_PM_AFU (0x0004ull << (63-31))
+#define CXL_PSL_SCNTL_An_PM_AFU_PBT (0x0104ull << (63-31))
+/* Purge Status (ro) */
+#define CXL_PSL_SCNTL_An_Ps_MASK (0x3ull << (63-39))
+#define CXL_PSL_SCNTL_An_Ps_Pending (0x1ull << (63-39))
+#define CXL_PSL_SCNTL_An_Ps_Complete (0x3ull << (63-39))
+/* Purge */
+#define CXL_PSL_SCNTL_An_Pc (0x1ull << (63-48))
+/* Suspend Status (ro) */
+#define CXL_PSL_SCNTL_An_Ss_MASK (0x3ull << (63-55))
+#define CXL_PSL_SCNTL_An_Ss_Pending (0x1ull << (63-55))
+#define CXL_PSL_SCNTL_An_Ss_Complete (0x3ull << (63-55))
+/* Suspend Control */
+#define CXL_PSL_SCNTL_An_Sc (0x1ull << (63-63))
+
+/* AFU Slice Enable Status (ro) */
+#define CXL_AFU_Cntl_An_ES_MASK (0x7ull << (63-2))
+#define CXL_AFU_Cntl_An_ES_Disabled (0x0ull << (63-2))
+#define CXL_AFU_Cntl_An_ES_Enabled (0x4ull << (63-2))
+/* AFU Slice Enable */
+#define CXL_AFU_Cntl_An_E (0x1ull << (63-3))
+/* AFU Slice Reset status (ro) */
+#define CXL_AFU_Cntl_An_RS_MASK (0x3ull << (63-5))
+#define CXL_AFU_Cntl_An_RS_Pending (0x1ull << (63-5))
+#define CXL_AFU_Cntl_An_RS_Complete (0x2ull << (63-5))
+/* AFU Slice Reset */
+#define CXL_AFU_Cntl_An_RA (0x1ull << (63-7))
+
+/****** CXL_SSTP0/1_An ******************************************************/
+/* These top bits are for the segment that CONTAINS the segment table */
+#define CXL_SSTP0_An_B_SHIFT SLB_VSID_SSIZE_SHIFT
+#define CXL_SSTP0_An_KS (1ull << (63-2))
+#define CXL_SSTP0_An_KP (1ull << (63-3))
+#define CXL_SSTP0_An_N (1ull << (63-4))
+#define CXL_SSTP0_An_L (1ull << (63-5))
+#define CXL_SSTP0_An_C (1ull << (63-6))
+#define CXL_SSTP0_An_TA (1ull << (63-7))
+#define CXL_SSTP0_An_LP_SHIFT (63-9) /* 2 Bits */
+/* And finally, the virtual address & size of the segment table: */
+#define CXL_SSTP0_An_SegTableSize_SHIFT (63-31) /* 12 Bits */
+#define CXL_SSTP0_An_SegTableSize_MASK \
+ (((1ull << 12) - 1) << CXL_SSTP0_An_SegTableSize_SHIFT)
+#define CXL_SSTP0_An_STVA_U_MASK ((1ull << (63-49))-1)
+#define CXL_SSTP1_An_STVA_L_MASK (~((1ull << (63-55))-1))
+#define CXL_SSTP1_An_V (1ull << (63-63))
+
+/****** CXL_PSL_SLBIE_[An] **************************************************/
+/* write: */
+#define CXL_SLBIE_C PPC_BIT(36) /* Class */
+#define CXL_SLBIE_SS PPC_BITMASK(37, 38) /* Segment Size */
+#define CXL_SLBIE_SS_SHIFT PPC_BITLSHIFT(38)
+#define CXL_SLBIE_TA PPC_BIT(38) /* Tags Active */
+/* read: */
+#define CXL_SLBIE_MAX PPC_BITMASK(24, 31)
+#define CXL_SLBIE_PENDING PPC_BITMASK(56, 63)
+
+/****** Common to all CXL_TLBIA/SLBIA_[An] **********************************/
+#define CXL_TLB_SLB_P (1ull) /* Pending (read) */
+
+/****** Common to all CXL_TLB/SLB_IA/IE_[An] registers **********************/
+#define CXL_TLB_SLB_IQ_ALL (0ull) /* Inv qualifier */
+#define CXL_TLB_SLB_IQ_LPID (1ull) /* Inv qualifier */
+#define CXL_TLB_SLB_IQ_LPIDPID (3ull) /* Inv qualifier */
+
+/****** CXL_PSL_AFUSEL ******************************************************/
+#define CXL_PSL_AFUSEL_A (1ull << (63-55)) /* Adapter wide invalidates affect all AFUs */
+
+/****** CXL_PSL_DSISR_An ****************************************************/
+#define CXL_PSL_DSISR_An_DS (1ull << (63-0)) /* Segment not found */
+#define CXL_PSL_DSISR_An_DM (1ull << (63-1)) /* PTE not found (See also: M) or protection fault */
+#define CXL_PSL_DSISR_An_ST (1ull << (63-2)) /* Segment Table PTE not found */
+#define CXL_PSL_DSISR_An_UR (1ull << (63-3)) /* AURP PTE not found */
+#define CXL_PSL_DSISR_TRANS (CXL_PSL_DSISR_An_DS | CXL_PSL_DSISR_An_DM | CXL_PSL_DSISR_An_ST | CXL_PSL_DSISR_An_UR)
+#define CXL_PSL_DSISR_An_PE (1ull << (63-4)) /* PSL Error (implementation specific) */
+#define CXL_PSL_DSISR_An_AE (1ull << (63-5)) /* AFU Error */
+#define CXL_PSL_DSISR_An_OC (1ull << (63-6)) /* OS Context Warning */
+/* NOTE: Bits 32:63 are undefined if DSISR[DS] = 1 */
+#define CXL_PSL_DSISR_An_M DSISR_NOHPTE /* PTE not found */
+#define CXL_PSL_DSISR_An_P DSISR_PROTFAULT /* Storage protection violation */
+#define CXL_PSL_DSISR_An_A (1ull << (63-37)) /* AFU lock access to write through or cache inhibited storage */
+#define CXL_PSL_DSISR_An_S DSISR_ISSTORE /* Access was afu_wr or afu_zero */
+#define CXL_PSL_DSISR_An_K DSISR_KEYFAULT /* Access not permitted by virtual page class key protection */
+
+/****** CXL_PSL_TFC_An ******************************************************/
+#define CXL_PSL_TFC_An_A (1ull << (63-28)) /* Acknowledge non-translation fault */
+#define CXL_PSL_TFC_An_C (1ull << (63-29)) /* Continue (abort transaction) */
+#define CXL_PSL_TFC_An_AE (1ull << (63-30)) /* Restart PSL with address error */
+#define CXL_PSL_TFC_An_R (1ull << (63-31)) /* Restart PSL transaction */
+
+/* cxl_process_element->software_status */
+#define CXL_PE_SOFTWARE_STATE_V (1ul << (31 - 0)) /* Valid */
+#define CXL_PE_SOFTWARE_STATE_C (1ul << (31 - 29)) /* Complete */
+#define CXL_PE_SOFTWARE_STATE_S (1ul << (31 - 30)) /* Suspend */
+#define CXL_PE_SOFTWARE_STATE_T (1ul << (31 - 31)) /* Terminate */
+
+/* SPA->sw_command_status */
+#define CXL_SPA_SW_CMD_MASK 0xffff000000000000ULL
+#define CXL_SPA_SW_CMD_TERMINATE 0x0001000000000000ULL
+#define CXL_SPA_SW_CMD_REMOVE 0x0002000000000000ULL
+#define CXL_SPA_SW_CMD_SUSPEND 0x0003000000000000ULL
+#define CXL_SPA_SW_CMD_RESUME 0x0004000000000000ULL
+#define CXL_SPA_SW_CMD_ADD 0x0005000000000000ULL
+#define CXL_SPA_SW_CMD_UPDATE 0x0006000000000000ULL
+#define CXL_SPA_SW_STATE_MASK 0x0000ffff00000000ULL
+#define CXL_SPA_SW_STATE_TERMINATED 0x0000000100000000ULL
+#define CXL_SPA_SW_STATE_REMOVED 0x0000000200000000ULL
+#define CXL_SPA_SW_STATE_SUSPENDED 0x0000000300000000ULL
+#define CXL_SPA_SW_STATE_RESUMED 0x0000000400000000ULL
+#define CXL_SPA_SW_STATE_ADDED 0x0000000500000000ULL
+#define CXL_SPA_SW_STATE_UPDATED 0x0000000600000000ULL
+#define CXL_SPA_SW_PSL_ID_MASK 0x00000000ffff0000ULL
+#define CXL_SPA_SW_LINK_MASK 0x000000000000ffffULL
+
+#define CXL_MAX_SLICES 4
+#define MAX_AFU_MMIO_REGS 3
+
+#define CXL_MODEL_DEDICATED 0x1
+#define CXL_MODEL_DIRECTED 0x2
+#define CXL_MODEL_TIME_SLICED 0x4
+#define CXL_SUPPORTED_MODELS (CXL_MODEL_DEDICATED | CXL_MODEL_DIRECTED)
+
+enum cxl_context_status {
+ CLOSED,
+ OPENED,
+ STARTED
+};
+
+enum prefault_modes {
+ CXL_PREFAULT_NONE,
+ CXL_PREFAULT_WED,
+ CXL_PREFAULT_ALL,
+};
+
+struct cxl_sste {
+ __be64 esid_data;
+ __be64 vsid_data;
+};
+
+#define to_cxl_adapter(d) container_of(d, struct cxl, dev)
+#define to_cxl_afu(d) container_of(d, struct cxl_afu, dev)
+
+struct cxl_afu {
+ irq_hw_number_t psl_hwirq;
+ irq_hw_number_t serr_hwirq;
+ unsigned int serr_virq;
+ void __iomem *p1n_mmio;
+ void __iomem *p2n_mmio;
+ phys_addr_t psn_phys;
+ u64 pp_offset;
+ u64 pp_size;
+ void __iomem *afu_desc_mmio;
+ struct cxl *adapter;
+ struct device dev;
+ struct cdev afu_cdev_s, afu_cdev_m;
+ struct device *chardev_s, *chardev_m;
+ struct idr contexts_idr;
+ struct dentry *debugfs;
+ spinlock_t contexts_lock;
+ struct mutex spa_mutex;
+ spinlock_t afu_cntl_lock;
+
+ /* Only the first part of the SPA is used for the process element
+ * linked list. The only other part that software needs to worry about
+ * is sw_command_status, which we store a separate pointer to.
+ * Everything else in the SPA is only used by hardware
+ */
+ struct cxl_process_element *spa;
+ __be64 *sw_command_status;
+ unsigned int spa_size;
+ int spa_order;
+ int spa_max_procs;
+ unsigned int psl_virq;
+
+ int pp_irqs;
+ int irqs_max;
+ int num_procs;
+ int max_procs_virtualised;
+ int slice;
+ int models_supported;
+ int current_model;
+ enum prefault_modes prefault_mode;
+ bool psa;
+ bool pp_psa;
+ bool enabled;
+};
+
+/* This is a cxl context. If the PSL is in dedicated model, there will be one
+ * of these per AFU. If in AFU directed there can be lots of these.
+ */
+struct cxl_context {
+ struct cxl_afu *afu;
+
+ /* Problem state MMIO */
+ phys_addr_t psn_phys;
+ u64 psn_size;
+
+ spinlock_t sst_lock; /* Protects segment table */
+ struct cxl_sste *sstp;
+ unsigned int sst_size, sst_lru;
+
+ wait_queue_head_t wq;
+ struct pid *pid;
+ spinlock_t lock; /* Protects pending_irq_mask, pending_fault and fault_addr */
+ /* Only used in PR mode */
+ u64 process_token;
+
+ unsigned long *irq_bitmap; /* Accessed from IRQ context */
+ struct cxl_irq_ranges irqs;
+ u64 fault_addr;
+ u64 fault_dsisr;
+ u64 afu_err;
+
+ /* This status and it's lock pretects start and detach context
+ * from racing. It also prevents detach from racing with
+ * itself
+ */
+ enum cxl_context_status status;
+ struct mutex status_mutex;
+
+
+ /* XXX: Is it possible to need multiple work items at once? */
+ struct work_struct fault_work;
+ u64 dsisr;
+ u64 dar;
+
+ struct cxl_process_element *elem;
+
+ int pe; /* process element handle */
+ u32 irq_count;
+ bool pe_inserted;
+ bool master;
+ bool kernel;
+ bool pending_irq;
+ bool pending_fault;
+ bool pending_afu_err;
+};
+
+struct cxl {
+ void __iomem *p1_mmio;
+ void __iomem *p2_mmio;
+ irq_hw_number_t err_hwirq;
+ unsigned int err_virq;
+ spinlock_t afu_list_lock;
+ struct cxl_afu *afu[CXL_MAX_SLICES];
+ struct device dev;
+ struct dentry *trace;
+ struct dentry *psl_err_chk;
+ struct dentry *debugfs;
+ struct bin_attribute cxl_attr;
+ int adapter_num;
+ int user_irqs;
+ u64 afu_desc_off;
+ u64 afu_desc_size;
+ u64 ps_off;
+ u64 ps_size;
+ u16 psl_rev;
+ u16 base_image;
+ u8 vsec_status;
+ u8 caia_major;
+ u8 caia_minor;
+ u8 slices;
+ bool user_image_loaded;
+ bool perst_loads_image;
+ bool perst_select_user;
+};
+
+int cxl_alloc_one_irq(struct cxl *adapter);
+void cxl_release_one_irq(struct cxl *adapter, int hwirq);
+int cxl_alloc_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter, unsigned int num);
+void cxl_release_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter);
+int cxl_setup_irq(struct cxl *adapter, unsigned int hwirq, unsigned int virq);
+
+/* common == phyp + powernv */
+struct cxl_process_element_common {
+ __be32 tid;
+ __be32 pid;
+ __be64 csrp;
+ __be64 aurp0;
+ __be64 aurp1;
+ __be64 sstp0;
+ __be64 sstp1;
+ __be64 amr;
+ u8 reserved3[4];
+ __be64 wed;
+} __packed;
+
+/* just powernv */
+struct cxl_process_element {
+ __be64 sr;
+ __be64 SPOffset;
+ __be64 sdr;
+ __be64 haurp;
+ __be32 ctxtime;
+ __be16 ivte_offsets[4];
+ __be16 ivte_ranges[4];
+ __be32 lpid;
+ struct cxl_process_element_common common;
+ __be32 software_state;
+} __packed;
+
+#define _cxl_reg_write(addr, val) \
+ out_be64((u64 __iomem *)(addr), val)
+#define _cxl_reg_read(addr) \
+ in_be64((u64 __iomem *)(addr))
+
+static inline void __iomem *_cxl_p1_addr(struct cxl *cxl, cxl_p1_reg_t reg)
+{
+ WARN_ON(!cpu_has_feature(CPU_FTR_HVMODE));
+ return cxl->p1_mmio + cxl_reg_off(reg);
+}
+#define cxl_p1_write(cxl, reg, val) \
+ _cxl_reg_write(_cxl_p1_addr(cxl, reg), val)
+#define cxl_p1_read(cxl, reg) \
+ _cxl_reg_read(_cxl_p1_addr(cxl, reg))
+
+static inline void __iomem *_cxl_p1n_addr(struct cxl_afu *afu, cxl_p1n_reg_t reg)
+{
+ WARN_ON(!cpu_has_feature(CPU_FTR_HVMODE));
+ return afu->p1n_mmio + cxl_reg_off(reg);
+}
+#define cxl_p1n_write(afu, reg, val) \
+ _cxl_reg_write(_cxl_p1n_addr(afu, reg), val)
+#define cxl_p1n_read(afu, reg) \
+ _cxl_reg_read(_cxl_p1n_addr(afu, reg))
+
+static inline void __iomem *_cxl_p2n_addr(struct cxl_afu *afu, cxl_p2n_reg_t reg)
+{
+ return afu->p2n_mmio + cxl_reg_off(reg);
+}
+#define cxl_p2n_write(afu, reg, val) \
+ _cxl_reg_write(_cxl_p2n_addr(afu, reg), val)
+#define cxl_p2n_read(afu, reg) \
+ _cxl_reg_read(_cxl_p2n_addr(afu, reg))
+
+struct cxl_calls {
+ void (*cxl_slbia)(struct mm_struct *mm);
+ struct module *owner;
+};
+int register_cxl_calls(struct cxl_calls *calls);
+void unregister_cxl_calls(struct cxl_calls *calls);
+
+int cxl_alloc_adapter_nr(struct cxl *adapter);
+void cxl_remove_adapter_nr(struct cxl *adapter);
+
+int cxl_file_init(void);
+void cxl_file_exit(void);
+int cxl_register_adapter(struct cxl *adapter);
+int cxl_register_afu(struct cxl_afu *afu);
+int cxl_chardev_m_afu_add(struct cxl_afu *afu);
+int cxl_chardev_s_afu_add(struct cxl_afu *afu);
+void cxl_chardev_afu_remove(struct cxl_afu *afu);
+
+void cxl_context_detach_all(struct cxl_afu *afu);
+void cxl_context_free(struct cxl_context *ctx);
+void cxl_context_detach(struct cxl_context *ctx);
+
+int cxl_sysfs_adapter_add(struct cxl *adapter);
+void cxl_sysfs_adapter_remove(struct cxl *adapter);
+int cxl_sysfs_afu_add(struct cxl_afu *afu);
+void cxl_sysfs_afu_remove(struct cxl_afu *afu);
+
+int cxl_afu_activate_model(struct cxl_afu *afu, int model);
+int _cxl_afu_deactivate_model(struct cxl_afu *afu, int model);
+int cxl_afu_deactivate_model(struct cxl_afu *afu);
+int cxl_afu_select_best_model(struct cxl_afu *afu);
+
+unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq,
+ irq_handler_t handler, void *cookie);
+void cxl_unmap_irq(unsigned int virq, void *cookie);
+int cxl_register_psl_irq(struct cxl_afu *afu);
+void cxl_release_psl_irq(struct cxl_afu *afu);
+int cxl_register_psl_err_irq(struct cxl *adapter);
+void cxl_release_psl_err_irq(struct cxl *adapter);
+int cxl_register_serr_irq(struct cxl_afu *afu);
+void cxl_release_serr_irq(struct cxl_afu *afu);
+int afu_register_irqs(struct cxl_context *ctx, u32 count);
+void afu_release_irqs(struct cxl_context *ctx);
+irqreturn_t cxl_slice_irq_err(int irq, void *data);
+
+int cxl_debugfs_init(void);
+void cxl_debugfs_exit(void);
+int cxl_debugfs_adapter_add(struct cxl *adapter);
+void cxl_debugfs_adapter_remove(struct cxl *adapter);
+int cxl_debugfs_afu_add(struct cxl_afu *afu);
+void cxl_debugfs_afu_remove(struct cxl_afu *afu);
+
+void cxl_handle_fault(struct work_struct *work);
+void cxl_prefault(struct cxl_context *ctx, u64 wed);
+
+struct cxl *get_cxl_adapter(int num);
+int cxl_alloc_sst(struct cxl_context *ctx, u64 *sstp0, u64 *sstp1);
+
+void init_cxl_native(void);
+
+struct cxl_context *cxl_context_alloc(void);
+int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master);
+void cxl_context_free(struct cxl_context *ctx);
+int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma);
+
+/* This matches the layout of the H_COLLECT_CA_INT_INFO retbuf */
+struct cxl_irq_info {
+ u64 dsisr;
+ u64 dar;
+ u64 dsr;
+ u32 pid;
+ u32 tid;
+ u64 afu_err;
+ u64 errstat;
+ u64 padding[3]; /* to match the expected retbuf size for plpar_hcall9 */
+};
+
+int cxl_attach_process(struct cxl_context *ctx, bool kernel, u64 wed,
+ u64 amr);
+int cxl_detach_process(struct cxl_context *ctx);
+
+int cxl_get_irq(struct cxl_context *ctx, struct cxl_irq_info *info);
+int cxl_ack_irq(struct cxl_context *ctx, u64 tfc, u64 psl_reset_mask);
+
+int cxl_check_error(struct cxl_afu *afu);
+int cxl_afu_slbia(struct cxl_afu *afu);
+int cxl_tlb_slb_invalidate(struct cxl *adapter);
+int cxl_afu_disable(struct cxl_afu *afu);
+int cxl_afu_reset(struct cxl_afu *afu);
+int cxl_psl_purge(struct cxl_afu *afu);
+
+void cxl_stop_trace(struct cxl *cxl);
+
+extern struct pci_driver cxl_pci_driver;
+
+#endif
diff --git a/drivers/misc/cxl/debugfs.c b/drivers/misc/cxl/debugfs.c
new file mode 100644
index 0000000..09c0ee9
--- /dev/null
+++ b/drivers/misc/cxl/debugfs.c
@@ -0,0 +1,112 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "cxl.h"
+
+struct dentry *cxl_debugfs;
+
+void cxl_stop_trace(struct cxl *adapter)
+{
+ int slice;
+
+ /* Stop the trace */
+ cxl_p1_write(adapter, CXL_PSL_TRACE, 0x8000000000000017LL);
+
+ /* Stop the slice traces */
+ spin_lock(&adapter->afu_list_lock);
+ for (slice = 0; slice < adapter->slices; slice++) {
+ if (adapter->afu[slice])
+ cxl_p1n_write(adapter->afu[slice], CXL_PSL_SLICE_TRACE, 0x8000000000000000LL);
+ }
+ spin_unlock(&adapter->afu_list_lock);
+}
+
+int cxl_debugfs_adapter_add(struct cxl *adapter)
+{
+ struct dentry *dir;
+ char buf[32];
+
+ if (!cxl_debugfs)
+ return -ENODEV;
+
+ snprintf(buf, 32, "card%i", adapter->adapter_num);
+ dir = debugfs_create_dir(buf, cxl_debugfs);
+ if (IS_ERR(dir))
+ return PTR_ERR(dir);
+ adapter->debugfs = dir;
+
+ debugfs_create_x64("fir1", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR1));
+ debugfs_create_x64("fir2", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR2));
+ debugfs_create_x64("fir_cntl", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR_CNTL));
+ debugfs_create_x64("err_ivte", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_ErrIVTE));
+
+ debugfs_create_x64("trace", S_IRUSR | S_IWUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_TRACE));
+
+ return 0;
+}
+
+void cxl_debugfs_adapter_remove(struct cxl *adapter)
+{
+ debugfs_remove_recursive(adapter->debugfs);
+}
+
+int cxl_debugfs_afu_add(struct cxl_afu *afu)
+{
+ struct dentry *dir;
+ char buf[32];
+
+ if (!afu->adapter->debugfs)
+ return -ENODEV;
+
+ snprintf(buf, 32, "psl%i.%i", afu->adapter->adapter_num, afu->slice);
+ dir = debugfs_create_dir(buf, afu->adapter->debugfs);
+ if (IS_ERR(dir))
+ return PTR_ERR(dir);
+ afu->debugfs = dir;
+
+ debugfs_create_x64("fir", S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_FIR_SLICE_An));
+ debugfs_create_x64("serr", S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_SERR_An));
+ debugfs_create_x64("afu_debug", S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_AFU_DEBUG_An));
+ debugfs_create_x64("sr", S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_SR_An));
+
+ debugfs_create_x64("dsisr", S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_PSL_DSISR_An));
+ debugfs_create_x64("dar", S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_PSL_DAR_An));
+ debugfs_create_x64("sstp0", S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_SSTP0_An));
+ debugfs_create_x64("sstp1", S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_SSTP1_An));
+ debugfs_create_x64("err_status", S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_PSL_ErrStat_An));
+
+ debugfs_create_x64("trace", S_IRUSR | S_IWUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_SLICE_TRACE));
+
+ return 0;
+}
+
+void cxl_debugfs_afu_remove(struct cxl_afu *afu)
+{
+ debugfs_remove_recursive(afu->debugfs);
+}
+
+int __init cxl_debugfs_init(void)
+{
+ struct dentry *ent;
+ ent = debugfs_create_dir("cxl", NULL);
+ if (IS_ERR(ent))
+ return PTR_ERR(ent);
+ cxl_debugfs = ent;
+
+ return 0;
+}
+
+void cxl_debugfs_exit(void)
+{
+ debugfs_remove_recursive(cxl_debugfs);
+}
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
new file mode 100644
index 0000000..5987b59
--- /dev/null
+++ b/drivers/misc/cxl/fault.c
@@ -0,0 +1,299 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/pid.h>
+#include <linux/mm.h>
+#include <linux/moduleparam.h>
+
+#undef MODULE_PARAM_PREFIX
+#define MODULE_PARAM_PREFIX "cxl" "."
+#include <asm/current.h>
+#include <asm/copro.h>
+#include <asm/mmu.h>
+
+#include "cxl.h"
+
+bool cxl_fault_debug = false;
+
+static struct cxl_sste* find_free_sste(struct cxl_sste *primary_group,
+ bool sec_hash,
+ struct cxl_sste *secondary_group,
+ unsigned int *lru)
+{
+ unsigned int i, entry;
+ struct cxl_sste *sste, *group = primary_group;
+
+ for (i = 0; i < 2; i++) {
+ for (entry = 0; entry < 8; entry++) {
+ sste = group + entry;
+ if (!(sste->esid_data & SLB_ESID_V))
+ return sste;
+ }
+ if (!sec_hash)
+ break;
+ group = secondary_group;
+ }
+ /* Nothing free, select an entry to cast out */
+ if (sec_hash && (*lru & 0x8))
+ sste = secondary_group + (*lru & 0x7);
+ else
+ sste = primary_group + (*lru & 0x7);
+ *lru = (*lru + 1) & 0xf;
+
+ return sste;
+}
+
+static void cxl_load_segment(struct cxl_context *ctx, struct copro_slb *slb)
+{
+ /* mask is the group index, we search primary and secondary here. */
+ unsigned int mask = (ctx->sst_size >> 7)-1; /* SSTP0[SegTableSize] */
+ bool sec_hash = 1;
+ struct cxl_sste *sste;
+ unsigned int hash;
+
+ WARN_ON_SMP(!spin_is_locked(&ctx->sst_lock));
+
+ sec_hash = !!(cxl_p1n_read(ctx->afu, CXL_PSL_SR_An) & CXL_PSL_SR_An_SC);
+
+ if (slb->vsid & SLB_VSID_B_1T)
+ hash = (slb->esid >> SID_SHIFT_1T) & mask;
+ else /* 256M */
+ hash = (slb->esid >> SID_SHIFT) & mask;
+
+ sste = find_free_sste(ctx->sstp + (hash << 3), sec_hash,
+ ctx->sstp + ((~hash & mask) << 3), &ctx->sst_lru);
+
+ pr_devel("CXL Populating SST[%li]: %#llx %#llx\n",
+ sste - ctx->sstp, slb->vsid, slb->esid);
+
+ sste->vsid_data = cpu_to_be64(slb->vsid);
+ sste->esid_data = cpu_to_be64(slb->esid);
+}
+
+static int cxl_fault_segment(struct cxl_context *ctx, struct mm_struct *mm,
+ u64 ea)
+{
+ struct copro_slb slb = {0,0};
+ unsigned long flags;
+ int rc;
+
+ spin_lock_irqsave(&ctx->sst_lock, flags);
+ if (!(rc = copro_calc_slb(mm, ea, &slb))) {
+ cxl_load_segment(ctx, &slb);
+ }
+ spin_unlock_irqrestore(&ctx->sst_lock, flags);
+
+ return rc;
+}
+
+static void cxl_ack_ae(struct cxl_context *ctx)
+{
+ unsigned long flags;
+
+ cxl_ack_irq(ctx, CXL_PSL_TFC_An_AE, 0);
+
+ spin_lock_irqsave(&ctx->lock, flags);
+ ctx->pending_fault = true;
+ ctx->fault_addr = ctx->dar;
+ ctx->fault_dsisr = ctx->dsisr;
+ spin_unlock_irqrestore(&ctx->lock, flags);
+
+ wake_up_all(&ctx->wq);
+}
+
+static int cxl_handle_segment_miss(struct cxl_context *ctx,
+ struct mm_struct *mm, u64 ea)
+{
+ int rc;
+
+ pr_devel("CXL interrupt: Segment fault pe: %i ea: %#llx\n", ctx->pe, ea);
+
+ if ((rc = cxl_fault_segment(ctx, mm, ea)))
+ cxl_ack_ae(ctx);
+ else {
+
+ mb(); /* Order seg table write to TFC MMIO write */
+ cxl_ack_irq(ctx, CXL_PSL_TFC_An_R, 0);
+ }
+
+ return IRQ_HANDLED;
+}
+
+static void cxl_handle_page_fault(struct cxl_context *ctx,
+ struct mm_struct *mm, u64 dsisr, u64 dar)
+{
+ unsigned flt = 0;
+ int result;
+ unsigned long access, flags;
+
+ if ((result = copro_handle_mm_fault(mm, dar, dsisr, &flt))) {
+ pr_devel("copro_handle_mm_fault failed: %#x\n", result);
+ return cxl_ack_ae(ctx);
+ }
+
+ /*
+ * update_mmu_cache() will not have loaded the hash since current->trap
+ * is not a 0x400 or 0x300, so just call hash_page_mm() here.
+ */
+ access = _PAGE_PRESENT;
+ if (dsisr & CXL_PSL_DSISR_An_S)
+ access |= _PAGE_RW;
+ if ((!ctx->kernel) || ~(dar & (1ULL << 63)))
+ access |= _PAGE_USER;
+ local_irq_save(flags);
+ hash_page_mm(mm, dar, access, 0x300);
+ local_irq_restore(flags);
+
+ pr_devel("Page fault successfully handled for pe: %i!\n", ctx->pe);
+ cxl_ack_irq(ctx, CXL_PSL_TFC_An_R, 0);
+}
+
+void cxl_handle_fault(struct work_struct *fault_work)
+{
+ struct cxl_context *ctx =
+ container_of(fault_work, struct cxl_context, fault_work);
+ u64 dsisr = ctx->dsisr;
+ u64 dar = ctx->dar;
+ struct task_struct *task;
+ struct mm_struct *mm;
+
+ if (cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An) != dsisr ||
+ cxl_p2n_read(ctx->afu, CXL_PSL_DAR_An) != dar ||
+ cxl_p2n_read(ctx->afu, CXL_PSL_PEHandle_An) != ctx->pe) {
+ /* Most likely explanation is harmless - a dedicated process
+ * has detached and these were cleared by the PSL purge, but
+ * warn about it just in case */
+ dev_notice(&ctx->afu->dev, "cxl_handle_fault: Translation fault regs changed\n");
+ return;
+ }
+
+ pr_devel("CXL BOTTOM HALF handling fault for afu pe: %i. "
+ "DSISR: %#llx DAR: %#llx\n", ctx->pe, dsisr, dar);
+
+ if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
+ pr_devel("cxl_handle_fault unable to get task %i\n",
+ pid_nr(ctx->pid));
+ cxl_ack_ae(ctx);
+ return;
+ }
+ if (!(mm = get_task_mm(task))) {
+ pr_devel("cxl_handle_fault unable to get mm %i\n",
+ pid_nr(ctx->pid));
+ cxl_ack_ae(ctx);
+ goto out;
+ }
+
+ if (dsisr & CXL_PSL_DSISR_An_DS)
+ cxl_handle_segment_miss(ctx, mm, dar);
+ else if (dsisr & CXL_PSL_DSISR_An_DM)
+ cxl_handle_page_fault(ctx, mm, dsisr, dar);
+ else
+ WARN(1, "cxl_handle_fault has nothing to handle\n");
+
+ mmput(mm);
+out:
+ put_task_struct(task);
+}
+
+static void cxl_prefault_one(struct cxl_context *ctx, u64 ea)
+{
+ int rc;
+ struct task_struct *task;
+ struct mm_struct *mm;
+
+ if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
+ pr_devel("cxl_prefault_one unable to get task %i\n",
+ pid_nr(ctx->pid));
+ return;
+ }
+ if (!(mm = get_task_mm(task))) {
+ pr_devel("cxl_prefault_one unable to get mm %i\n",
+ pid_nr(ctx->pid));
+ put_task_struct(task);
+ return;
+ }
+
+ rc = cxl_fault_segment(ctx, mm, ea);
+
+ mmput(mm);
+ put_task_struct(task);
+}
+
+static u64 next_segment(u64 ea, u64 vsid)
+{
+ if (vsid & SLB_VSID_B_1T)
+ ea |= (1ULL << 40) - 1;
+ else
+ ea |= (1ULL << 28) - 1;
+
+ return ea + 1;
+}
+
+static void cxl_prefault_vma(struct cxl_context *ctx)
+{
+ u64 ea, last_esid = 0;
+ struct copro_slb slb;
+ struct vm_area_struct *vma;
+ int rc;
+ struct task_struct *task;
+ struct mm_struct *mm;
+ unsigned long flags;
+
+ if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
+ pr_devel("cxl_prefault_vma unable to get task %i\n",
+ pid_nr(ctx->pid));
+ return;
+ }
+ if (!(mm = get_task_mm(task))) {
+ pr_devel("cxl_prefault_vm unable to get mm %i\n",
+ pid_nr(ctx->pid));
+ goto out1;
+ }
+
+ spin_lock_irqsave(&ctx->sst_lock, flags);
+ down_read(&mm->mmap_sem);
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ for (ea = vma->vm_start; ea < vma->vm_end;
+ ea = next_segment(ea, slb.vsid)) {
+ rc = copro_calc_slb(mm, ea, &slb);
+ if (rc)
+ continue;
+
+ if (last_esid == slb.esid)
+ continue;
+
+ cxl_load_segment(ctx, &slb);
+ last_esid = slb.esid;
+ }
+ }
+ up_read(&mm->mmap_sem);
+ spin_unlock_irqrestore(&ctx->sst_lock, flags);
+
+ mmput(mm);
+out1:
+ put_task_struct(task);
+}
+
+void cxl_prefault(struct cxl_context *ctx, u64 wed)
+{
+ switch (ctx->afu->prefault_mode) {
+ case CXL_PREFAULT_WED:
+ cxl_prefault_one(ctx, wed);
+ break;
+ case CXL_PREFAULT_ALL:
+ cxl_prefault_vma(ctx);
+ break;
+ default:
+ break;
+ }
+}
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
new file mode 100644
index 0000000..74367c4
--- /dev/null
+++ b/drivers/misc/cxl/file.c
@@ -0,0 +1,493 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/bitmap.h>
+#include <linux/sched.h>
+#include <linux/poll.h>
+#include <linux/pid.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/cputable.h>
+#include <asm/current.h>
+#include <asm/copro.h>
+
+#include "cxl.h"
+
+#define CXL_NUM_MINORS 256 /* Total to reserve */
+#define CXL_DEV_MINORS 9 /* 1 control + 4 AFUs * 2 (master/shared) */
+
+#define CXL_CARD_MINOR(adapter) (adapter->adapter_num * CXL_DEV_MINORS)
+#define CXL_AFU_MINOR(afu) (CXL_CARD_MINOR(afu->adapter) + 1 + (2 * afu->slice))
+#define CXL_AFU_MINOR_M(afu) (CXL_AFU_MINOR(afu) + 1)
+#define CXL_AFU_MKDEV(afu) MKDEV(MAJOR(cxl_dev), CXL_AFU_MINOR(afu))
+#define CXL_AFU_MKDEV_M(afu) MKDEV(MAJOR(cxl_dev), CXL_AFU_MINOR_M(afu))
+
+#define CXL_DEVT_ADAPTER(dev) (MINOR(dev) / CXL_DEV_MINORS)
+#define CXL_DEVT_AFU(dev) ((MINOR(dev) % CXL_DEV_MINORS - 1) / 2)
+
+#define CXL_DEVT_IS_CARD(dev) (MINOR(dev) % CXL_DEV_MINORS == 0)
+#define CXL_DEVT_IS_AFU(dev) (!CXL_DEVT_IS_CARD(dev))
+#define _CXL_DEVT_IS_AFU_S(dev) (((MINOR(dev) % CXL_DEV_MINORS) % 2) == 1)
+#define CXL_DEVT_IS_AFU_S(dev) (!CXL_DEVT_IS_CARD(dev) && _CXL_DEVT_IS_AFU_S(dev))
+#define CXL_DEVT_IS_AFU_M(dev) (!CXL_DEVT_IS_CARD(dev) && !_CXL_DEVT_IS_AFU_S(dev))
+
+dev_t cxl_dev;
+
+struct class *cxl_class;
+
+static int __afu_open(struct inode *inode, struct file *file, bool master)
+{
+ struct cxl *adapter;
+ struct cxl_afu *afu;
+ struct cxl_context *ctx;
+ int adapter_num = CXL_DEVT_ADAPTER(inode->i_rdev);
+ int slice = CXL_DEVT_AFU(inode->i_rdev);
+ int rc = -ENODEV;
+
+ pr_devel("afu_open afu%i.%i\n", slice, adapter_num);
+
+ if (!(adapter = get_cxl_adapter(adapter_num)))
+ return -ENODEV;
+
+ if (slice > adapter->slices)
+ goto err_put_adapter;
+
+ spin_lock(&adapter->afu_list_lock);
+ if (!(afu = adapter->afu[slice])) {
+ spin_unlock(&adapter->afu_list_lock);
+ goto err_put_adapter;
+ }
+ get_device(&afu->dev);
+ spin_unlock(&adapter->afu_list_lock);
+
+ if (!afu->current_model)
+ goto err_put_afu;
+
+ if (!(ctx = cxl_context_alloc())) {
+ rc = -ENOMEM;
+ goto err_put_afu;
+ }
+
+ if ((rc = cxl_context_init(ctx, afu, master)))
+ goto err_put_afu;
+
+ pr_devel("afu_open pe: %i\n", ctx->pe);
+ file->private_data = ctx;
+ cxl_ctx_get();
+
+ /* Our ref on the AFU will now hold the adapter */
+ put_device(&adapter->dev);
+
+ return 0;
+
+err_put_afu:
+ put_device(&afu->dev);
+err_put_adapter:
+ put_device(&adapter->dev);
+ return rc;
+}
+static int afu_open(struct inode *inode, struct file *file)
+{
+ return __afu_open(inode, file, false);
+}
+
+static int afu_master_open(struct inode *inode, struct file *file)
+{
+ return __afu_open(inode, file, true);
+}
+
+static int afu_release(struct inode *inode, struct file *file)
+{
+ struct cxl_context *ctx = file->private_data;
+
+ pr_devel("%s: closing cxl file descriptor. pe: %i\n",
+ __func__, ctx->pe);
+ cxl_context_detach(ctx);
+
+ put_device(&ctx->afu->dev);
+
+ /* It should be safe to remove the context now */
+ cxl_context_free(ctx);
+
+ cxl_ctx_put();
+ return 0;
+}
+
+static long afu_ioctl_start_work(struct cxl_context *ctx,
+ struct cxl_ioctl_start_work __user *uwork)
+{
+ struct cxl_ioctl_start_work work;
+ u64 amr = 0;
+ int rc;
+
+ pr_devel("%s: pe: %i\n", __func__, ctx->pe);
+
+ mutex_lock(&ctx->status_mutex);
+ if (ctx->status != OPENED)
+ return -EIO;
+
+ if (copy_from_user(&work, uwork,
+ sizeof(struct cxl_ioctl_start_work)))
+ return -EFAULT;
+
+ /* if any of the reserved fields are set or any of the unused
+ * flags are set it's invalid
+ */
+ if (work.reserved1 || work.reserved2 || work.reserved3 ||
+ work.reserved4 || work.reserved5 || work.reserved6 ||
+ (work.flags & ~CXL_START_WORK_ALL))
+ return -EINVAL;
+
+ if (!(work.flags & CXL_START_WORK_NUM_IRQS))
+ work.num_interrupts = ctx->afu->pp_irqs;
+ else if ((work.num_interrupts < ctx->afu->pp_irqs) ||
+ (work.num_interrupts > ctx->afu->irqs_max))
+ return -EINVAL;
+ if ((rc = afu_register_irqs(ctx, work.num_interrupts)))
+ return rc;
+
+ if (work.flags & CXL_START_WORK_AMR)
+ amr = work.amr & mfspr(SPRN_UAMOR);
+
+ if ((rc = cxl_attach_process(ctx, false, work.wed, amr)))
+ return rc;
+
+ ctx->status = STARTED;
+ mutex_unlock(&ctx->status_mutex);
+
+ return 0;
+}
+static long afu_ioctl_process_element(struct cxl_context *ctx,
+ int __user *upe)
+{
+ pr_devel("%s: pe: %i\n", __func__, ctx->pe);
+
+ if (copy_to_user(upe, &ctx->pe, sizeof(int)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct cxl_context *ctx = file->private_data;
+
+ if (ctx->status == CLOSED)
+ return -EIO;
+
+ pr_devel("afu_ioctl\n");
+ switch (cmd) {
+ case CXL_IOCTL_START_WORK:
+ return afu_ioctl_start_work(ctx, (struct cxl_ioctl_start_work __user *)arg);
+ case CXL_IOCTL_GET_PROCESS_ELEMENT:
+ return afu_ioctl_process_element(ctx, (int __user *)arg);
+ }
+ return -EINVAL;
+}
+
+static long afu_compat_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ return afu_ioctl(file, cmd, arg);
+}
+
+static int afu_mmap(struct file *file, struct vm_area_struct *vm)
+{
+ struct cxl_context *ctx = file->private_data;
+
+ /* AFU must be started before we can MMIO */
+ if (ctx->status != STARTED)
+ return -EIO;
+
+ return cxl_context_iomap(ctx, vm);
+}
+
+static unsigned int afu_poll(struct file *file, struct poll_table_struct *poll)
+{
+ struct cxl_context *ctx = file->private_data;
+ int mask = 0;
+ unsigned long flags;
+
+
+ poll_wait(file, &ctx->wq, poll);
+
+ pr_devel("afu_poll wait done pe: %i\n", ctx->pe);
+
+ spin_lock_irqsave(&ctx->lock, flags);
+ if (ctx->pending_irq || ctx->pending_fault ||
+ ctx->pending_afu_err)
+ mask |= POLLIN | POLLRDNORM;
+ else if (ctx->status == CLOSED)
+ /* Only error on closed when there are no futher events pending
+ */
+ mask |= POLLERR;
+ spin_unlock_irqrestore(&ctx->lock, flags);
+
+ pr_devel("afu_poll pe: %i returning %#x\n", ctx->pe, mask);
+
+ return mask;
+}
+
+static inline int ctx_event_pending(struct cxl_context *ctx)
+{
+ return (ctx->pending_irq || ctx->pending_fault ||
+ ctx->pending_afu_err || (ctx->status == CLOSED));
+}
+
+static ssize_t afu_read(struct file *file, char __user *buf, size_t count,
+ loff_t *off)
+{
+ struct cxl_context *ctx = file->private_data;
+ struct cxl_event event;
+ unsigned long flags;
+ DEFINE_WAIT(wait);
+
+ if (count < CXL_READ_MIN_SIZE)
+ return -EINVAL;
+
+ spin_lock_irqsave(&ctx->lock, flags);
+
+ for (;;) {
+ prepare_to_wait(&ctx->wq, &wait, TASK_INTERRUPTIBLE);
+ if (ctx_event_pending(ctx))
+ break;
+
+ spin_unlock_irqrestore(&ctx->lock, flags);
+ if (file->f_flags & O_NONBLOCK)
+ return -EAGAIN;
+
+ if (signal_pending(current))
+ return -ERESTARTSYS;
+
+ pr_devel("afu_read going to sleep...\n");
+ schedule();
+ pr_devel("afu_read woken up\n");
+ spin_lock_irqsave(&ctx->lock, flags);
+ }
+
+ finish_wait(&ctx->wq, &wait);
+
+ memset(&event, 0, sizeof(event));
+ event.header.process_element = ctx->pe;
+ event.header.size = sizeof(struct cxl_event_header);
+ if (ctx->pending_irq) {
+ pr_devel("afu_read delivering AFU interrupt\n");
+ event.header.size += sizeof(struct cxl_event_afu_interrupt);
+ event.header.type = CXL_EVENT_AFU_INTERRUPT;
+ event.irq.irq = find_first_bit(ctx->irq_bitmap, ctx->irq_count) + 1;
+ clear_bit(event.irq.irq - 1, ctx->irq_bitmap);
+ if (bitmap_empty(ctx->irq_bitmap, ctx->irq_count))
+ ctx->pending_irq = false;
+ } else if (ctx->pending_fault) {
+ pr_devel("afu_read delivering data storage fault\n");
+ event.header.size += sizeof(struct cxl_event_data_storage);
+ event.header.type = CXL_EVENT_DATA_STORAGE;
+ event.fault.addr = ctx->fault_addr;
+ event.fault.dsisr = ctx->fault_dsisr;
+ ctx->pending_fault = false;
+ } else if (ctx->pending_afu_err) {
+ pr_devel("afu_read delivering afu error\n");
+ event.header.size += sizeof(struct cxl_event_afu_error);
+ event.header.type = CXL_EVENT_AFU_ERROR;
+ event.afu_err.err = ctx->afu_err;
+ ctx->pending_afu_err = false;
+ } else if (ctx->status == CLOSED) {
+ pr_devel("afu_read fatal error\n");
+ spin_unlock_irqrestore(&ctx->lock, flags);
+ return -EIO;
+ } else
+ WARN(1, "afu_read must be buggy\n");
+
+ spin_unlock_irqrestore(&ctx->lock, flags);
+
+ if (copy_to_user(buf, &event, event.header.size))
+ return -EFAULT;
+ return event.header.size;
+}
+
+static const struct file_operations afu_fops = {
+ .owner = THIS_MODULE,
+ .open = afu_open,
+ .poll = afu_poll,
+ .read = afu_read,
+ .release = afu_release,
+ .unlocked_ioctl = afu_ioctl,
+ .compat_ioctl = afu_compat_ioctl,
+ .mmap = afu_mmap,
+};
+
+static const struct file_operations afu_master_fops = {
+ .owner = THIS_MODULE,
+ .open = afu_master_open,
+ .poll = afu_poll,
+ .read = afu_read,
+ .release = afu_release,
+ .unlocked_ioctl = afu_ioctl,
+ .compat_ioctl = afu_compat_ioctl,
+ .mmap = afu_mmap,
+};
+
+
+static char *cxl_devnode(struct device *dev, umode_t *mode)
+{
+ struct cxl_afu *afu;
+
+ if (CXL_DEVT_IS_CARD(dev->devt)) {
+ /* These minor numbers will eventually be used to program the
+ * PSL and AFUs once we have dynamic reprogramming support */
+ return NULL;
+ } else { /* CXL_DEVT_IS_AFU */
+ /* Default character devices in each programming model just get
+ * named /dev/cxl/afuX.Y */
+ afu = dev_get_drvdata(dev);
+ if ((afu->current_model == CXL_MODEL_DEDICATED) &&
+ CXL_DEVT_IS_AFU_M(dev->devt))
+ return kasprintf(GFP_KERNEL, "cxl/%s", dev_name(&afu->dev));
+ if ((afu->current_model == CXL_MODEL_DIRECTED) &&
+ CXL_DEVT_IS_AFU_S(dev->devt))
+ return kasprintf(GFP_KERNEL, "cxl/%s", dev_name(&afu->dev));
+ }
+ return kasprintf(GFP_KERNEL, "cxl/%s", dev_name(dev));
+}
+
+extern struct class *cxl_class;
+
+int cxl_chardev_m_afu_add(struct cxl_afu *afu)
+{
+ struct device *dev;
+ int rc;
+
+ cdev_init(&afu->afu_cdev_m, &afu_master_fops);
+ if ((rc = cdev_add(&afu->afu_cdev_m, CXL_AFU_MKDEV_M(afu), 1))) {
+ dev_err(&afu->dev, "Unable to add master chardev: %i\n", rc);
+ return rc;
+ }
+
+ dev = device_create(cxl_class, &afu->dev, CXL_AFU_MKDEV_M(afu), afu,
+ "afu%i.%im", afu->adapter->adapter_num, afu->slice);
+ if (IS_ERR(dev)) {
+ dev_err(&afu->dev, "Unable to create master chardev in sysfs: %i\n", rc);
+ rc = PTR_ERR(dev);
+ goto err;
+ }
+
+ afu->chardev_m = dev;
+
+ return 0;
+err:
+ cdev_del(&afu->afu_cdev_m);
+ return rc;
+}
+
+int cxl_chardev_s_afu_add(struct cxl_afu *afu)
+{
+ struct device *dev;
+ int rc;
+
+ cdev_init(&afu->afu_cdev_s, &afu_fops);
+ if ((rc = cdev_add(&afu->afu_cdev_s, CXL_AFU_MKDEV(afu), 1))) {
+ dev_err(&afu->dev, "Unable to add shared chardev: %i\n", rc);
+ return rc;
+ }
+
+ dev = device_create(cxl_class, &afu->dev, CXL_AFU_MKDEV(afu), afu,
+ "afu%i.%is", afu->adapter->adapter_num, afu->slice);
+ if (IS_ERR(dev)) {
+ dev_err(&afu->dev, "Unable to create shared chardev in sysfs: %i\n", rc);
+ rc = PTR_ERR(dev);
+ goto err;
+ }
+
+ afu->chardev_s = dev;
+
+ return 0;
+err:
+ cdev_del(&afu->afu_cdev_s);
+ return rc;
+}
+
+void cxl_chardev_afu_remove(struct cxl_afu *afu)
+{
+ if (afu->chardev_m) {
+ cdev_del(&afu->afu_cdev_m);
+ device_unregister(afu->chardev_m);
+ }
+ if (afu->chardev_s) {
+ cdev_del(&afu->afu_cdev_s);
+ device_unregister(afu->chardev_s);
+ }
+}
+
+int cxl_register_afu(struct cxl_afu *afu)
+{
+ afu->dev.class = cxl_class;
+
+ return device_register(&afu->dev);
+}
+
+int cxl_register_adapter(struct cxl *adapter)
+{
+ adapter->dev.class = cxl_class;
+
+ /* Future: When we support dynamically reprogramming the PSL & AFU we
+ * will expose the interface to do that via a chardev:
+ * adapter->dev.devt = CXL_CARD_MKDEV(adapter);
+ */
+
+ return device_register(&adapter->dev);
+}
+
+int __init cxl_file_init(void)
+{
+ int rc;
+
+ /* If these change we really need to update API. Either change some
+ * flags or update API version number CXL_API_VERSION.
+ */
+ BUILD_BUG_ON(CXL_API_VERSION != 1);
+ BUILD_BUG_ON(sizeof(struct cxl_ioctl_start_work) != 64);
+ BUILD_BUG_ON(sizeof(struct cxl_event_header) != 8);
+ BUILD_BUG_ON(sizeof(struct cxl_event_afu_interrupt) != 8);
+ BUILD_BUG_ON(sizeof(struct cxl_event_data_storage) != 32);
+ BUILD_BUG_ON(sizeof(struct cxl_event_afu_error) != 16);
+
+ if ((rc = alloc_chrdev_region(&cxl_dev, 0, CXL_NUM_MINORS, "cxl"))) {
+ pr_err("Unable to allocate CXL major number: %i\n", rc);
+ return rc;
+ }
+
+ pr_devel("CXL device allocated, MAJOR %i\n", MAJOR(cxl_dev));
+
+ cxl_class = class_create(THIS_MODULE, "cxl");
+ if (IS_ERR(cxl_class)) {
+ pr_err("Unable to create CXL class\n");
+ rc = PTR_ERR(cxl_class);
+ goto err;
+ }
+ cxl_class->devnode = cxl_devnode;
+
+ return 0;
+
+err:
+ unregister_chrdev_region(cxl_dev, CXL_NUM_MINORS);
+ return rc;
+}
+
+void cxl_file_exit(void)
+{
+ unregister_chrdev_region(cxl_dev, CXL_NUM_MINORS);
+ class_destroy(cxl_class);
+}
diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c
new file mode 100644
index 0000000..d20931b
--- /dev/null
+++ b/drivers/misc/cxl/irq.c
@@ -0,0 +1,398 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/interrupt.h>
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
+#include <linux/slab.h>
+#include <linux/pid.h>
+#include <asm/cputable.h>
+#include <misc/cxl.h>
+
+#include "cxl.h"
+
+/* XXX: This is implementation specific */
+static irqreturn_t handle_psl_slice_error(struct cxl_context *ctx, u64 dsisr, u64 errstat)
+{
+ u64 fir1, fir2, fir_slice, serr, afu_debug;
+
+ fir1 = cxl_p1_read(ctx->afu->adapter, CXL_PSL_FIR1);
+ fir2 = cxl_p1_read(ctx->afu->adapter, CXL_PSL_FIR2);
+ fir_slice = cxl_p1n_read(ctx->afu, CXL_PSL_FIR_SLICE_An);
+ serr = cxl_p1n_read(ctx->afu, CXL_PSL_SERR_An);
+ afu_debug = cxl_p1n_read(ctx->afu, CXL_AFU_DEBUG_An);
+
+ dev_crit(&ctx->afu->dev, "PSL ERROR STATUS: 0x%.16llx\n", errstat);
+ dev_crit(&ctx->afu->dev, "PSL_FIR1: 0x%.16llx\n", fir1);
+ dev_crit(&ctx->afu->dev, "PSL_FIR2: 0x%.16llx\n", fir2);
+ dev_crit(&ctx->afu->dev, "PSL_SERR_An: 0x%.16llx\n", serr);
+ dev_crit(&ctx->afu->dev, "PSL_FIR_SLICE_An: 0x%.16llx\n", fir_slice);
+ dev_crit(&ctx->afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%.16llx\n", afu_debug);
+
+ dev_crit(&ctx->afu->dev, "STOPPING CXL TRACE\n");
+ cxl_stop_trace(ctx->afu->adapter);
+
+ return cxl_ack_irq(ctx, 0, errstat);
+}
+
+irqreturn_t cxl_slice_irq_err(int irq, void *data)
+{
+ struct cxl_afu *afu = data;
+ u64 fir_slice, errstat, serr, afu_debug;
+
+ WARN(irq, "CXL SLICE ERROR interrupt %i\n", irq);
+
+ serr = cxl_p1n_read(afu, CXL_PSL_SERR_An);
+ fir_slice = cxl_p1n_read(afu, CXL_PSL_FIR_SLICE_An);
+ errstat = cxl_p2n_read(afu, CXL_PSL_ErrStat_An);
+ afu_debug = cxl_p1n_read(afu, CXL_AFU_DEBUG_An);
+ dev_crit(&afu->dev, "PSL_SERR_An: 0x%.16llx\n", serr);
+ dev_crit(&afu->dev, "PSL_FIR_SLICE_An: 0x%.16llx\n", fir_slice);
+ dev_crit(&afu->dev, "CXL_PSL_ErrStat_An: 0x%.16llx\n", errstat);
+ dev_crit(&afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%.16llx\n", afu_debug);
+
+ cxl_p1n_write(afu, CXL_PSL_SERR_An, serr);
+
+ return IRQ_HANDLED;
+}
+
+irqreturn_t cxl_irq_err(int irq, void *data)
+{
+ struct cxl *adapter = data;
+ u64 fir1, fir2, err_ivte;
+
+ WARN(1, "CXL ERROR interrupt %i\n", irq);
+
+ err_ivte = cxl_p1_read(adapter, CXL_PSL_ErrIVTE);
+ dev_crit(&adapter->dev, "PSL_ErrIVTE: 0x%.16llx\n", err_ivte);
+
+ dev_crit(&adapter->dev, "STOPPING CXL TRACE\n");
+ cxl_stop_trace(adapter);
+
+ fir1 = cxl_p1_read(adapter, CXL_PSL_FIR1);
+ fir2 = cxl_p1_read(adapter, CXL_PSL_FIR2);
+
+ dev_crit(&adapter->dev, "PSL_FIR1: 0x%.16llx\nPSL_FIR2: 0x%.16llx\n", fir1, fir2);
+
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t schedule_cxl_fault(struct cxl_context *ctx, u64 dsisr, u64 dar)
+{
+ ctx->dsisr = dsisr;
+ ctx->dar = dar;
+ schedule_work(&ctx->fault_work);
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t cxl_irq(int irq, void *data)
+{
+ struct cxl_context *ctx = data;
+ struct cxl_irq_info irq_info;
+ u64 dsisr, dar;
+ int result;
+
+ if ((result = cxl_get_irq(ctx, &irq_info))) {
+ WARN(1, "Unable to get CXL IRQ Info: %i\n", result);
+ return IRQ_HANDLED;
+ }
+
+ dsisr = irq_info.dsisr;
+ dar = irq_info.dar;
+
+ pr_devel("CXL interrupt %i for afu pe: %i DSISR: %#llx DAR: %#llx\n", irq, ctx->pe, dsisr, dar);
+
+ if (dsisr & CXL_PSL_DSISR_An_DS) {
+ /* We don't inherently need to sleep to handle this, but we do
+ * need to get a ref to the task's mm, which we can't do from
+ * irq context without the potential for a deadlock since it
+ * takes the task_lock. An alternate option would be to keep a
+ * reference to the task's mm the entire time it has cxl open,
+ * but to do that we need to solve the issue where we hold a
+ * ref to the mm, but the mm can hold a ref to the fd after an
+ * mmap preventing anything from being cleaned up. */
+ pr_devel("Scheduling segment miss handling for later pe: %i\n", ctx->pe);
+ return schedule_cxl_fault(ctx, dsisr, dar);
+ }
+
+ if (dsisr & CXL_PSL_DSISR_An_M)
+ pr_devel("CXL interrupt: PTE not found\n");
+ if (dsisr & CXL_PSL_DSISR_An_P)
+ pr_devel("CXL interrupt: Storage protection violation\n");
+ if (dsisr & CXL_PSL_DSISR_An_A)
+ pr_devel("CXL interrupt: AFU lock access to write through or cache inhibited storage\n");
+ if (dsisr & CXL_PSL_DSISR_An_S)
+ pr_devel("CXL interrupt: Access was afu_wr or afu_zero\n");
+ if (dsisr & CXL_PSL_DSISR_An_K)
+ pr_devel("CXL interrupt: Access not permitted by virtual page class key protection\n");
+
+ if (dsisr & CXL_PSL_DSISR_An_DM) {
+ /* In some cases we might be able to handle the fault
+ * immediately if hash_page would succeed, but we still need
+ * the task's mm, which as above we can't get without a lock */
+ pr_devel("Scheduling page fault handling for later pe: %i\n", ctx->pe);
+ return schedule_cxl_fault(ctx, dsisr, dar);
+ }
+ if (dsisr & CXL_PSL_DSISR_An_ST)
+ WARN(1, "CXL interrupt: Segment Table PTE not found\n");
+ if (dsisr & CXL_PSL_DSISR_An_UR)
+ pr_devel("CXL interrupt: AURP PTE not found\n");
+ if (dsisr & CXL_PSL_DSISR_An_PE)
+ return handle_psl_slice_error(ctx, dsisr, irq_info.errstat);
+ if (dsisr & CXL_PSL_DSISR_An_AE) {
+ pr_devel("CXL interrupt: AFU Error %.llx\n", irq_info.afu_err);
+
+ if (ctx->pending_afu_err) {
+ /* This shouldn't happen - the PSL treats these errors
+ * as fatal and will have reset the AFU, so there's not
+ * much point buffering multiple AFU errors.
+ * OTOH if we DO ever see a storm of these come in it's
+ * probably best that we log them somewhere: */
+ dev_err_ratelimited(&ctx->afu->dev, "CXL AFU Error "
+ "undelivered to pe %i: %.llx\n",
+ ctx->pe, irq_info.afu_err);
+ } else {
+ spin_lock(&ctx->lock);
+ ctx->afu_err = irq_info.afu_err;
+ ctx->pending_afu_err = 1;
+ spin_unlock(&ctx->lock);
+
+ wake_up_all(&ctx->wq);
+ }
+
+ cxl_ack_irq(ctx, CXL_PSL_TFC_An_A, 0);
+ }
+ if (dsisr & CXL_PSL_DSISR_An_OC)
+ pr_devel("CXL interrupt: OS Context Warning\n");
+
+ WARN(1, "Unhandled CXL PSL IRQ\n");
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t cxl_irq_multiplexed(int irq, void *data)
+{
+ struct cxl_afu *afu = data;
+ struct cxl_context *ctx;
+ int ph = cxl_p2n_read(afu, CXL_PSL_PEHandle_An) & 0xffff;
+ int ret;
+
+ rcu_read_lock();
+ ctx = idr_find(&afu->contexts_idr, ph);
+ if (ctx) {
+ ret = cxl_irq(irq, ctx);
+ rcu_read_unlock();
+ return ret;
+ }
+ rcu_read_unlock();
+
+ WARN(1, "Unable to demultiplex CXL PSL IRQ\n");
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t cxl_irq_afu(int irq, void *data)
+{
+ struct cxl_context *ctx = data;
+ irq_hw_number_t hwirq = irqd_to_hwirq(irq_get_irq_data(irq));
+ int irq_off, afu_irq = 1;
+ __u16 range;
+ int r;
+
+ for (r = 1; r < CXL_IRQ_RANGES; r++) {
+ irq_off = hwirq - ctx->irqs.offset[r];
+ range = ctx->irqs.range[r];
+ if (irq_off >= 0 && irq_off < range) {
+ afu_irq += irq_off;
+ break;
+ }
+ afu_irq += range;
+ }
+ if (unlikely(r >= CXL_IRQ_RANGES)) {
+ WARN(1, "Recieved AFU IRQ out of range for pe %i (virq %i hwirq %lx)\n",
+ ctx->pe, irq, hwirq);
+ return IRQ_HANDLED;
+ }
+
+ pr_devel("Received AFU interrupt %i for pe: %i (virq %i hwirq %lx)\n",
+ afu_irq, ctx->pe, irq, hwirq);
+
+ if (unlikely(!ctx->irq_bitmap)) {
+ WARN(1, "Recieved AFU IRQ for context with no IRQ bitmap\n");
+ return IRQ_HANDLED;
+ }
+ spin_lock(&ctx->lock);
+ set_bit(afu_irq - 1, ctx->irq_bitmap);
+ ctx->pending_irq = true;
+ spin_unlock(&ctx->lock);
+
+ wake_up_all(&ctx->wq);
+
+ return IRQ_HANDLED;
+}
+
+unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq,
+ irq_handler_t handler, void *cookie)
+{
+ unsigned int virq;
+ int result;
+
+ /* IRQ Domain? */
+ virq = irq_create_mapping(NULL, hwirq);
+ if (!virq) {
+ dev_warn(&adapter->dev, "cxl_map_irq: irq_create_mapping failed\n");
+ return 0;
+ }
+
+ cxl_setup_irq(adapter, hwirq, virq);
+
+ pr_devel("hwirq %#lx mapped to virq %u\n", hwirq, virq);
+
+ result = request_irq(virq, handler, 0, "cxl", cookie);
+ if (result) {
+ dev_warn(&adapter->dev, "cxl_map_irq: request_irq failed: %i\n", result);
+ return 0;
+ }
+
+ return virq;
+}
+
+void cxl_unmap_irq(unsigned int virq, void *cookie)
+{
+ free_irq(virq, cookie);
+ irq_dispose_mapping(virq);
+}
+
+static int cxl_register_one_irq(struct cxl *adapter,
+ irq_handler_t handler,
+ void *cookie,
+ irq_hw_number_t *dest_hwirq,
+ unsigned int *dest_virq)
+{
+ int hwirq, virq;
+
+ if ((hwirq = cxl_alloc_one_irq(adapter)) < 0)
+ return hwirq;
+
+ if (!(virq = cxl_map_irq(adapter, hwirq, handler, cookie)))
+ goto err;
+
+ *dest_hwirq = hwirq;
+ *dest_virq = virq;
+
+ return 0;
+
+err:
+ cxl_release_one_irq(adapter, hwirq);
+ return -ENOMEM;
+}
+
+int cxl_register_psl_err_irq(struct cxl *adapter)
+{
+ int rc;
+
+ if ((rc = cxl_register_one_irq(adapter, cxl_irq_err, adapter,
+ &adapter->err_hwirq,
+ &adapter->err_virq)))
+ return rc;
+
+ cxl_p1_write(adapter, CXL_PSL_ErrIVTE, adapter->err_hwirq & 0xffff);
+
+ return 0;
+}
+
+void cxl_release_psl_err_irq(struct cxl *adapter)
+{
+ cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000);
+ cxl_unmap_irq(adapter->err_virq, adapter);
+ cxl_release_one_irq(adapter, adapter->err_hwirq);
+}
+
+int cxl_register_serr_irq(struct cxl_afu *afu)
+{
+ u64 serr;
+ int rc;
+
+ if ((rc = cxl_register_one_irq(afu->adapter, cxl_slice_irq_err, afu,
+ &afu->serr_hwirq,
+ &afu->serr_virq)))
+ return rc;
+
+ serr = cxl_p1n_read(afu, CXL_PSL_SERR_An);
+ serr = (serr & 0x00ffffffffff0000ULL) | (afu->serr_hwirq & 0xffff);
+ cxl_p1n_write(afu, CXL_PSL_SERR_An, serr);
+
+ return 0;
+}
+
+void cxl_release_serr_irq(struct cxl_afu *afu)
+{
+ cxl_p1n_write(afu, CXL_PSL_SERR_An, 0x0000000000000000);
+ cxl_unmap_irq(afu->serr_virq, afu);
+ cxl_release_one_irq(afu->adapter, afu->serr_hwirq);
+}
+
+int cxl_register_psl_irq(struct cxl_afu *afu)
+{
+ return cxl_register_one_irq(afu->adapter, cxl_irq_multiplexed, afu,
+ &afu->psl_hwirq, &afu->psl_virq);
+}
+
+void cxl_release_psl_irq(struct cxl_afu *afu)
+{
+ cxl_unmap_irq(afu->psl_virq, afu);
+ cxl_release_one_irq(afu->adapter, afu->psl_hwirq);
+}
+
+int afu_register_irqs(struct cxl_context *ctx, u32 count)
+{
+ irq_hw_number_t hwirq;
+ int rc, r, i;
+
+ if ((rc = cxl_alloc_irq_ranges(&ctx->irqs, ctx->afu->adapter, count)))
+ return rc;
+
+ /* Multiplexed PSL Interrupt */
+ ctx->irqs.offset[0] = ctx->afu->psl_hwirq;
+ ctx->irqs.range[0] = 1;
+
+ ctx->irq_count = count;
+ ctx->irq_bitmap = kcalloc(BITS_TO_LONGS(count),
+ sizeof(*ctx->irq_bitmap), GFP_KERNEL);
+ if (!ctx->irq_bitmap)
+ return -ENOMEM;
+ for (r = 1; r < CXL_IRQ_RANGES; r++) {
+ hwirq = ctx->irqs.offset[r];
+ for (i = 0; i < ctx->irqs.range[r]; hwirq++, i++) {
+ cxl_map_irq(ctx->afu->adapter, hwirq,
+ cxl_irq_afu, ctx);
+ }
+ }
+
+ return 0;
+}
+
+void afu_release_irqs(struct cxl_context *ctx)
+{
+ irq_hw_number_t hwirq;
+ unsigned int virq;
+ int r, i;
+
+ for (r = 1; r < CXL_IRQ_RANGES; r++) {
+ hwirq = ctx->irqs.offset[r];
+ for (i = 0; i < ctx->irqs.range[r]; hwirq++, i++) {
+ virq = irq_find_mapping(NULL, hwirq);
+ if (virq)
+ cxl_unmap_irq(virq, ctx);
+ }
+ }
+
+ cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter);
+}
diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c
new file mode 100644
index 0000000..2d78471
--- /dev/null
+++ b/drivers/misc/cxl/main.c
@@ -0,0 +1,234 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/spinlock.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/idr.h>
+#include <linux/pci.h>
+#include <asm/cputable.h>
+#include <misc/cxl.h>
+
+#include "cxl.h"
+
+static DEFINE_SPINLOCK(adapter_idr_lock);
+static DEFINE_IDR(cxl_adapter_idr);
+
+uint cxl_verbose;
+module_param_named(verbose, cxl_verbose, uint, 0600);
+MODULE_PARM_DESC(verbose, "Enable verbose dmesg output");
+
+static inline void _cxl_slbia(struct cxl_context *ctx, struct mm_struct *mm)
+{
+ struct task_struct *task;
+ unsigned long flags;
+
+ if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
+ pr_devel("%s unable to get task %i\n",
+ __func__, pid_nr(ctx->pid));
+ return;
+ }
+
+ if (task->mm != mm)
+ goto out_put;
+
+ pr_devel("%s matched mm - card: %i afu: %i pe: %i\n", __func__,
+ ctx->afu->adapter->adapter_num, ctx->afu->slice, ctx->pe);
+
+ spin_lock_irqsave(&ctx->sst_lock, flags);
+ if (!ctx->sstp)
+ goto out_unlock;
+ memset(ctx->sstp, 0, ctx->sst_size);
+ mb();
+ cxl_afu_slbia(ctx->afu);
+
+out_unlock:
+ spin_unlock_irqrestore(&ctx->sst_lock, flags);
+out_put:
+ put_task_struct(task);
+}
+
+static inline void cxl_slbia_core(struct mm_struct *mm)
+{
+ struct cxl *adapter;
+ struct cxl_afu *afu;
+ struct cxl_context *ctx;
+ int card, slice, id;
+
+ pr_devel("%s called\n", __func__);
+
+ spin_lock(&adapter_idr_lock);
+ idr_for_each_entry(&cxl_adapter_idr, adapter, card) {
+ /* XXX: Make this lookup faster with link from mm to ctx */
+ spin_lock(&adapter->afu_list_lock);
+ for (slice = 0; slice < adapter->slices; slice++) {
+ afu = adapter->afu[slice];
+ if (!afu->enabled)
+ continue;
+ rcu_read_lock();
+ idr_for_each_entry(&afu->contexts_idr, ctx, id)
+ _cxl_slbia(ctx, mm);
+ rcu_read_unlock();
+ }
+ spin_unlock(&adapter->afu_list_lock);
+ }
+ spin_unlock(&adapter_idr_lock);
+}
+
+struct cxl_calls cxl_calls = {
+ .cxl_slbia = cxl_slbia_core,
+ .owner = THIS_MODULE,
+};
+
+int cxl_alloc_sst(struct cxl_context *ctx, u64 *sstp0, u64 *sstp1)
+{
+ unsigned long vsid;
+ u64 ea_mask;
+ u64 size;
+
+ *sstp0 = 0;
+ *sstp1 = 0;
+
+ ctx->sst_size = PAGE_SIZE;
+ ctx->sst_lru = 0;
+ ctx->sstp = (struct cxl_sste *)get_zeroed_page(GFP_KERNEL);
+ if (!ctx->sstp) {
+ pr_err("cxl_alloc_sst: Unable to allocate segment table\n");
+ return -ENOMEM;
+ }
+ pr_devel("SSTP allocated at 0x%p\n", ctx->sstp);
+
+ vsid = get_kernel_vsid((u64)ctx->sstp, mmu_kernel_ssize) << 12;
+
+ *sstp0 |= (u64)mmu_kernel_ssize << CXL_SSTP0_An_B_SHIFT;
+ *sstp0 |= (SLB_VSID_KERNEL | mmu_psize_defs[mmu_linear_psize].sllp) << 50;
+
+ size = (((u64)ctx->sst_size >> 8) - 1) << CXL_SSTP0_An_SegTableSize_SHIFT;
+ if (unlikely(size & ~CXL_SSTP0_An_SegTableSize_MASK)) {
+ WARN(1, "Impossible segment table size\n");
+ return -EINVAL;
+ }
+ *sstp0 |= size;
+
+ if (mmu_kernel_ssize == MMU_SEGSIZE_256M)
+ ea_mask = 0xfffff00ULL;
+ else
+ ea_mask = 0xffffffff00ULL;
+
+ *sstp0 |= vsid >> (50-14); /* Top 14 bits of VSID */
+ *sstp1 |= (vsid << (64-(50-14))) & ~ea_mask;
+ *sstp1 |= (u64)ctx->sstp & ea_mask;
+ *sstp1 |= CXL_SSTP1_An_V;
+
+ pr_devel("Looked up %#llx: slbfee. %#llx (ssize: %x, vsid: %#lx), copied to SSTP0: %#llx, SSTP1: %#llx\n",
+ (u64)ctx->sstp, (u64)ctx->sstp & ESID_MASK, mmu_kernel_ssize, vsid, *sstp0, *sstp1);
+
+ return 0;
+}
+
+/* Find a CXL adapter by it's number and increase it's refcount */
+struct cxl *get_cxl_adapter(int num)
+{
+ struct cxl *adapter;
+
+ spin_lock(&adapter_idr_lock);
+ if ((adapter = idr_find(&cxl_adapter_idr, num)))
+ get_device(&adapter->dev);
+ spin_unlock(&adapter_idr_lock);
+
+ return adapter;
+}
+
+int cxl_alloc_adapter_nr(struct cxl *adapter)
+{
+ int i;
+
+ idr_preload(GFP_KERNEL);
+ spin_lock(&adapter_idr_lock);
+ i = idr_alloc(&cxl_adapter_idr, adapter, 0, 0, GFP_NOWAIT);
+ spin_unlock(&adapter_idr_lock);
+ idr_preload_end();
+ if (i < 0)
+ return i;
+
+ adapter->adapter_num = i;
+
+ return 0;
+}
+
+void cxl_remove_adapter_nr(struct cxl *adapter)
+{
+ idr_remove(&cxl_adapter_idr, adapter->adapter_num);
+}
+
+int cxl_afu_select_best_model(struct cxl_afu *afu)
+{
+ if (afu->models_supported & CXL_MODEL_DIRECTED)
+ return cxl_afu_activate_model(afu, CXL_MODEL_DIRECTED);
+
+ if (afu->models_supported & CXL_MODEL_DEDICATED)
+ return cxl_afu_activate_model(afu, CXL_MODEL_DEDICATED);
+
+ dev_warn(&afu->dev, "No supported programing models available\n");
+ /* We don't fail this so the user can inspect sysfs */
+ return 0;
+}
+
+static int __init init_cxl(void)
+{
+ int rc = 0;
+
+ if (!cpu_has_feature(CPU_FTR_HVMODE))
+ return -EPERM;
+
+ if ((rc = cxl_file_init()))
+ return rc;
+
+ cxl_debugfs_init();
+
+ if ((rc = register_cxl_calls(&cxl_calls)))
+ goto err;
+
+ if ((rc = pci_register_driver(&cxl_pci_driver)))
+ goto err1;
+
+ return 0;
+err1:
+ unregister_cxl_calls(&cxl_calls);
+err:
+ cxl_debugfs_exit();
+ cxl_file_exit();
+
+ return rc;
+}
+
+static void exit_cxl(void)
+{
+ pci_unregister_driver(&cxl_pci_driver);
+
+ cxl_debugfs_exit();
+ cxl_file_exit();
+ unregister_cxl_calls(&cxl_calls);
+}
+
+module_init(init_cxl);
+module_exit(exit_cxl);
+
+MODULE_DESCRIPTION("IBM Coherent Accelerator");
+MODULE_AUTHOR("Ian Munsie <imunsie@au1.ibm.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
new file mode 100644
index 0000000..8692057
--- /dev/null
+++ b/drivers/misc/cxl/native.c
@@ -0,0 +1,683 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/mutex.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include <asm/synch.h>
+#include <misc/cxl.h>
+
+#include "cxl.h"
+
+static int afu_control(struct cxl_afu *afu, u64 command,
+ u64 result, u64 mask, bool enabled)
+{
+ u64 AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
+ unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT);
+
+ spin_lock(&afu->afu_cntl_lock);
+ pr_devel("AFU command starting: %llx\n", command);
+
+ cxl_p2n_write(afu, CXL_AFU_Cntl_An, AFU_Cntl | command);
+
+ AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
+ while ((AFU_Cntl & mask) != result) {
+ if (time_after_eq(jiffies, timeout)) {
+ dev_warn(&afu->dev, "WARNING: AFU control timed out!\n");
+ spin_unlock(&afu->afu_cntl_lock);
+ return -EBUSY;
+ }
+ pr_devel_ratelimited("AFU control... (0x%.16llx)\n",
+ AFU_Cntl | command);
+ cpu_relax();
+ AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
+ };
+ pr_devel("AFU command complete: %llx\n", command);
+ afu->enabled = enabled;
+ spin_unlock(&afu->afu_cntl_lock);
+
+ return 0;
+}
+
+static int afu_enable(struct cxl_afu *afu)
+{
+ pr_devel("AFU enable request\n");
+
+ return afu_control(afu, CXL_AFU_Cntl_An_E,
+ CXL_AFU_Cntl_An_ES_Enabled,
+ CXL_AFU_Cntl_An_ES_MASK, true);
+}
+
+int cxl_afu_disable(struct cxl_afu *afu)
+{
+ pr_devel("AFU disable request\n");
+
+ return afu_control(afu, 0, CXL_AFU_Cntl_An_ES_Disabled,
+ CXL_AFU_Cntl_An_ES_MASK, false);
+}
+
+/* This will disable as well as reset */
+int cxl_afu_reset(struct cxl_afu *afu)
+{
+ pr_devel("AFU reset request\n");
+
+ return afu_control(afu, CXL_AFU_Cntl_An_RA,
+ CXL_AFU_Cntl_An_RS_Complete | CXL_AFU_Cntl_An_ES_Disabled,
+ CXL_AFU_Cntl_An_RS_MASK | CXL_AFU_Cntl_An_ES_MASK,
+ false);
+}
+
+static int afu_check_and_enable(struct cxl_afu *afu)
+{
+ if (afu->enabled)
+ return 0;
+ return afu_enable(afu);
+}
+
+int cxl_psl_purge(struct cxl_afu *afu)
+{
+ u64 PSL_CNTL = cxl_p1n_read(afu, CXL_PSL_SCNTL_An);
+ u64 AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
+ u64 dsisr, dar;
+ u64 start, end;
+ unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT);
+
+ pr_devel("PSL purge request\n");
+
+ if ((AFU_Cntl & CXL_AFU_Cntl_An_ES_MASK) != CXL_AFU_Cntl_An_ES_Disabled) {
+ WARN(1, "psl_purge request while AFU not disabled!\n");
+ cxl_afu_disable(afu);
+ }
+
+ cxl_p1n_write(afu, CXL_PSL_SCNTL_An,
+ PSL_CNTL | CXL_PSL_SCNTL_An_Pc);
+ start = local_clock();
+ PSL_CNTL = cxl_p1n_read(afu, CXL_PSL_SCNTL_An);
+ while ((PSL_CNTL & CXL_PSL_SCNTL_An_Ps_MASK)
+ == CXL_PSL_SCNTL_An_Ps_Pending) {
+ if (time_after_eq(jiffies, timeout)) {
+ dev_warn(&afu->dev, "WARNING: PSL Purge timed out!\n");
+ return -EBUSY;
+ }
+ dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
+ pr_devel_ratelimited("PSL purging... PSL_CNTL: 0x%.16llx PSL_DSISR: 0x%.16llx\n", PSL_CNTL, dsisr);
+ if (dsisr & CXL_PSL_DSISR_TRANS) {
+ dar = cxl_p2n_read(afu, CXL_PSL_DAR_An);
+ dev_notice(&afu->dev, "PSL purge terminating pending translation, DSISR: 0x%.16llx, DAR: 0x%.16llx\n", dsisr, dar);
+ cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_AE);
+ } else if (dsisr) {
+ dev_notice(&afu->dev, "PSL purge acknowledging pending non-translation fault, DSISR: 0x%.16llx\n", dsisr);
+ cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_A);
+ } else {
+ cpu_relax();
+ }
+ PSL_CNTL = cxl_p1n_read(afu, CXL_PSL_SCNTL_An);
+ };
+ end = local_clock();
+ pr_devel("PSL purged in %lld ns\n", end - start);
+
+ cxl_p1n_write(afu, CXL_PSL_SCNTL_An,
+ PSL_CNTL & ~CXL_PSL_SCNTL_An_Pc);
+ return 0;
+}
+
+static int spa_max_procs(int spa_size)
+{
+ /* From the CAIA:
+ * end_of_SPA_area = SPA_Base + ((n+4) * 128) + (( ((n*8) + 127) >> 7) * 128) + 255
+ * Most of that junk is really just an overly-complicated way of saying
+ * the last 256 bytes are __aligned(128), so it's really:
+ * end_of_SPA_area = end_of_PSL_queue_area + __aligned(128) 255
+ * and
+ * end_of_PSL_queue_area = SPA_Base + ((n+4) * 128) + (n*8) - 1
+ * so
+ * sizeof(SPA) = ((n+4) * 128) + (n*8) + __aligned(128) 256
+ * Ignore the alignment (which is safe in this case as long as we are
+ * careful with our rounding) and solve for n:
+ */
+ return ((spa_size / 8) - 96) / 17;
+}
+
+static int alloc_spa(struct cxl_afu *afu)
+{
+ u64 spap;
+
+ /* Work out how many pages to allocate */
+ afu->spa_order = 0;
+ do {
+ afu->spa_order++;
+ afu->spa_size = (1 << afu->spa_order) * PAGE_SIZE;
+ afu->spa_max_procs = spa_max_procs(afu->spa_size);
+ } while (afu->spa_max_procs < afu->num_procs);
+
+ WARN_ON(afu->spa_size > 0x100000); /* Max size supported by the hardware */
+
+ if (!(afu->spa = (struct cxl_process_element *)
+ __get_free_pages(GFP_KERNEL | __GFP_ZERO, afu->spa_order))) {
+ pr_err("cxl_alloc_spa: Unable to allocate scheduled process area\n");
+ return -ENOMEM;
+ }
+ pr_devel("spa pages: %i afu->spa_max_procs: %i afu->num_procs: %i\n",
+ 1<<afu->spa_order, afu->spa_max_procs, afu->num_procs);
+
+ afu->sw_command_status = (__be64 *)((char *)afu->spa +
+ ((afu->spa_max_procs + 3) * 128));
+
+ spap = virt_to_phys(afu->spa) & CXL_PSL_SPAP_Addr;
+ spap |= ((afu->spa_size >> (12 - CXL_PSL_SPAP_Size_Shift)) - 1) & CXL_PSL_SPAP_Size;
+ spap |= CXL_PSL_SPAP_V;
+ pr_devel("cxl: SPA allocated at 0x%p. Max processes: %i, sw_command_status: 0x%p CXL_PSL_SPAP_An=0x%016llx\n", afu->spa, afu->spa_max_procs, afu->sw_command_status, spap);
+ cxl_p1n_write(afu, CXL_PSL_SPAP_An, spap);
+
+ return 0;
+}
+
+static void release_spa(struct cxl_afu *afu)
+{
+ free_pages((unsigned long) afu->spa, afu->spa_order);
+}
+
+int cxl_tlb_slb_invalidate(struct cxl *adapter)
+{
+ unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT);
+
+ pr_devel("CXL adapter wide TLBIA & SLBIA\n");
+
+ cxl_p1_write(adapter, CXL_PSL_AFUSEL, CXL_PSL_AFUSEL_A);
+
+ cxl_p1_write(adapter, CXL_PSL_TLBIA, CXL_TLB_SLB_IQ_ALL);
+ while (cxl_p1_read(adapter, CXL_PSL_TLBIA) & CXL_TLB_SLB_P) {
+ if (time_after_eq(jiffies, timeout)) {
+ dev_warn(&adapter->dev, "WARNING: CXL adapter wide TLBIA timed out!\n");
+ return -EBUSY;
+ }
+ cpu_relax();
+ }
+
+ cxl_p1_write(adapter, CXL_PSL_SLBIA, CXL_TLB_SLB_IQ_ALL);
+ while (cxl_p1_read(adapter, CXL_PSL_SLBIA) & CXL_TLB_SLB_P) {
+ if (time_after_eq(jiffies, timeout)) {
+ dev_warn(&adapter->dev, "WARNING: CXL adapter wide SLBIA timed out!\n");
+ return -EBUSY;
+ }
+ cpu_relax();
+ }
+ return 0;
+}
+
+int cxl_afu_slbia(struct cxl_afu *afu)
+{
+ unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT);
+
+ pr_devel("cxl_afu_slbia issuing SLBIA command\n");
+ cxl_p2n_write(afu, CXL_SLBIA_An, CXL_TLB_SLB_IQ_ALL);
+ while (cxl_p2n_read(afu, CXL_SLBIA_An) & CXL_TLB_SLB_P) {
+ if (time_after_eq(jiffies, timeout)) {
+ dev_warn(&afu->dev, "WARNING: CXL AFU SLBIA timed out!\n");
+ return -EBUSY;
+ }
+ cpu_relax();
+ }
+ return 0;
+}
+
+static int cxl_write_sstp(struct cxl_afu *afu, u64 sstp0, u64 sstp1)
+{
+ int rc;
+
+ /* 1. Disable SSTP by writing 0 to SSTP1[V] */
+ cxl_p2n_write(afu, CXL_SSTP1_An, 0);
+
+ /* 2. Invalidate all SLB entries */
+ if ((rc = cxl_afu_slbia(afu)))
+ return rc;
+
+ /* 3. Set SSTP0_An */
+ cxl_p2n_write(afu, CXL_SSTP0_An, sstp0);
+
+ /* 4. Set SSTP1_An */
+ cxl_p2n_write(afu, CXL_SSTP1_An, sstp1);
+
+ return 0;
+}
+
+/* Using per slice version may improve performance here. (ie. SLBIA_An) */
+static void slb_invalid(struct cxl_context *ctx)
+{
+ struct cxl *adapter = ctx->afu->adapter;
+ u64 slbia;
+
+ WARN_ON(!mutex_is_locked(&ctx->afu->spa_mutex));
+
+ cxl_p1_write(adapter, CXL_PSL_LBISEL,
+ ((u64)be32_to_cpu(ctx->elem->common.pid) << 32) |
+ be32_to_cpu(ctx->elem->lpid));
+ cxl_p1_write(adapter, CXL_PSL_SLBIA, CXL_TLB_SLB_IQ_LPIDPID);
+
+ while (1) {
+ slbia = cxl_p1_read(adapter, CXL_PSL_SLBIA);
+ if (!(slbia & CXL_TLB_SLB_P))
+ break;
+ cpu_relax();
+ }
+}
+
+static int do_process_element_cmd(struct cxl_context *ctx,
+ u64 cmd, u64 pe_state)
+{
+ u64 state;
+
+ WARN_ON(!ctx->afu->enabled);
+
+ ctx->elem->software_state = cpu_to_be32(pe_state);
+ smp_wmb();
+ *(ctx->afu->sw_command_status) = cpu_to_be64(cmd | 0 | ctx->pe);
+ smp_mb();
+ cxl_p1n_write(ctx->afu, CXL_PSL_LLCMD_An, cmd | ctx->pe);
+ while (1) {
+ state = be64_to_cpup(ctx->afu->sw_command_status);
+ if (state == ~0ULL) {
+ pr_err("cxl: Error adding process element to AFU\n");
+ return -1;
+ }
+ if ((state & (CXL_SPA_SW_CMD_MASK | CXL_SPA_SW_STATE_MASK | CXL_SPA_SW_LINK_MASK)) ==
+ (cmd | (cmd >> 16) | ctx->pe))
+ break;
+ /* The command won't finish in the PSL if there are
+ * outstanding DSIs. Hence we need to yield here in
+ * case there are outstanding DSIs that we need to
+ * service. Tuning possiblity: we could wait for a
+ * while before sched
+ */
+ schedule();
+
+ }
+ return 0;
+}
+
+static int add_process_element(struct cxl_context *ctx)
+{
+ int rc = 0;
+
+ mutex_lock(&ctx->afu->spa_mutex);
+ pr_devel("%s Adding pe: %i started\n", __func__, ctx->pe);
+ if (!(rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_ADD, CXL_PE_SOFTWARE_STATE_V)))
+ ctx->pe_inserted = true;
+ pr_devel("%s Adding pe: %i finished\n", __func__, ctx->pe);
+ mutex_unlock(&ctx->afu->spa_mutex);
+ return rc;
+}
+
+static int terminate_process_element(struct cxl_context *ctx)
+{
+ int rc = 0;
+
+ /* fast path terminate if it's already invalid */
+ if (!(ctx->elem->software_state & cpu_to_be32(CXL_PE_SOFTWARE_STATE_V)))
+ return rc;
+
+ mutex_lock(&ctx->afu->spa_mutex);
+ pr_devel("%s Terminate pe: %i started\n", __func__, ctx->pe);
+ rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_TERMINATE,
+ CXL_PE_SOFTWARE_STATE_V | CXL_PE_SOFTWARE_STATE_T);
+ ctx->elem->software_state = 0; /* Remove Valid bit */
+ pr_devel("%s Terminate pe: %i finished\n", __func__, ctx->pe);
+ mutex_unlock(&ctx->afu->spa_mutex);
+ return rc;
+}
+
+static int remove_process_element(struct cxl_context *ctx)
+{
+ int rc = 0;
+
+ mutex_lock(&ctx->afu->spa_mutex);
+ pr_devel("%s Remove pe: %i started\n", __func__, ctx->pe);
+ if (!(rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_REMOVE, 0)))
+ ctx->pe_inserted = false;
+ slb_invalid(ctx);
+ pr_devel("%s Remove pe: %i finished\n", __func__, ctx->pe);
+ mutex_unlock(&ctx->afu->spa_mutex);
+
+ return rc;
+}
+
+
+static void assign_psn_space(struct cxl_context *ctx)
+{
+ if (!ctx->afu->pp_size || ctx->master) {
+ ctx->psn_phys = ctx->afu->psn_phys;
+ ctx->psn_size = ctx->afu->adapter->ps_size;
+ } else {
+ ctx->psn_phys = ctx->afu->psn_phys +
+ (ctx->afu->pp_offset + ctx->afu->pp_size * ctx->pe);
+ ctx->psn_size = ctx->afu->pp_size;
+ }
+}
+
+static int activate_afu_directed(struct cxl_afu *afu)
+{
+ int rc;
+
+ dev_info(&afu->dev, "Activating AFU directed model\n");
+
+ if (alloc_spa(afu))
+ return -ENOMEM;
+
+ cxl_p1n_write(afu, CXL_PSL_SCNTL_An, CXL_PSL_SCNTL_An_PM_AFU);
+ cxl_p1n_write(afu, CXL_PSL_AMOR_An, 0xFFFFFFFFFFFFFFFFULL);
+ cxl_p1n_write(afu, CXL_PSL_ID_An, CXL_PSL_ID_An_F | CXL_PSL_ID_An_L);
+
+ afu->current_model = CXL_MODEL_DIRECTED;
+ afu->num_procs = afu->max_procs_virtualised;
+
+ if ((rc = cxl_chardev_m_afu_add(afu)))
+ return rc;
+
+ if ((rc = cxl_chardev_s_afu_add(afu)))
+ goto err;
+
+ return 0;
+err:
+ cxl_chardev_afu_remove(afu);
+ return rc;
+}
+
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+#define set_endian(sr) ((sr) |= CXL_PSL_SR_An_LE)
+#else
+#define set_endian(sr) ((sr) &= ~(CXL_PSL_SR_An_LE))
+#endif
+
+static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr)
+{
+
+ u64 sr, sstp0, sstp1;
+ int r, result;
+
+ assign_psn_space(ctx);
+
+ ctx->elem->ctxtime = 0; /* disable */
+ ctx->elem->lpid = cpu_to_be32(mfspr(SPRN_LPID));
+ ctx->elem->haurp = 0; /* disable */
+ ctx->elem->sdr = cpu_to_be64(mfspr(SPRN_SDR1));
+
+ sr = CXL_PSL_SR_An_SC;
+ if (ctx->master)
+ sr |= CXL_PSL_SR_An_MP;
+ if (mfspr(SPRN_LPCR) & LPCR_TC)
+ sr |= CXL_PSL_SR_An_TC;
+ /* HV=0, PR=1, R=1 for userspace
+ * For kernel contexts: this would need to change
+ */
+ sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R;
+ set_endian(sr);
+ sr &= ~(CXL_PSL_SR_An_HV);
+ if (!test_tsk_thread_flag(current, TIF_32BIT))
+ sr |= CXL_PSL_SR_An_SF;
+ ctx->elem->common.pid = cpu_to_be32(current->pid);
+ ctx->elem->common.tid = 0;
+ ctx->elem->sr = cpu_to_be64(sr);
+
+ ctx->elem->common.csrp = 0; /* disable */
+ ctx->elem->common.aurp0 = 0; /* disable */
+ ctx->elem->common.aurp1 = 0; /* disable */
+
+ if ((result = cxl_alloc_sst(ctx, &sstp0, &sstp1)))
+ return result;
+
+ cxl_prefault(ctx, wed);
+
+ ctx->elem->common.sstp0 = cpu_to_be64(sstp0);
+ ctx->elem->common.sstp1 = cpu_to_be64(sstp1);
+
+ for (r = 0; r < CXL_IRQ_RANGES; r++) {
+ ctx->elem->ivte_offsets[r] = cpu_to_be16(ctx->irqs.offset[r]);
+ ctx->elem->ivte_ranges[r] = cpu_to_be16(ctx->irqs.range[r]);
+ }
+
+ ctx->elem->common.amr = cpu_to_be64(amr);
+ ctx->elem->common.wed = cpu_to_be64(wed);
+
+ /* first guy needs to enable */
+ if ((result = afu_check_and_enable(ctx->afu)))
+ return result;
+
+ add_process_element(ctx);
+
+ return 0;
+}
+
+static int deactivate_afu_directed(struct cxl_afu *afu)
+{
+ dev_info(&afu->dev, "Deactivating AFU directed model\n");
+
+ afu->current_model = 0;
+ afu->num_procs = 0;
+
+ cxl_chardev_afu_remove(afu);
+
+ cxl_afu_reset(afu);
+ cxl_afu_disable(afu);
+ cxl_psl_purge(afu);
+
+ release_spa(afu);
+
+ return 0;
+}
+
+static int activate_dedicated_process(struct cxl_afu *afu)
+{
+ dev_info(&afu->dev, "Activating dedicated process model\n");
+
+ cxl_p1n_write(afu, CXL_PSL_SCNTL_An, CXL_PSL_SCNTL_An_PM_Process);
+
+ cxl_p1n_write(afu, CXL_PSL_CtxTime_An, 0); /* disable */
+ cxl_p1n_write(afu, CXL_PSL_SPAP_An, 0); /* disable */
+ cxl_p1n_write(afu, CXL_PSL_AMOR_An, 0xFFFFFFFFFFFFFFFFULL);
+ cxl_p1n_write(afu, CXL_PSL_LPID_An, mfspr(SPRN_LPID));
+ cxl_p1n_write(afu, CXL_HAURP_An, 0); /* disable */
+ cxl_p1n_write(afu, CXL_PSL_SDR_An, mfspr(SPRN_SDR1));
+
+ cxl_p2n_write(afu, CXL_CSRP_An, 0); /* disable */
+ cxl_p2n_write(afu, CXL_AURP0_An, 0); /* disable */
+ cxl_p2n_write(afu, CXL_AURP1_An, 0); /* disable */
+
+ afu->current_model = CXL_MODEL_DEDICATED;
+ afu->num_procs = 1;
+
+ return cxl_chardev_m_afu_add(afu);
+}
+
+static int attach_dedicated(struct cxl_context *ctx, u64 wed, u64 amr)
+{
+ struct cxl_afu *afu = ctx->afu;
+ u64 sr, sstp0, sstp1;
+ int rc;
+
+ sr = CXL_PSL_SR_An_SC;
+ set_endian(sr);
+ if (ctx->master)
+ sr |= CXL_PSL_SR_An_MP;
+ if (mfspr(SPRN_LPCR) & LPCR_TC)
+ sr |= CXL_PSL_SR_An_TC;
+ sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R;
+ if (!test_tsk_thread_flag(current, TIF_32BIT))
+ sr |= CXL_PSL_SR_An_SF;
+ cxl_p2n_write(afu, CXL_PSL_PID_TID_An, (u64)current->pid << 32);
+ cxl_p1n_write(afu, CXL_PSL_SR_An, sr);
+
+ if ((rc = cxl_alloc_sst(ctx, &sstp0, &sstp1)))
+ return rc;
+
+ if ((rc = cxl_write_sstp(afu, sstp0, sstp1)))
+ return rc;
+
+ cxl_prefault(ctx, wed);
+
+ cxl_p1n_write(afu, CXL_PSL_IVTE_Offset_An,
+ (((u64)ctx->irqs.offset[0] & 0xffff) << 48) |
+ (((u64)ctx->irqs.offset[1] & 0xffff) << 32) |
+ (((u64)ctx->irqs.offset[2] & 0xffff) << 16) |
+ ((u64)ctx->irqs.offset[3] & 0xffff));
+ cxl_p1n_write(afu, CXL_PSL_IVTE_Limit_An, (u64)
+ (((u64)ctx->irqs.range[0] & 0xffff) << 48) |
+ (((u64)ctx->irqs.range[1] & 0xffff) << 32) |
+ (((u64)ctx->irqs.range[2] & 0xffff) << 16) |
+ ((u64)ctx->irqs.range[3] & 0xffff));
+
+ cxl_p2n_write(afu, CXL_PSL_AMR_An, amr);
+
+ /* master only context for dedicated */
+ assign_psn_space(ctx);
+
+ if ((rc = cxl_afu_reset(afu)))
+ return rc;
+
+ cxl_p2n_write(afu, CXL_PSL_WED_An, wed);
+
+ return afu_enable(afu);
+}
+
+static int deactivate_dedicated_process(struct cxl_afu *afu)
+{
+ dev_info(&afu->dev, "Deactivating dedicated process model\n");
+
+ afu->current_model = 0;
+ afu->num_procs = 0;
+
+ cxl_chardev_afu_remove(afu);
+
+ return 0;
+}
+
+int _cxl_afu_deactivate_model(struct cxl_afu *afu, int model)
+{
+ if (model == CXL_MODEL_DIRECTED)
+ return deactivate_afu_directed(afu);
+ if (model == CXL_MODEL_DEDICATED)
+ return deactivate_dedicated_process(afu);
+ return 0;
+}
+
+int cxl_afu_deactivate_model(struct cxl_afu *afu)
+{
+ return _cxl_afu_deactivate_model(afu, afu->current_model);
+}
+
+int cxl_afu_activate_model(struct cxl_afu *afu, int model)
+{
+ if (!model)
+ return 0;
+ if (!(model & afu->models_supported))
+ return -EINVAL;
+
+ if (model == CXL_MODEL_DIRECTED)
+ return activate_afu_directed(afu);
+ if (model == CXL_MODEL_DEDICATED)
+ return activate_dedicated_process(afu);
+
+ return -EINVAL;
+}
+
+int cxl_attach_process(struct cxl_context *ctx, bool kernel, u64 wed, u64 amr)
+{
+ ctx->kernel = kernel;
+ if (ctx->afu->current_model == CXL_MODEL_DIRECTED)
+ return attach_afu_directed(ctx, wed, amr);
+
+ if (ctx->afu->current_model == CXL_MODEL_DEDICATED)
+ return attach_dedicated(ctx, wed, amr);
+
+ return -EINVAL;
+}
+
+static inline int detach_process_native_dedicated(struct cxl_context *ctx)
+{
+ cxl_afu_reset(ctx->afu);
+ cxl_afu_disable(ctx->afu);
+ cxl_psl_purge(ctx->afu);
+ return 0;
+}
+
+/* TODO: handle case when this is called inside a rcu_read_lock() which may
+ * happen when we unbind the driver (ie. cxl_context_detach_all()) . Terminate
+ * & remove use a mutex lock and schedule which will not good with lock held.
+ * May need to write do_process_element_cmd() that handles outstanding page
+ * faults synchronously.
+ */
+static inline int detach_process_native_afu_directed(struct cxl_context *ctx)
+{
+ if (!ctx->pe_inserted)
+ return 0;
+ if (terminate_process_element(ctx))
+ return -1;
+ if (remove_process_element(ctx))
+ return -1;
+
+ return 0;
+}
+
+int cxl_detach_process(struct cxl_context *ctx)
+{
+ if (ctx->afu->current_model == CXL_MODEL_DEDICATED)
+ return detach_process_native_dedicated(ctx);
+
+ return detach_process_native_afu_directed(ctx);
+}
+
+int cxl_get_irq(struct cxl_context *ctx, struct cxl_irq_info *info)
+{
+ u64 pidtid;
+
+ info->dsisr = cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An);
+ info->dar = cxl_p2n_read(ctx->afu, CXL_PSL_DAR_An);
+ info->dsr = cxl_p2n_read(ctx->afu, CXL_PSL_DSR_An);
+ pidtid = cxl_p2n_read(ctx->afu, CXL_PSL_PID_TID_An);
+ info->pid = pidtid >> 32;
+ info->tid = pidtid & 0xffffffff;
+ info->afu_err = cxl_p2n_read(ctx->afu, CXL_AFU_ERR_An);
+ info->errstat = cxl_p2n_read(ctx->afu, CXL_PSL_ErrStat_An);
+
+ return 0;
+}
+
+static void recover_psl_err(struct cxl_afu *afu, u64 errstat)
+{
+ u64 dsisr;
+
+ pr_devel("RECOVERING FROM PSL ERROR... (0x%.16llx)\n", errstat);
+
+ /* Clear PSL_DSISR[PE] */
+ dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
+ cxl_p2n_write(afu, CXL_PSL_DSISR_An, dsisr & ~CXL_PSL_DSISR_An_PE);
+
+ /* Write 1s to clear error status bits */
+ cxl_p2n_write(afu, CXL_PSL_ErrStat_An, errstat);
+}
+
+int cxl_ack_irq(struct cxl_context *ctx, u64 tfc, u64 psl_reset_mask)
+{
+ if (tfc)
+ cxl_p2n_write(ctx->afu, CXL_PSL_TFC_An, tfc);
+ if (psl_reset_mask)
+ recover_psl_err(ctx->afu, psl_reset_mask);
+
+ return 0;
+}
+
+int cxl_check_error(struct cxl_afu *afu)
+{
+ return (cxl_p1n_read(afu, CXL_PSL_SCNTL_An) == ~0ULL);
+}
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
new file mode 100644
index 0000000..eff4953
--- /dev/null
+++ b/drivers/misc/cxl/pci.c
@@ -0,0 +1,994 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/pci_regs.h>
+#include <linux/pci_ids.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+#include <linux/pci.h>
+#include <linux/of.h>
+#include <linux/delay.h>
+#include <asm/opal.h>
+#include <asm/msi_bitmap.h>
+#include <asm/pci-bridge.h> /* for struct pci_controller */
+#include <asm/pnv-pci.h>
+
+#include "cxl.h"
+
+
+#define CXL_PCI_VSEC_ID 0x1280
+#define CXL_VSEC_MIN_SIZE 0x80
+
+#define CXL_READ_VSEC_LENGTH(dev, vsec, dest) \
+ { \
+ pci_read_config_word(dev, vsec + 0x6, dest); \
+ *dest >>= 4; \
+ }
+#define CXL_READ_VSEC_NAFUS(dev, vsec, dest) \
+ pci_read_config_byte(dev, vsec + 0x8, dest)
+
+#define CXL_READ_VSEC_STATUS(dev, vsec, dest) \
+ pci_read_config_byte(dev, vsec + 0x9, dest)
+#define CXL_STATUS_SECOND_PORT 0x80
+#define CXL_STATUS_MSI_X_FULL 0x40
+#define CXL_STATUS_MSI_X_SINGLE 0x20
+#define CXL_STATUS_FLASH_RW 0x08
+#define CXL_STATUS_FLASH_RO 0x04
+#define CXL_STATUS_LOADABLE_AFU 0x02
+#define CXL_STATUS_LOADABLE_PSL 0x01
+/* If we see these features we won't try to use the card */
+#define CXL_UNSUPPORTED_FEATURES \
+ (CXL_STATUS_MSI_X_FULL | CXL_STATUS_MSI_X_SINGLE)
+
+#define CXL_READ_VSEC_MODE_CONTROL(dev, vsec, dest) \
+ pci_read_config_byte(dev, vsec + 0xa, dest)
+#define CXL_WRITE_VSEC_MODE_CONTROL(dev, vsec, val) \
+ pci_write_config_byte(dev, vsec + 0xa, val)
+#define CXL_VSEC_PROTOCOL_MASK 0xe0
+#define CXL_VSEC_PROTOCOL_1024TB 0x80
+#define CXL_VSEC_PROTOCOL_512TB 0x40
+#define CXL_VSEC_PROTOCOL_256TB 0x20 /* Power 8 uses this */
+#define CXL_VSEC_PROTOCOL_ENABLE 0x01
+
+#define CXL_READ_VSEC_PSL_REVISION(dev, vsec, dest) \
+ pci_read_config_word(dev, vsec + 0xc, dest)
+#define CXL_READ_VSEC_CAIA_MINOR(dev, vsec, dest) \
+ pci_read_config_byte(dev, vsec + 0xe, dest)
+#define CXL_READ_VSEC_CAIA_MAJOR(dev, vsec, dest) \
+ pci_read_config_byte(dev, vsec + 0xf, dest)
+#define CXL_READ_VSEC_BASE_IMAGE(dev, vsec, dest) \
+ pci_read_config_word(dev, vsec + 0x10, dest)
+
+#define CXL_READ_VSEC_IMAGE_STATE(dev, vsec, dest) \
+ pci_read_config_byte(dev, vsec + 0x13, dest)
+#define CXL_WRITE_VSEC_IMAGE_STATE(dev, vsec, val) \
+ pci_write_config_byte(dev, vsec + 0x13, val)
+#define CXL_VSEC_USER_IMAGE_LOADED 0x80 /* RO */
+#define CXL_VSEC_PERST_LOADS_IMAGE 0x20 /* RW */
+#define CXL_VSEC_PERST_SELECT_USER 0x10 /* RW */
+
+#define CXL_READ_VSEC_AFU_DESC_OFF(dev, vsec, dest) \
+ pci_read_config_dword(dev, vsec + 0x20, dest)
+#define CXL_READ_VSEC_AFU_DESC_SIZE(dev, vsec, dest) \
+ pci_read_config_dword(dev, vsec + 0x24, dest)
+#define CXL_READ_VSEC_PS_OFF(dev, vsec, dest) \
+ pci_read_config_dword(dev, vsec + 0x28, dest)
+#define CXL_READ_VSEC_PS_SIZE(dev, vsec, dest) \
+ pci_read_config_dword(dev, vsec + 0x2c, dest)
+
+
+/* This works a little different than the p1/p2 register accesses to make it
+ * easier to pull out individual fields */
+#define AFUD_READ(afu, off) _cxl_reg_read(afu->afu_desc_mmio + off)
+#define EXTRACT_PPC_BIT(val, bit) (!!(val & PPC_BIT(bit)))
+#define EXTRACT_PPC_BITS(val, bs, be) ((val & PPC_BITMASK(bs, be)) >> PPC_BITLSHIFT(be))
+
+#define AFUD_READ_INFO(afu) AFUD_READ(afu, 0x0)
+#define AFUD_NUM_INTS_PER_PROC(val) EXTRACT_PPC_BITS(val, 0, 15)
+#define AFUD_NUM_PROCS(val) EXTRACT_PPC_BITS(val, 16, 31)
+#define AFUD_NUM_CRS(val) EXTRACT_PPC_BITS(val, 32, 47)
+#define AFUD_MULTIMODEL(val) EXTRACT_PPC_BIT(val, 48)
+#define AFUD_PUSH_BLOCK_TRANSFER(val) EXTRACT_PPC_BIT(val, 55)
+#define AFUD_DEDICATED_PROCESS(val) EXTRACT_PPC_BIT(val, 59)
+#define AFUD_AFU_DIRECTED(val) EXTRACT_PPC_BIT(val, 61)
+#define AFUD_TIME_SLICED(val) EXTRACT_PPC_BIT(val, 63)
+#define AFUD_READ_CR(afu) AFUD_READ(afu, 0x20)
+#define AFUD_CR_LEN(val) EXTRACT_PPC_BITS(val, 8, 63)
+#define AFUD_READ_CR_OFF(afu) AFUD_READ(afu, 0x28)
+#define AFUD_READ_PPPSA(afu) AFUD_READ(afu, 0x30)
+#define AFUD_PPPSA_PP(val) EXTRACT_PPC_BIT(val, 6)
+#define AFUD_PPPSA_PSA(val) EXTRACT_PPC_BIT(val, 7)
+#define AFUD_PPPSA_LEN(val) EXTRACT_PPC_BITS(val, 8, 63)
+#define AFUD_READ_PPPSA_OFF(afu) AFUD_READ(afu, 0x38)
+#define AFUD_READ_EB(afu) AFUD_READ(afu, 0x40)
+#define AFUD_EB_LEN(val) EXTRACT_PPC_BITS(val, 8, 63)
+#define AFUD_READ_EB_OFF(afu) AFUD_READ(afu, 0x48)
+
+static DEFINE_PCI_DEVICE_TABLE(cxl_pci_tbl) = {
+ { PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x0477), },
+ { PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x044b), },
+ { PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x04cf), },
+ { PCI_DEVICE_CLASS(0x120000, ~0), },
+
+ { }
+};
+MODULE_DEVICE_TABLE(pci, cxl_pci_tbl);
+
+
+/* Mostly using these wrappers to avoid confusion:
+ * priv 1 is BAR2, while priv 2 is BAR0 */
+static inline resource_size_t p1_base(struct pci_dev *dev)
+{
+ return pci_resource_start(dev, 2);
+}
+
+static inline resource_size_t p1_size(struct pci_dev *dev)
+{
+ return pci_resource_len(dev, 2);
+}
+
+static inline resource_size_t p2_base(struct pci_dev *dev)
+{
+ return pci_resource_start(dev, 0);
+}
+
+static inline resource_size_t p2_size(struct pci_dev *dev)
+{
+ return pci_resource_len(dev, 0);
+}
+
+static int find_cxl_vsec(struct pci_dev *dev)
+{
+ int vsec = 0;
+ u16 val;
+
+ while ((vsec = pci_find_next_ext_capability(dev, vsec, PCI_EXT_CAP_ID_VNDR))) {
+ pci_read_config_word(dev, vsec + 0x4, &val);
+ if (val == CXL_PCI_VSEC_ID)
+ return vsec;
+ }
+ return 0;
+
+}
+
+static void dump_cxl_config_space(struct pci_dev *dev)
+{
+ int vsec;
+ u32 val;
+
+ dev_info(&dev->dev, "dump_cxl_config_space\n");
+
+ pci_read_config_dword(dev, PCI_BASE_ADDRESS_0, &val);
+ dev_info(&dev->dev, "BAR0: %#.8x\n", val);
+ pci_read_config_dword(dev, PCI_BASE_ADDRESS_1, &val);
+ dev_info(&dev->dev, "BAR1: %#.8x\n", val);
+ pci_read_config_dword(dev, PCI_BASE_ADDRESS_2, &val);
+ dev_info(&dev->dev, "BAR2: %#.8x\n", val);
+ pci_read_config_dword(dev, PCI_BASE_ADDRESS_3, &val);
+ dev_info(&dev->dev, "BAR3: %#.8x\n", val);
+ pci_read_config_dword(dev, PCI_BASE_ADDRESS_4, &val);
+ dev_info(&dev->dev, "BAR4: %#.8x\n", val);
+ pci_read_config_dword(dev, PCI_BASE_ADDRESS_5, &val);
+ dev_info(&dev->dev, "BAR5: %#.8x\n", val);
+
+ dev_info(&dev->dev, "p1 regs: %#llx, len: %#llx\n",
+ p1_base(dev), p1_size(dev));
+ dev_info(&dev->dev, "p2 regs: %#llx, len: %#llx\n",
+ p1_base(dev), p2_size(dev));
+ dev_info(&dev->dev, "BAR 4/5: %#llx, len: %#llx\n",
+ pci_resource_start(dev, 4), pci_resource_len(dev, 4));
+
+ if (!(vsec = find_cxl_vsec(dev)))
+ return;
+
+#define show_reg(name, what) \
+ dev_info(&dev->dev, "cxl vsec: %30s: %#x\n", name, what)
+
+ pci_read_config_dword(dev, vsec + 0x0, &val);
+ show_reg("Cap ID", (val >> 0) & 0xffff);
+ show_reg("Cap Ver", (val >> 16) & 0xf);
+ show_reg("Next Cap Ptr", (val >> 20) & 0xfff);
+ pci_read_config_dword(dev, vsec + 0x4, &val);
+ show_reg("VSEC ID", (val >> 0) & 0xffff);
+ show_reg("VSEC Rev", (val >> 16) & 0xf);
+ show_reg("VSEC Length", (val >> 20) & 0xfff);
+ pci_read_config_dword(dev, vsec + 0x8, &val);
+ show_reg("Num AFUs", (val >> 0) & 0xff);
+ show_reg("Status", (val >> 8) & 0xff);
+ show_reg("Mode Control", (val >> 16) & 0xff);
+ show_reg("Reserved", (val >> 24) & 0xff);
+ pci_read_config_dword(dev, vsec + 0xc, &val);
+ show_reg("PSL Rev", (val >> 0) & 0xffff);
+ show_reg("CAIA Ver", (val >> 16) & 0xffff);
+ pci_read_config_dword(dev, vsec + 0x10, &val);
+ show_reg("Base Image Rev", (val >> 0) & 0xffff);
+ show_reg("Reserved", (val >> 16) & 0x0fff);
+ show_reg("Image Control", (val >> 28) & 0x3);
+ show_reg("Reserved", (val >> 30) & 0x1);
+ show_reg("Image Loaded", (val >> 31) & 0x1);
+
+ pci_read_config_dword(dev, vsec + 0x14, &val);
+ show_reg("Reserved", val);
+ pci_read_config_dword(dev, vsec + 0x18, &val);
+ show_reg("Reserved", val);
+ pci_read_config_dword(dev, vsec + 0x1c, &val);
+ show_reg("Reserved", val);
+
+ pci_read_config_dword(dev, vsec + 0x20, &val);
+ show_reg("AFU Descriptor Offset", val);
+ pci_read_config_dword(dev, vsec + 0x24, &val);
+ show_reg("AFU Descriptor Size", val);
+ pci_read_config_dword(dev, vsec + 0x28, &val);
+ show_reg("Problem State Offset", val);
+ pci_read_config_dword(dev, vsec + 0x2c, &val);
+ show_reg("Problem State Size", val);
+
+ pci_read_config_dword(dev, vsec + 0x30, &val);
+ show_reg("Reserved", val);
+ pci_read_config_dword(dev, vsec + 0x34, &val);
+ show_reg("Reserved", val);
+ pci_read_config_dword(dev, vsec + 0x38, &val);
+ show_reg("Reserved", val);
+ pci_read_config_dword(dev, vsec + 0x3c, &val);
+ show_reg("Reserved", val);
+
+ pci_read_config_dword(dev, vsec + 0x40, &val);
+ show_reg("PSL Programming Port", val);
+ pci_read_config_dword(dev, vsec + 0x44, &val);
+ show_reg("PSL Programming Control", val);
+
+ pci_read_config_dword(dev, vsec + 0x48, &val);
+ show_reg("Reserved", val);
+ pci_read_config_dword(dev, vsec + 0x4c, &val);
+ show_reg("Reserved", val);
+
+ pci_read_config_dword(dev, vsec + 0x50, &val);
+ show_reg("Flash Address Register", val);
+ pci_read_config_dword(dev, vsec + 0x54, &val);
+ show_reg("Flash Size Register", val);
+ pci_read_config_dword(dev, vsec + 0x58, &val);
+ show_reg("Flash Status/Control Register", val);
+ pci_read_config_dword(dev, vsec + 0x58, &val);
+ show_reg("Flash Data Port", val);
+
+#undef show_reg
+}
+
+static void dump_afu_descriptor(struct cxl_afu *afu)
+{
+ u64 val;
+
+#define show_reg(name, what) \
+ dev_info(&afu->dev, "afu desc: %30s: %#llx\n", name, what)
+
+ val = AFUD_READ_INFO(afu);
+ show_reg("num_ints_per_process", AFUD_NUM_INTS_PER_PROC(val));
+ show_reg("num_of_processes", AFUD_NUM_PROCS(val));
+ show_reg("num_of_afu_CRs", AFUD_NUM_CRS(val));
+ show_reg("req_prog_model", val & 0xffffULL);
+
+ val = AFUD_READ(afu, 0x8);
+ show_reg("Reserved", val);
+ val = AFUD_READ(afu, 0x10);
+ show_reg("Reserved", val);
+ val = AFUD_READ(afu, 0x18);
+ show_reg("Reserved", val);
+
+ val = AFUD_READ_CR(afu);
+ show_reg("Reserved", (val >> (63-7)) & 0xff);
+ show_reg("AFU_CR_len", AFUD_CR_LEN(val));
+
+ val = AFUD_READ_CR_OFF(afu);
+ show_reg("AFU_CR_offset", val);
+
+ val = AFUD_READ_PPPSA(afu);
+ show_reg("PerProcessPSA_control", (val >> (63-7)) & 0xff);
+ show_reg("PerProcessPSA Length", AFUD_PPPSA_LEN(val));
+
+ val = AFUD_READ_PPPSA_OFF(afu);
+ show_reg("PerProcessPSA_offset", val);
+
+ val = AFUD_READ_EB(afu);
+ show_reg("Reserved", (val >> (63-7)) & 0xff);
+ show_reg("AFU_EB_len", AFUD_EB_LEN(val));
+
+ val = AFUD_READ_EB_OFF(afu);
+ show_reg("AFU_EB_offset", val);
+
+#undef show_reg
+}
+
+extern struct device_node *pnv_pci_to_phb_node(struct pci_dev *dev);
+
+static int init_implementation_adapter_regs(struct cxl *adapter, struct pci_dev *dev)
+{
+ struct device_node *np;
+ const __be32 *prop;
+ u64 psl_dsnctl;
+ u64 chipid;
+
+ if (!(np = pnv_pci_to_phb_node(dev)))
+ return -ENODEV;
+
+ while (np && !(prop = of_get_property(np, "ibm,chip-id", NULL)))
+ np = of_get_next_parent(np);
+ if (!np)
+ return -ENODEV;
+ chipid = be32_to_cpup(prop);
+ of_node_put(np);
+
+ /* Tell PSL where to route data to */
+ psl_dsnctl = 0x02E8900002000000ULL | (chipid << (63-5));
+ cxl_p1_write(adapter, CXL_PSL_DSNDCTL, psl_dsnctl);
+ cxl_p1_write(adapter, CXL_PSL_RESLCKTO, 0x20000000200ULL);
+ /* snoop write mask */
+ cxl_p1_write(adapter, CXL_PSL_SNWRALLOC, 0x00000000FFFFFFFFULL);
+ /* set fir_accum */
+ cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, 0x0800000000000000ULL);
+ /* for debugging with trace arrays */
+ cxl_p1_write(adapter, CXL_PSL_TRACE, 0x0000FF7C00000000ULL);
+
+ return 0;
+}
+
+static int init_implementation_afu_regs(struct cxl_afu *afu)
+{
+ /* read/write masks for this slice */
+ cxl_p1n_write(afu, CXL_PSL_APCALLOC_A, 0xFFFFFFFEFEFEFEFEULL);
+ /* APC read/write masks for this slice */
+ cxl_p1n_write(afu, CXL_PSL_COALLOC_A, 0xFF000000FEFEFEFEULL);
+ /* for debugging with trace arrays */
+ cxl_p1n_write(afu, CXL_PSL_SLICE_TRACE, 0x0000FFFF00000000ULL);
+ cxl_p1n_write(afu, CXL_PSL_RXCTL_A, 0xF000000000000000ULL);
+
+ return 0;
+}
+
+int cxl_setup_irq(struct cxl *adapter, unsigned int hwirq,
+ unsigned int virq)
+{
+ struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
+
+ return pnv_cxl_ioda_msi_setup(dev, hwirq, virq);
+}
+
+int cxl_alloc_one_irq(struct cxl *adapter)
+{
+ struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
+
+ return pnv_cxl_alloc_hwirqs(dev, 1);
+}
+
+void cxl_release_one_irq(struct cxl *adapter, int hwirq)
+{
+ struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
+
+ return pnv_cxl_release_hwirqs(dev, hwirq, 1);
+}
+
+int cxl_alloc_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter, unsigned int num)
+{
+ struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
+
+ return pnv_cxl_alloc_hwirq_ranges(irqs, dev, num);
+}
+
+void cxl_release_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter)
+{
+ struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
+
+ pnv_cxl_release_hwirq_ranges(irqs, dev);
+}
+
+static int setup_cxl_bars(struct pci_dev *dev)
+{
+ /* Safety check in case we get backported to < 3.17 without M64 */
+ if ((p1_base(dev) < 0x100000000ULL) ||
+ (p2_base(dev) < 0x100000000ULL)) {
+ dev_err(&dev->dev, "ABORTING: M32 BAR assignment incompatible with CXL\n");
+ return -ENODEV;
+ }
+
+ /* BAR 4/5 has a special meaning for CXL and must be programmed with a
+ * special value corresponding to the CXL protocol address range.
+ * For POWER 8 that means bits 48:49 must be set to 10 */
+ pci_write_config_dword(dev, PCI_BASE_ADDRESS_4, 0x00000000);
+ pci_write_config_dword(dev, PCI_BASE_ADDRESS_5, 0x00020000);
+
+ return 0;
+}
+
+/*
+ * pciex node: ibm,opal-m64-window = <0x3d058 0x0 0x3d058 0x0 0x8 0x0>;
+ */
+
+static int switch_card_to_cxl(struct pci_dev *dev)
+{
+ int vsec;
+ u8 val;
+ int rc;
+
+ dev_info(&dev->dev, "switch card to CXL\n");
+
+ if (!(vsec = find_cxl_vsec(dev))) {
+ dev_err(&dev->dev, "ABORTING: CXL VSEC not found!\n");
+ return -ENODEV;
+ }
+
+ if ((rc = CXL_READ_VSEC_MODE_CONTROL(dev, vsec, &val))) {
+ dev_err(&dev->dev, "failed to read current mode control: %i", rc);
+ return rc;
+ }
+ val &= ~CXL_VSEC_PROTOCOL_MASK;
+ val |= CXL_VSEC_PROTOCOL_256TB | CXL_VSEC_PROTOCOL_ENABLE;
+ if ((rc = CXL_WRITE_VSEC_MODE_CONTROL(dev, vsec, val))) {
+ dev_err(&dev->dev, "failed to enable CXL protocol: %i", rc);
+ return rc;
+ }
+ /* The CAIA spec (v0.12 11.6 Bi-modal Device Support) states
+ * we must wait 100ms after this mode switch before touching
+ * PCIe config space.
+ */
+ msleep(100);
+
+ return 0;
+}
+
+static int cxl_map_slice_regs(struct cxl_afu *afu, struct cxl *adapter, struct pci_dev *dev)
+{
+ u64 p1n_base, p2n_base, afu_desc;
+ const u64 p1n_size = 0x100;
+ const u64 p2n_size = 0x1000;
+
+ p1n_base = p1_base(dev) + 0x10000 + (afu->slice * p1n_size);
+ p2n_base = p2_base(dev) + (afu->slice * p2n_size);
+ afu->psn_phys = p2_base(dev) + (adapter->ps_off + (afu->slice * adapter->ps_size));
+ afu_desc = p2_base(dev) + adapter->afu_desc_off + (afu->slice * adapter->afu_desc_size);
+
+ if (!(afu->p1n_mmio = ioremap(p1n_base, p1n_size)))
+ goto err;
+ if (!(afu->p2n_mmio = ioremap(p2n_base, p2n_size)))
+ goto err1;
+ if (afu_desc) {
+ if (!(afu->afu_desc_mmio = ioremap(afu_desc, adapter->afu_desc_size)))
+ goto err2;
+ }
+
+ return 0;
+err2:
+ iounmap(afu->p2n_mmio);
+err1:
+ iounmap(afu->p1n_mmio);
+err:
+ dev_err(&afu->dev, "Error mapping AFU MMIO regions\n");
+ return -ENOMEM;
+}
+
+static void cxl_unmap_slice_regs(struct cxl_afu *afu)
+{
+ if (afu->p1n_mmio)
+ iounmap(afu->p2n_mmio);
+ if (afu->p1n_mmio)
+ iounmap(afu->p1n_mmio);
+}
+
+static void cxl_release_afu(struct device *dev)
+{
+ struct cxl_afu *afu = to_cxl_afu(dev);
+
+ pr_devel("cxl_release_afu\n");
+
+ kfree(afu);
+}
+
+static struct cxl_afu *cxl_alloc_afu(struct cxl *adapter, int slice)
+{
+ struct cxl_afu *afu;
+
+ if (!(afu = kzalloc(sizeof(struct cxl_afu), GFP_KERNEL)))
+ return NULL;
+
+ afu->adapter = adapter;
+ afu->dev.parent = &adapter->dev;
+ afu->dev.release = cxl_release_afu;
+ afu->slice = slice;
+ idr_init(&afu->contexts_idr);
+ spin_lock_init(&afu->contexts_lock);
+ spin_lock_init(&afu->afu_cntl_lock);
+ mutex_init(&afu->spa_mutex);
+
+ afu->prefault_mode = CXL_PREFAULT_NONE;
+ afu->irqs_max = afu->adapter->user_irqs;
+
+ return afu;
+}
+
+/* Expects AFU struct to have recently been zeroed out */
+static int cxl_read_afu_descriptor(struct cxl_afu *afu)
+{
+ u64 val;
+
+ val = AFUD_READ_INFO(afu);
+ afu->pp_irqs = AFUD_NUM_INTS_PER_PROC(val);
+ afu->max_procs_virtualised = AFUD_NUM_PROCS(val);
+
+ if (AFUD_AFU_DIRECTED(val))
+ afu->models_supported |= CXL_MODEL_DIRECTED;
+ if (AFUD_DEDICATED_PROCESS(val))
+ afu->models_supported |= CXL_MODEL_DEDICATED;
+ if (AFUD_TIME_SLICED(val))
+ afu->models_supported |= CXL_MODEL_TIME_SLICED;
+
+ val = AFUD_READ_PPPSA(afu);
+ afu->pp_size = AFUD_PPPSA_LEN(val) * 4096;
+ afu->psa = AFUD_PPPSA_PSA(val);
+ if ((afu->pp_psa = AFUD_PPPSA_PP(val)))
+ afu->pp_offset = AFUD_READ_PPPSA_OFF(afu);
+
+ return 0;
+}
+
+static int cxl_afu_descriptor_looks_ok(struct cxl_afu *afu)
+{
+ if (afu->psa && afu->adapter->ps_size <
+ (afu->pp_offset + afu->pp_size*afu->max_procs_virtualised)) {
+ dev_err(&afu->dev, "per-process PSA can't fit inside the PSA!\n");
+ return -ENODEV;
+ }
+
+ if (afu->pp_psa && (afu->pp_size < PAGE_SIZE))
+ dev_warn(&afu->dev, "AFU uses < PAGE_SIZE per-process PSA!");
+
+ return 0;
+}
+
+static int sanitise_afu_regs(struct cxl_afu *afu)
+{
+ u64 reg;
+
+ /* Clear out any regs that contain either an IVTE or address or may be
+ * waiting on an acknowledgement to try to be a bit safer as we bring
+ * it online */
+ reg = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
+ if ((reg & CXL_AFU_Cntl_An_ES_MASK) != CXL_AFU_Cntl_An_ES_Disabled) {
+ dev_warn(&afu->dev, "WARNING: AFU was not disabled: %#.16llx\n", reg);
+ if (cxl_afu_reset(afu))
+ return -EIO;
+ if (cxl_afu_disable(afu))
+ return -EIO;
+ if (cxl_psl_purge(afu))
+ return -EIO;
+ }
+ cxl_p1n_write(afu, CXL_PSL_SPAP_An, 0x0000000000000000);
+ cxl_p1n_write(afu, CXL_PSL_IVTE_Limit_An, 0x0000000000000000);
+ cxl_p1n_write(afu, CXL_PSL_IVTE_Offset_An, 0x0000000000000000);
+ cxl_p1n_write(afu, CXL_PSL_AMBAR_An, 0x0000000000000000);
+ cxl_p1n_write(afu, CXL_PSL_SPOffset_An, 0x0000000000000000);
+ cxl_p1n_write(afu, CXL_HAURP_An, 0x0000000000000000);
+ cxl_p2n_write(afu, CXL_CSRP_An, 0x0000000000000000);
+ cxl_p2n_write(afu, CXL_AURP1_An, 0x0000000000000000);
+ cxl_p2n_write(afu, CXL_AURP0_An, 0x0000000000000000);
+ cxl_p2n_write(afu, CXL_SSTP1_An, 0x0000000000000000);
+ cxl_p2n_write(afu, CXL_SSTP0_An, 0x0000000000000000);
+ reg = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
+ if (reg) {
+ dev_warn(&afu->dev, "AFU had pending DSISR: %#.16llx\n", reg);
+ if (reg & CXL_PSL_DSISR_TRANS)
+ cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_AE);
+ else
+ cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_A);
+ }
+ reg = cxl_p1n_read(afu, CXL_PSL_SERR_An);
+ if (reg) {
+ if (reg & ~0xffff)
+ dev_warn(&afu->dev, "AFU had pending SERR: %#.16llx\n", reg);
+ cxl_p1n_write(afu, CXL_PSL_SERR_An, reg & ~0xffff);
+ }
+ reg = cxl_p2n_read(afu, CXL_PSL_ErrStat_An);
+ if (reg) {
+ dev_warn(&afu->dev, "AFU had pending error status: %#.16llx\n", reg);
+ cxl_p2n_write(afu, CXL_PSL_ErrStat_An, reg);
+ }
+
+ return 0;
+}
+
+static int cxl_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
+{
+ struct cxl_afu *afu;
+ bool free = true;
+ int rc;
+
+ if (!(afu = cxl_alloc_afu(adapter, slice)))
+ return -ENOMEM;
+
+ if ((rc = dev_set_name(&afu->dev, "afu%i.%i", adapter->adapter_num, slice)))
+ goto err1;
+
+ if ((rc = cxl_map_slice_regs(afu, adapter, dev)))
+ goto err1;
+
+ if ((rc = sanitise_afu_regs(afu)))
+ goto err2;
+
+ /* We need to reset the AFU before we can read the AFU descriptor */
+ if ((rc = cxl_afu_reset(afu)))
+ goto err2;
+
+ if (cxl_verbose)
+ dump_afu_descriptor(afu);
+
+ if ((rc = cxl_read_afu_descriptor(afu)))
+ goto err2;
+
+ if ((rc = cxl_afu_descriptor_looks_ok(afu)))
+ goto err2;
+
+ if ((rc = init_implementation_afu_regs(afu)))
+ goto err2;
+
+ if ((rc = cxl_register_serr_irq(afu)))
+ goto err2;
+
+ if ((rc = cxl_register_psl_irq(afu)))
+ goto err3;
+
+ /* Don't care if this fails */
+ cxl_debugfs_afu_add(afu);
+
+ /* After we call this function we must not free the afu directly, even
+ * if it returns an error! */
+ if ((rc = cxl_register_afu(afu)))
+ goto err_put1;
+
+ if ((rc = cxl_sysfs_afu_add(afu)))
+ goto err_put1;
+
+
+ if ((rc = cxl_afu_select_best_model(afu)))
+ goto err_put2;
+
+ adapter->afu[afu->slice] = afu;
+
+ return 0;
+
+err_put2:
+ cxl_sysfs_afu_remove(afu);
+err_put1:
+ device_unregister(&afu->dev);
+ free = false;
+ cxl_debugfs_afu_remove(afu);
+ cxl_release_psl_irq(afu);
+err3:
+ cxl_release_serr_irq(afu);
+err2:
+ cxl_unmap_slice_regs(afu);
+err1:
+ if (free)
+ kfree(afu);
+ return rc;
+}
+
+static void cxl_remove_afu(struct cxl_afu *afu)
+{
+ pr_devel("cxl_remove_afu\n");
+
+ if (!afu)
+ return;
+
+ cxl_sysfs_afu_remove(afu);
+ cxl_debugfs_afu_remove(afu);
+
+ spin_lock(&afu->adapter->afu_list_lock);
+ afu->adapter->afu[afu->slice] = NULL;
+ spin_unlock(&afu->adapter->afu_list_lock);
+
+ cxl_context_detach_all(afu);
+ cxl_afu_deactivate_model(afu);
+
+ cxl_release_psl_irq(afu);
+ cxl_release_serr_irq(afu);
+ cxl_unmap_slice_regs(afu);
+
+ device_unregister(&afu->dev);
+}
+
+
+static int cxl_map_adapter_regs(struct cxl *adapter, struct pci_dev *dev)
+{
+ if (pci_request_region(dev, 2, "priv 2 regs"))
+ goto err1;
+ if (pci_request_region(dev, 0, "priv 1 regs"))
+ goto err2;
+
+ pr_devel("cxl_map_adapter_regs: p1: %#.16llx %#llx, p2: %#.16llx %#llx",
+ p1_base(dev), p1_size(dev), p2_base(dev), p2_size(dev));
+
+ if (!(adapter->p1_mmio = ioremap(p1_base(dev), p1_size(dev))))
+ goto err3;
+
+ if (!(adapter->p2_mmio = ioremap(p2_base(dev), p2_size(dev))))
+ goto err4;
+
+ return 0;
+
+err4:
+ iounmap(adapter->p1_mmio);
+ adapter->p1_mmio = NULL;
+err3:
+ pci_release_region(dev, 0);
+err2:
+ pci_release_region(dev, 2);
+err1:
+ return -ENOMEM;
+}
+
+static void cxl_unmap_adapter_regs(struct cxl *adapter)
+{
+ if (adapter->p1_mmio)
+ iounmap(adapter->p1_mmio);
+ if (adapter->p2_mmio)
+ iounmap(adapter->p2_mmio);
+}
+
+static int cxl_read_vsec(struct cxl *adapter, struct pci_dev *dev)
+{
+ int vsec;
+ u32 afu_desc_off, afu_desc_size;
+ u32 ps_off, ps_size;
+ u16 vseclen;
+ u8 image_state;
+
+ if (!(vsec = find_cxl_vsec(dev))) {
+ dev_err(&adapter->dev, "ABORTING: CXL VSEC not found!\n");
+ return -ENODEV;
+ }
+
+ CXL_READ_VSEC_LENGTH(dev, vsec, &vseclen);
+ if (vseclen < CXL_VSEC_MIN_SIZE) {
+ pr_err("ABORTING: CXL VSEC too short\n");
+ return -EINVAL;
+ }
+
+ CXL_READ_VSEC_STATUS(dev, vsec, &adapter->vsec_status);
+ CXL_READ_VSEC_PSL_REVISION(dev, vsec, &adapter->psl_rev);
+ CXL_READ_VSEC_CAIA_MAJOR(dev, vsec, &adapter->caia_major);
+ CXL_READ_VSEC_CAIA_MINOR(dev, vsec, &adapter->caia_minor);
+ CXL_READ_VSEC_BASE_IMAGE(dev, vsec, &adapter->base_image);
+ CXL_READ_VSEC_IMAGE_STATE(dev, vsec, &image_state);
+ adapter->user_image_loaded = !!(image_state & CXL_VSEC_USER_IMAGE_LOADED);
+ adapter->perst_loads_image = !!(image_state & CXL_VSEC_PERST_LOADS_IMAGE);
+ adapter->perst_select_user = !!(image_state & CXL_VSEC_PERST_SELECT_USER);
+
+ CXL_READ_VSEC_NAFUS(dev, vsec, &adapter->slices);
+ CXL_READ_VSEC_AFU_DESC_OFF(dev, vsec, &afu_desc_off);
+ CXL_READ_VSEC_AFU_DESC_SIZE(dev, vsec, &afu_desc_size);
+ CXL_READ_VSEC_PS_OFF(dev, vsec, &ps_off);
+ CXL_READ_VSEC_PS_SIZE(dev, vsec, &ps_size);
+
+ /* Convert everything to bytes, because there is NO WAY I'd look at the
+ * code a month later and forget what units these are in ;-) */
+ adapter->ps_off = ps_off * 64 * 1024;
+ adapter->ps_size = ps_size * 64 * 1024;
+ adapter->afu_desc_off = afu_desc_off * 64 * 1024;
+ adapter->afu_desc_size = afu_desc_size *64 * 1024;
+
+ /* Total IRQs - 1 PSL ERROR - #AFU*(1 slice error + 1 DSI) */
+ adapter->user_irqs = pnv_cxl_get_irq_count(dev) - 1 - 2*adapter->slices;
+
+ return 0;
+}
+
+static int cxl_vsec_looks_ok(struct cxl *adapter, struct pci_dev *dev)
+{
+ if (adapter->vsec_status & CXL_STATUS_SECOND_PORT)
+ return -EBUSY;
+
+ if (adapter->vsec_status & CXL_UNSUPPORTED_FEATURES) {
+ dev_err(&adapter->dev, "ABORTING: CXL requires unsupported features\n");
+ return -EINVAL;
+ }
+
+ if (!adapter->slices) {
+ /* Once we support dynamic reprogramming we can use the card if
+ * it supports loadable AFUs */
+ dev_err(&adapter->dev, "ABORTING: Device has no AFUs\n");
+ return -EINVAL;
+ }
+
+ if (!adapter->afu_desc_off || !adapter->afu_desc_size) {
+ dev_err(&adapter->dev, "ABORTING: VSEC shows no AFU descriptors\n");
+ return -EINVAL;
+ }
+
+ if (adapter->ps_size > p2_size(dev) - adapter->ps_off) {
+ dev_err(&adapter->dev, "ABORTING: Problem state size larger than "
+ "available in BAR2: 0x%llx > 0x%llx\n",
+ adapter->ps_size, p2_size(dev) - adapter->ps_off);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void cxl_release_adapter(struct device *dev)
+{
+ struct cxl *adapter = to_cxl_adapter(dev);
+
+ pr_devel("cxl_release_adapter\n");
+
+ kfree(adapter);
+}
+
+static struct cxl *cxl_alloc_adapter(struct pci_dev *dev)
+{
+ struct cxl *adapter;
+
+ if (!(adapter = kzalloc(sizeof(struct cxl), GFP_KERNEL)))
+ return NULL;
+
+ adapter->dev.parent = &dev->dev;
+ adapter->dev.release = cxl_release_adapter;
+ pci_set_drvdata(dev, adapter);
+ spin_lock_init(&adapter->afu_list_lock);
+
+ return adapter;
+}
+
+static int sanitise_adapter_regs(struct cxl *adapter)
+{
+ cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000);
+ return cxl_tlb_slb_invalidate(adapter);
+}
+
+static struct cxl *cxl_init_adapter(struct pci_dev *dev)
+{
+ struct cxl *adapter;
+ bool free = true;
+ int rc;
+
+
+ if (!(adapter = cxl_alloc_adapter(dev)))
+ return ERR_PTR(-ENOMEM);
+
+ if ((rc = switch_card_to_cxl(dev)))
+ goto err1;
+
+ if ((rc = cxl_alloc_adapter_nr(adapter)))
+ goto err1;
+
+ if ((rc = dev_set_name(&adapter->dev, "card%i", adapter->adapter_num)))
+ goto err2;
+
+ if ((rc = cxl_read_vsec(adapter, dev)))
+ goto err2;
+
+ if ((rc = cxl_vsec_looks_ok(adapter, dev)))
+ goto err2;
+
+ if ((rc = cxl_map_adapter_regs(adapter, dev)))
+ goto err2;
+
+ if ((rc = sanitise_adapter_regs(adapter)))
+ goto err2;
+
+ if ((rc = init_implementation_adapter_regs(adapter, dev)))
+ goto err3;
+
+ if ((rc = pnv_phb_to_cxl(dev)))
+ goto err3;
+
+ if ((rc = cxl_register_psl_err_irq(adapter)))
+ goto err3;
+
+ /* Don't care if this one fails: */
+ cxl_debugfs_adapter_add(adapter);
+
+ /* After we call this function we must not free the adapter directly,
+ * even if it returns an error! */
+ if ((rc = cxl_register_adapter(adapter)))
+ goto err_put1;
+
+ if ((rc = cxl_sysfs_adapter_add(adapter)))
+ goto err_put1;
+
+ return adapter;
+
+err_put1:
+ device_unregister(&adapter->dev);
+ free = false;
+ cxl_debugfs_adapter_remove(adapter);
+ cxl_release_psl_err_irq(adapter);
+err3:
+ cxl_unmap_adapter_regs(adapter);
+err2:
+ cxl_remove_adapter_nr(adapter);
+err1:
+ if (free)
+ kfree(adapter);
+ return ERR_PTR(rc);
+}
+
+static void cxl_remove_adapter(struct cxl *adapter)
+{
+ struct pci_dev *pdev = to_pci_dev(adapter->dev.parent);
+
+ pr_devel("cxl_release_adapter\n");
+
+ cxl_sysfs_adapter_remove(adapter);
+ cxl_debugfs_adapter_remove(adapter);
+ cxl_release_psl_err_irq(adapter);
+ cxl_unmap_adapter_regs(adapter);
+ cxl_remove_adapter_nr(adapter);
+
+ device_unregister(&adapter->dev);
+
+ pci_release_region(pdev, 0);
+ pci_release_region(pdev, 2);
+ pci_disable_device(pdev);
+}
+
+static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
+{
+ struct cxl *adapter;
+ int slice;
+ int rc;
+
+ pci_dev_get(dev);
+
+ if (cxl_verbose)
+ dump_cxl_config_space(dev);
+
+ if ((rc = setup_cxl_bars(dev)))
+ return rc;
+
+ if ((rc = pci_enable_device(dev))) {
+ dev_err(&dev->dev, "pci_enable_device failed: %i\n", rc);
+ return rc;
+ }
+
+ adapter = cxl_init_adapter(dev);
+ if (IS_ERR(adapter)) {
+ dev_err(&dev->dev, "cxl_init_adapter failed: %li\n", PTR_ERR(adapter));
+ return PTR_ERR(adapter);
+ }
+
+ for (slice = 0; slice < adapter->slices; slice++) {
+ if ((rc = cxl_init_afu(adapter, slice, dev)))
+ dev_err(&dev->dev, "AFU %i failed to initialise: %i\n", slice, rc);
+ }
+
+ return 0;
+}
+
+static void cxl_remove(struct pci_dev *dev)
+{
+ struct cxl *adapter = pci_get_drvdata(dev);
+ int afu;
+
+ dev_warn(&dev->dev, "pci remove\n");
+
+ /* Lock to prevent someone grabbing a ref through the adapter list as
+ * we are removing it */
+ for (afu = 0; afu < adapter->slices; afu++)
+ cxl_remove_afu(adapter->afu[afu]);
+ cxl_remove_adapter(adapter);
+}
+
+struct pci_driver cxl_pci_driver = {
+ .name = "cxl-pci",
+ .id_table = cxl_pci_tbl,
+ .probe = cxl_probe,
+ .remove = cxl_remove,
+};
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
new file mode 100644
index 0000000..ecc30060
--- /dev/null
+++ b/drivers/misc/cxl/sysfs.c
@@ -0,0 +1,360 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/sysfs.h>
+
+#include "cxl.h"
+
+#define to_afu_chardev_m(d) dev_get_drvdata(d)
+
+/********* Adapter attributes **********************************************/
+
+static ssize_t caia_version_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl *adapter = to_cxl_adapter(device);
+
+ return scnprintf(buf, PAGE_SIZE, "%i.%i\n", adapter->caia_major,
+ adapter->caia_minor);
+}
+
+static ssize_t psl_revision_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl *adapter = to_cxl_adapter(device);
+
+ return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->psl_rev);
+}
+
+static ssize_t base_image_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl *adapter = to_cxl_adapter(device);
+
+ return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->base_image);
+}
+
+static ssize_t image_loaded_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl *adapter = to_cxl_adapter(device);
+
+ if (adapter->user_image_loaded)
+ return scnprintf(buf, PAGE_SIZE, "user\n");
+ return scnprintf(buf, PAGE_SIZE, "factory\n");
+}
+
+static struct device_attribute adapter_attrs[] = {
+ __ATTR_RO(caia_version),
+ __ATTR_RO(psl_revision),
+ __ATTR_RO(base_image),
+ __ATTR_RO(image_loaded),
+ /* __ATTR_RW(reset_loads_image); */
+ /* __ATTR_RW(reset_image_select); */
+};
+
+
+/********* AFU master specific attributes **********************************/
+
+static ssize_t mmio_size_show_master(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl_afu *afu = to_afu_chardev_m(device);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->adapter->ps_size);
+}
+
+static ssize_t pp_mmio_off_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl_afu *afu = to_afu_chardev_m(device);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->pp_offset);
+}
+
+static ssize_t pp_mmio_len_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl_afu *afu = to_afu_chardev_m(device);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->pp_size);
+}
+
+static struct device_attribute afu_master_attrs[] = {
+ __ATTR(mmio_size, S_IRUGO, mmio_size_show_master, NULL),
+ __ATTR_RO(pp_mmio_off),
+ __ATTR_RO(pp_mmio_len),
+};
+
+
+/********* AFU attributes **************************************************/
+
+static ssize_t mmio_size_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl_afu *afu = to_cxl_afu(device);
+
+ if (afu->pp_size)
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->pp_size);
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->adapter->ps_size);
+}
+
+static ssize_t reset_store_afu(struct device *device,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct cxl_afu *afu = to_cxl_afu(device);
+ int rc;
+
+ if ((rc = cxl_afu_reset(afu)))
+ return rc;
+ return count;
+}
+
+static ssize_t irqs_min_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl_afu *afu = to_cxl_afu(device);
+
+ return scnprintf(buf, PAGE_SIZE, "%i\n", afu->pp_irqs);
+}
+
+static ssize_t irqs_max_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl_afu *afu = to_cxl_afu(device);
+
+ return scnprintf(buf, PAGE_SIZE, "%i\n", afu->irqs_max);
+}
+
+static ssize_t irqs_max_store(struct device *device,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct cxl_afu *afu = to_cxl_afu(device);
+ ssize_t ret;
+ int irqs_max;
+
+ ret = sscanf(buf, "%i", &irqs_max);
+ if (ret != 1)
+ return -EINVAL;
+
+ if (irqs_max < afu->pp_irqs)
+ return -EINVAL;
+
+ if (irqs_max > afu->adapter->user_irqs)
+ return -EINVAL;
+
+ afu->irqs_max = irqs_max;
+ return count;
+}
+
+static ssize_t models_supported_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl_afu *afu = to_cxl_afu(device);
+ char *p = buf, *end = buf + PAGE_SIZE;
+
+ if (afu->models_supported & CXL_MODEL_DEDICATED)
+ p += scnprintf(p, end - p, "dedicated_process\n");
+ if (afu->models_supported & CXL_MODEL_DIRECTED)
+ p += scnprintf(p, end - p, "afu_directed\n");
+ return (p - buf);
+}
+
+static ssize_t prefault_mode_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl_afu *afu = to_cxl_afu(device);
+
+ switch (afu->prefault_mode) {
+ case CXL_PREFAULT_WED:
+ return scnprintf(buf, PAGE_SIZE, "wed\n");
+ case CXL_PREFAULT_ALL:
+ return scnprintf(buf, PAGE_SIZE, "all\n");
+ default:
+ return scnprintf(buf, PAGE_SIZE, "none\n");
+ }
+}
+
+static ssize_t prefault_mode_store(struct device *device,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct cxl_afu *afu = to_cxl_afu(device);
+ enum prefault_modes mode = -1;
+
+ if (!strncmp(buf, "wed", 3))
+ mode = CXL_PREFAULT_WED;
+ if (!strncmp(buf, "all", 3))
+ mode = CXL_PREFAULT_ALL;
+ if (!strncmp(buf, "none", 4))
+ mode = CXL_PREFAULT_NONE;
+
+ if (mode == -1)
+ return -EINVAL;
+
+ afu->prefault_mode = mode;
+ return count;
+}
+
+static ssize_t model_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl_afu *afu = to_cxl_afu(device);
+
+ if (afu->current_model == CXL_MODEL_DEDICATED)
+ return scnprintf(buf, PAGE_SIZE, "dedicated_process\n");
+ if (afu->current_model == CXL_MODEL_DIRECTED)
+ return scnprintf(buf, PAGE_SIZE, "afu_directed\n");
+ return scnprintf(buf, PAGE_SIZE, "none\n");
+}
+
+static ssize_t model_store(struct device *device,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct cxl_afu *afu = to_cxl_afu(device);
+ int old_model, model = -1;
+ int rc = -EBUSY;
+
+ /* can't change this if we have a user */
+ spin_lock(&afu->contexts_lock);
+ if (!idr_is_empty(&afu->contexts_idr))
+ goto err;
+
+ if (!strncmp(buf, "dedicated_process", 17))
+ model = CXL_MODEL_DEDICATED;
+ if (!strncmp(buf, "afu_directed", 12))
+ model = CXL_MODEL_DIRECTED;
+ if (!strncmp(buf, "none", 4))
+ model = 0;
+
+ if (model == -1) {
+ rc = -EINVAL;
+ goto err;
+ }
+
+ /* cxl_afu_deactivate_model needs to be done outside the lock, prevent
+ * other contexts coming in before we are ready: */
+ old_model = afu->current_model;
+ afu->current_model = 0;
+ afu->num_procs = 0;
+
+ spin_unlock(&afu->contexts_lock);
+
+ if ((rc = _cxl_afu_deactivate_model(afu, old_model)))
+ return rc;
+ if ((rc = cxl_afu_activate_model(afu, model)))
+ return rc;
+
+ return count;
+err:
+ spin_unlock(&afu->contexts_lock);
+ return rc;
+}
+
+static ssize_t api_version_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return scnprintf(buf, PAGE_SIZE, "%i\n", CXL_API_VERSION);
+}
+
+static ssize_t api_version_compatible_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return scnprintf(buf, PAGE_SIZE, "%i\n", CXL_API_VERSION_COMPATIBLE);
+}
+
+static struct device_attribute afu_attrs[] = {
+ __ATTR_RO(mmio_size),
+ __ATTR_RO(irqs_min),
+ __ATTR_RW(irqs_max),
+ __ATTR_RO(models_supported),
+ __ATTR_RW(model),
+ __ATTR_RW(prefault_mode),
+ __ATTR_RO(api_version),
+ __ATTR_RO(api_version_compatible),
+ __ATTR(reset, S_IWUSR, NULL, reset_store_afu),
+};
+
+
+
+int cxl_sysfs_adapter_add(struct cxl *adapter)
+{
+ int i, rc;
+
+ for (i = 0; i < ARRAY_SIZE(adapter_attrs); i++) {
+ if ((rc = device_create_file(&adapter->dev, &adapter_attrs[i])))
+ goto err;
+ }
+ return 0;
+err:
+ for (i--; i >= 0; i--)
+ device_remove_file(&adapter->dev, &adapter_attrs[i]);
+ return rc;
+}
+void cxl_sysfs_adapter_remove(struct cxl *adapter)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(adapter_attrs); i++)
+ device_remove_file(&adapter->dev, &adapter_attrs[i]);
+}
+
+int cxl_sysfs_afu_add(struct cxl_afu *afu)
+{
+ int afu_attr, mstr_attr, rc = 0;
+
+ for (afu_attr = 0; afu_attr < ARRAY_SIZE(afu_attrs); afu_attr++) {
+ if ((rc = device_create_file(&afu->dev, &afu_attrs[afu_attr])))
+ goto err;
+ }
+ for (mstr_attr = 0; mstr_attr < ARRAY_SIZE(afu_master_attrs); mstr_attr++) {
+ if ((rc = device_create_file(afu->chardev_m, &afu_master_attrs[mstr_attr])))
+ goto err1;
+ }
+
+ return 0;
+
+err1:
+ for (mstr_attr--; mstr_attr >= 0; mstr_attr--)
+ device_remove_file(afu->chardev_m, &afu_master_attrs[mstr_attr]);
+err:
+ for (afu_attr--; afu_attr >= 0; afu_attr--)
+ device_remove_file(&afu->dev, &afu_attrs[afu_attr]);
+ return rc;
+}
+
+void cxl_sysfs_afu_remove(struct cxl_afu *afu)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(afu_master_attrs); i++)
+ device_remove_file(afu->chardev_m, &afu_master_attrs[i]);
+ for (i = 0; i < ARRAY_SIZE(afu_attrs); i++)
+ device_remove_file(&afu->dev, &afu_attrs[i]);
+}
--
1.9.1
^ permalink raw reply related
* [PATCH v3 12/16] cxl: Add base builtin support
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
This adds the base cxl support that needs to be build into the kernel to use
cxl as a module. This is needed so that the cxl call backs from the core
powerpc mm code always exist irrespective of if the cxl module is loaded or
not. This is similar to how cell works with CONFIG_SPU_BASE.
This adds a cxl_slbia() call (similar to spu_flush_all_slbs()) which checks for
the cxl module being loaded. If the modules is not loaded we return, otherwise
we call into the cxl SLB invalidation code.
This also adds the cxl_ctx_in_use() function for use in the mm code to see if
any cxl contexts are currently in use. This is used by the tlbie() to
determine if it can do local TLB invalidations or not. This also adds get/put
calls for the cxl driver module to refcount the active cxl contexts.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
drivers/misc/Kconfig | 1 +
drivers/misc/Makefile | 1 +
drivers/misc/cxl/Kconfig | 8 +++++
drivers/misc/cxl/Makefile | 1 +
drivers/misc/cxl/base.c | 86 +++++++++++++++++++++++++++++++++++++++++++++++
5 files changed, 97 insertions(+)
create mode 100644 drivers/misc/cxl/Kconfig
create mode 100644 drivers/misc/cxl/Makefile
create mode 100644 drivers/misc/cxl/base.c
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index b841180..bbeb451 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -527,4 +527,5 @@ source "drivers/misc/vmw_vmci/Kconfig"
source "drivers/misc/mic/Kconfig"
source "drivers/misc/genwqe/Kconfig"
source "drivers/misc/echo/Kconfig"
+source "drivers/misc/cxl/Kconfig"
endmenu
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 5497d02..7d5c4cd 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -55,3 +55,4 @@ obj-y += mic/
obj-$(CONFIG_GENWQE) += genwqe/
obj-$(CONFIG_ECHO) += echo/
obj-$(CONFIG_VEXPRESS_SYSCFG) += vexpress-syscfg.o
+obj-$(CONFIG_CXL_BASE) += cxl/
diff --git a/drivers/misc/cxl/Kconfig b/drivers/misc/cxl/Kconfig
new file mode 100644
index 0000000..5cdd319
--- /dev/null
+++ b/drivers/misc/cxl/Kconfig
@@ -0,0 +1,8 @@
+#
+# IBM Coherent Accelerator (CXL) compatible devices
+#
+
+config CXL_BASE
+ bool
+ default n
+ select PPC_COPRO_BASE
diff --git a/drivers/misc/cxl/Makefile b/drivers/misc/cxl/Makefile
new file mode 100644
index 0000000..e30ad0a
--- /dev/null
+++ b/drivers/misc/cxl/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_CXL_BASE) += base.o
diff --git a/drivers/misc/cxl/base.c b/drivers/misc/cxl/base.c
new file mode 100644
index 0000000..0654ad8
--- /dev/null
+++ b/drivers/misc/cxl/base.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/rcupdate.h>
+#include <asm/errno.h>
+#include <misc/cxl.h>
+#include "cxl.h"
+
+/* protected by rcu */
+static struct cxl_calls *cxl_calls;
+
+atomic_t cxl_use_count = ATOMIC_INIT(0);
+EXPORT_SYMBOL(cxl_use_count);
+
+#ifdef CONFIG_CXL_MODULE
+
+static inline struct cxl_calls *cxl_calls_get(void)
+{
+ struct cxl_calls *calls = NULL;
+
+ rcu_read_lock();
+ calls = rcu_dereference(cxl_calls);
+ if (calls && !try_module_get(calls->owner))
+ calls = NULL;
+ rcu_read_unlock();
+
+ return calls;
+}
+
+static inline void cxl_calls_put(struct cxl_calls *calls)
+{
+ BUG_ON(calls != cxl_calls);
+
+ /* we don't need to rcu this, as we hold a reference to the module */
+ module_put(cxl_calls->owner);
+}
+
+#else /* !defined CONFIG_CXL_MODULE */
+
+static inline struct cxl_calls *cxl_calls_get(void)
+{
+ return cxl_calls;
+}
+
+static inline void cxl_calls_put(struct cxl_calls *calls) { }
+
+#endif /* CONFIG_CXL_MODULE */
+
+void cxl_slbia(struct mm_struct *mm)
+{
+ struct cxl_calls *calls;
+
+ calls = cxl_calls_get();
+ if (!calls)
+ return;
+
+ if (cxl_ctx_in_use())
+ calls->cxl_slbia(mm);
+
+ cxl_calls_put(calls);
+}
+
+int register_cxl_calls(struct cxl_calls *calls)
+{
+ if (cxl_calls)
+ return -EBUSY;
+
+ rcu_assign_pointer(cxl_calls, calls);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(register_cxl_calls);
+
+void unregister_cxl_calls(struct cxl_calls *calls)
+{
+ BUG_ON(cxl_calls->owner != calls->owner);
+ RCU_INIT_POINTER(cxl_calls, NULL);
+ synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(unregister_cxl_calls);
--
1.9.1
^ permalink raw reply related
* [PATCH v3 11/16] powerpc/mm: Add hooks for cxl
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
This add a hook into tlbie() so that we use global invalidations when there are
cxl contexts active.
Normally cxl snoops broadcast tlbie. cxl can have TLB entries invalidated via
MMIO, but we aren't doing that yet. So for now we are just disabling local
tlbies when cxl contexts are active. In future we can make tlbie() local mode
smarter so that it invalidates cxl contexts explicitly when it needs to.
This also adds a hooks for when SLBs are invalidated to ensure any
corresponding SLBs in cxl are also invalidated at the same time.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/mm/copro_fault.c | 2 ++
arch/powerpc/mm/hash_native_64.c | 6 +++++-
2 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 222ef9b..55791fc 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -26,6 +26,7 @@
#include <asm/reg.h>
#include <asm/copro.h>
#include <asm/spu.h>
+#include <misc/cxl.h>
/*
* This ought to be kept in sync with the powerpc specific do_page_fault
@@ -143,5 +144,6 @@ void copro_flush_all_slbs(struct mm_struct *mm)
#ifdef CONFIG_SPU_BASE
spu_flush_all_slbs(mm);
#endif
+ cxl_slbia(mm);
}
EXPORT_SYMBOL_GPL(copro_flush_all_slbs);
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index afc0a82..ae4962a 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -29,6 +29,8 @@
#include <asm/kexec.h>
#include <asm/ppc-opcode.h>
+#include <misc/cxl.h>
+
#ifdef DEBUG_LOW
#define DBG_LOW(fmt...) udbg_printf(fmt)
#else
@@ -149,9 +151,11 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
static inline void tlbie(unsigned long vpn, int psize, int apsize,
int ssize, int local)
{
- unsigned int use_local = local && mmu_has_feature(MMU_FTR_TLBIEL);
+ unsigned int use_local;
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+ use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) && !cxl_ctx_in_use();
+
if (use_local)
use_local = mmu_psize_defs[psize].tlbiel;
if (lock_tlbie && !use_local)
--
1.9.1
^ permalink raw reply related
* [PATCH v3 10/16] powerpc/opal: Add PHB to cxl mode call
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
This adds the OPAL call to change a PHB into cxl mode.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/include/asm/opal.h | 2 ++
arch/powerpc/platforms/powernv/opal-wrappers.S | 1 +
2 files changed, 3 insertions(+)
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 86055e5..84c37c4dbc 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -146,6 +146,7 @@ struct opal_sg_list {
#define OPAL_GET_PARAM 89
#define OPAL_SET_PARAM 90
#define OPAL_DUMP_RESEND 91
+#define OPAL_PCI_SET_PHB_CXL_MODE 93
#define OPAL_DUMP_INFO2 94
#define OPAL_PCI_EEH_FREEZE_SET 97
#define OPAL_HANDLE_HMI 98
@@ -924,6 +925,7 @@ int64_t opal_sensor_read(uint32_t sensor_hndl, int token, __be32 *sensor_data);
int64_t opal_handle_hmi(void);
int64_t opal_register_dump_region(uint32_t id, uint64_t start, uint64_t end);
int64_t opal_unregister_dump_region(uint32_t id);
+int64_t opal_pci_set_phb_cxl_mode(uint64_t phb_id, uint64_t mode, uint64_t pe_number);
/* Internal functions */
extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 2e6ce1b..0fb56dc 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -247,3 +247,4 @@ OPAL_CALL(opal_set_param, OPAL_SET_PARAM);
OPAL_CALL(opal_handle_hmi, OPAL_HANDLE_HMI);
OPAL_CALL(opal_register_dump_region, OPAL_REGISTER_DUMP_REGION);
OPAL_CALL(opal_unregister_dump_region, OPAL_UNREGISTER_DUMP_REGION);
+OPAL_CALL(opal_pci_set_phb_cxl_mode, OPAL_PCI_SET_PHB_CXL_MODE);
--
1.9.1
^ permalink raw reply related
* [PATCH v3 09/16] powerpc/mm: Add new hash_page_mm()
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
This adds a new function hash_page_mm() based on the existing hash_page().
This version allows any struct mm to be passed in, rather than assuming
current. This is useful for servicing co-processor faults which are not in the
context of the current running process.
We need to be careful here as the current hash_page() assumes current in a few
places.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/include/asm/mmu-hash64.h | 1 +
arch/powerpc/mm/hash_utils_64.c | 24 +++++++++++++++++-------
2 files changed, 18 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 6d0b7a2..f84e5a5 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -322,6 +322,7 @@ extern int __hash_page_64K(unsigned long ea, unsigned long access,
unsigned int local, int ssize);
struct mm_struct;
unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap);
+extern int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap);
extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap);
int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
pte_t *ptep, unsigned long trap, int local, int ssize,
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index bbdb054..698834d 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -904,7 +904,7 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
return;
slice_set_range_psize(mm, addr, 1, MMU_PAGE_4K);
copro_flush_all_slbs(mm);
- if (get_paca_psize(addr) != MMU_PAGE_4K) {
+ if ((get_paca_psize(addr) != MMU_PAGE_4K) && (current->mm == mm)) {
get_paca()->context = mm->context;
slb_flush_and_rebolt();
}
@@ -989,12 +989,11 @@ static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
* -1 - critical hash insertion error
* -2 - access not permitted by subpage protection mechanism
*/
-int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
+int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap)
{
enum ctx_state prev_state = exception_enter();
pgd_t *pgdir;
unsigned long vsid;
- struct mm_struct *mm;
pte_t *ptep;
unsigned hugeshift;
const struct cpumask *tmp;
@@ -1008,7 +1007,6 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
switch (REGION_ID(ea)) {
case USER_REGION_ID:
user_region = 1;
- mm = current->mm;
if (! mm) {
DBG_LOW(" user region with no mm !\n");
rc = 1;
@@ -1019,7 +1017,6 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
vsid = get_vsid(mm->context.id, ea, ssize);
break;
case VMALLOC_REGION_ID:
- mm = &init_mm;
vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
if (ea < VMALLOC_END)
psize = mmu_vmalloc_psize;
@@ -1104,7 +1101,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
WARN_ON(1);
}
#endif
- check_paca_psize(ea, mm, psize, user_region);
+ if (current->mm == mm)
+ check_paca_psize(ea, mm, psize, user_region);
goto bail;
}
@@ -1145,7 +1143,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
}
}
- check_paca_psize(ea, mm, psize, user_region);
+ if (current->mm == mm)
+ check_paca_psize(ea, mm, psize, user_region);
#endif /* CONFIG_PPC_64K_PAGES */
#ifdef CONFIG_PPC_HAS_HASH_64K
@@ -1180,6 +1179,17 @@ bail:
exception_exit(prev_state);
return rc;
}
+EXPORT_SYMBOL_GPL(hash_page_mm);
+
+int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
+{
+ struct mm_struct *mm = current->mm;
+
+ if (REGION_ID(ea) == VMALLOC_REGION_ID)
+ mm = &init_mm;
+
+ return hash_page_mm(mm, ea, access, trap);
+}
EXPORT_SYMBOL_GPL(hash_page);
void hash_preload(struct mm_struct *mm, unsigned long ea,
--
1.9.1
^ permalink raw reply related
* [PATCH v3 08/16] powerpc/powerpc: Add new PCIe functions for allocating cxl interrupts
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
This adds a number of functions for allocating IRQs under powernv PCIe for cxl.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/include/asm/pnv-pci.h | 27 ++++++
arch/powerpc/platforms/powernv/pci-ioda.c | 153 ++++++++++++++++++++++++++++++
2 files changed, 180 insertions(+)
create mode 100644 arch/powerpc/include/asm/pnv-pci.h
diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h
new file mode 100644
index 0000000..71717b5
--- /dev/null
+++ b/arch/powerpc/include/asm/pnv-pci.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ASM_PNV_PCI_H
+#define _ASM_PNV_PCI_H
+
+#include <linux/pci.h>
+#include <misc/cxl.h>
+
+int pnv_phb_to_cxl(struct pci_dev *dev);
+int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
+ unsigned int virq);
+int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num);
+void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num);
+int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
+ struct pci_dev *dev, int num);
+void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs,
+ struct pci_dev *dev);
+int pnv_cxl_get_irq_count(struct pci_dev *dev);
+
+#endif
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index baf3de6..3b67010b 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -38,6 +38,8 @@
#include <asm/debug.h>
#include <asm/firmware.h>
+#include <misc/cxl.h>
+
#include "powernv.h"
#include "pci.h"
@@ -1329,6 +1331,157 @@ static void set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
irq_set_chip(virq, &phb->ioda.irq_chip);
}
+#ifdef CONFIG_CXL_BASE
+
+struct device_node *pnv_pci_to_phb_node(struct pci_dev *dev)
+{
+ struct pci_controller *hose = pci_bus_to_host(dev->bus);
+
+ return hose->dn;
+}
+EXPORT_SYMBOL(pnv_pci_to_phb_node);
+
+int pnv_phb_to_cxl(struct pci_dev *dev)
+{
+ struct pci_controller *hose = pci_bus_to_host(dev->bus);
+ struct pnv_phb *phb = hose->private_data;
+ struct pnv_ioda_pe *pe;
+ int rc;
+
+ pe = pnv_ioda_get_pe(dev);
+ if (!pe)
+ return -ENODEV;
+
+ pe_info(pe, "Switching PHB to CXL\n");
+
+ rc = opal_pci_set_phb_cxl_mode(phb->opal_id, 1, pe->pe_number);
+ if (rc)
+ dev_err(&dev->dev, "opal_pci_set_phb_cxl_mode failed: %i\n", rc);
+
+ return rc;
+}
+EXPORT_SYMBOL(pnv_phb_to_cxl);
+
+/* Find PHB for cxl dev and allocate MSI hwirqs?
+ * Returns the absolute hardware IRQ number
+ */
+int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num)
+{
+ struct pci_controller *hose = pci_bus_to_host(dev->bus);
+ struct pnv_phb *phb = hose->private_data;
+ int hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, num);
+
+ if (hwirq < 0) {
+ dev_warn(&dev->dev, "Failed to find a free MSI\n");
+ return -ENOSPC;
+ }
+
+ return phb->msi_base + hwirq;
+}
+EXPORT_SYMBOL(pnv_cxl_alloc_hwirqs);
+
+void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num)
+{
+ struct pci_controller *hose = pci_bus_to_host(dev->bus);
+ struct pnv_phb *phb = hose->private_data;
+
+ msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, num);
+}
+EXPORT_SYMBOL(pnv_cxl_release_hwirqs);
+
+void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs,
+ struct pci_dev *dev)
+{
+ struct pci_controller *hose = pci_bus_to_host(dev->bus);
+ struct pnv_phb *phb = hose->private_data;
+ int i, hwirq;
+
+ for (i = 1; i < CXL_IRQ_RANGES; i++) {
+ if (!irqs->range[i])
+ continue;
+ pr_devel("cxl release irq range 0x%x: offset: 0x%lx limit: %ld\n",
+ i, irqs->offset[i],
+ irqs->range[i]);
+ hwirq = irqs->offset[i] - phb->msi_base;
+ msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq,
+ irqs->range[i]);
+ }
+}
+EXPORT_SYMBOL(pnv_cxl_release_hwirq_ranges);
+
+int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
+ struct pci_dev *dev, int num)
+{
+ struct pci_controller *hose = pci_bus_to_host(dev->bus);
+ struct pnv_phb *phb = hose->private_data;
+ int i, hwirq, try;
+
+ memset(irqs, 0, sizeof(struct cxl_irq_ranges));
+
+ /* 0 is reserved for the multiplexed PSL DSI interrupt */
+ for (i = 1; i < CXL_IRQ_RANGES && num; i++) {
+ try = num;
+ while (try) {
+ hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, try);
+ if (hwirq >= 0)
+ break;
+ try /= 2;
+ }
+ if (!try)
+ goto fail;
+
+ irqs->offset[i] = phb->msi_base + hwirq;
+ irqs->range[i] = try;
+ pr_devel("cxl alloc irq range 0x%x: offset: 0x%lx limit: %li\n",
+ i, irqs->offset[i], irqs->range[i]);
+ num -= try;
+ }
+ if (num)
+ goto fail;
+
+ return 0;
+fail:
+ pnv_cxl_release_hwirq_ranges(irqs, dev);
+ return -ENOSPC;
+}
+EXPORT_SYMBOL(pnv_cxl_alloc_hwirq_ranges);
+
+int pnv_cxl_get_irq_count(struct pci_dev *dev)
+{
+ struct pci_controller *hose = pci_bus_to_host(dev->bus);
+ struct pnv_phb *phb = hose->private_data;
+
+ return phb->msi_bmp.irq_count;
+}
+EXPORT_SYMBOL(pnv_cxl_get_irq_count);
+
+int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
+ unsigned int virq)
+{
+ struct pci_controller *hose = pci_bus_to_host(dev->bus);
+ struct pnv_phb *phb = hose->private_data;
+ unsigned int xive_num = hwirq - phb->msi_base;
+ struct pnv_ioda_pe *pe;
+ int rc;
+
+ if (!(pe = pnv_ioda_get_pe(dev)))
+ return -ENODEV;
+
+ /* Assign XIVE to PE */
+ rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num);
+ if (rc) {
+ pe_warn(pe, "%s: OPAL error %d setting msi_base 0x%x "
+ "hwirq 0x%x XIVE 0x%x PE\n",
+ pci_name(dev), rc, phb->msi_base, hwirq, xive_num);
+ return -EIO;
+ }
+ set_msi_irq_chip(phb, virq);
+
+ return 0;
+}
+EXPORT_SYMBOL(pnv_cxl_ioda_msi_setup);
+#endif
+
static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
unsigned int hwirq, unsigned int virq,
unsigned int is_64, struct msi_msg *msg)
--
1.9.1
^ permalink raw reply related
* [PATCH v3 07/16] cxl: Add new header for call backs and structs
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
This new header adds callbacks and structs needed by the rest of the kernel to
hook into the cxl infrastructure.
cxl_ctx_get/put/in_use are static inlined here as they are called in tlbie
which we want to be fast (mpe's suggestion).
Empty functions are provided when CONFIG_CXL_BASE is not enabled.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
include/misc/cxl.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 48 insertions(+)
create mode 100644 include/misc/cxl.h
diff --git a/include/misc/cxl.h b/include/misc/cxl.h
new file mode 100644
index 0000000..10cb742
--- /dev/null
+++ b/include/misc/cxl.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _MISC_CXL_H
+#define _MISC_CXL_H
+
+#define CXL_IRQ_RANGES 4
+
+struct cxl_irq_ranges {
+ irq_hw_number_t offset[CXL_IRQ_RANGES];
+ irq_hw_number_t range[CXL_IRQ_RANGES];
+};
+
+#ifdef CONFIG_CXL_BASE
+
+extern atomic_t cxl_use_count;
+
+static inline bool cxl_ctx_in_use(void)
+{
+ return (atomic_read(&cxl_use_count) != 0);
+}
+
+static inline void cxl_ctx_get(void)
+{
+ atomic_inc(&cxl_use_count);
+}
+
+static inline void cxl_ctx_put(void)
+{
+ atomic_dec(&cxl_use_count);
+}
+
+void cxl_slbia(struct mm_struct *mm);
+
+#else /* CONFIG_CXL_BASE */
+
+static inline bool cxl_ctx_in_use(void) { return false; }
+static inline void cxl_slbia(struct mm_struct *mm) {}
+
+#endif /* CONFIG_CXL_BASE */
+
+#endif
--
1.9.1
^ permalink raw reply related
* [PATCH v3 06/16] powerpc/powernv: Split out set MSI IRQ chip code
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
Some of the MSI IRQ code in pnv_pci_ioda_msi_setup() is generically useful so
split it out.
This will be used by some of the cxl PCIe code later.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/platforms/powernv/pci-ioda.c | 42 ++++++++++++++++++-------------
1 file changed, 24 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index df241b1..baf3de6 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1306,14 +1306,35 @@ static void pnv_ioda2_msi_eoi(struct irq_data *d)
icp_native_eoi(d);
}
+
+static void set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
+{
+ struct irq_data *idata;
+ struct irq_chip *ichip;
+
+ if (phb->type != PNV_PHB_IODA2)
+ return;
+
+ if (!phb->ioda.irq_chip_init) {
+ /*
+ * First time we setup an MSI IRQ, we need to setup the
+ * corresponding IRQ chip to route correctly.
+ */
+ idata = irq_get_irq_data(virq);
+ ichip = irq_data_get_irq_chip(idata);
+ phb->ioda.irq_chip_init = 1;
+ phb->ioda.irq_chip = *ichip;
+ phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi;
+ }
+ irq_set_chip(virq, &phb->ioda.irq_chip);
+}
+
static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
unsigned int hwirq, unsigned int virq,
unsigned int is_64, struct msi_msg *msg)
{
struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev);
struct pci_dn *pdn = pci_get_pdn(dev);
- struct irq_data *idata;
- struct irq_chip *ichip;
unsigned int xive_num = hwirq - phb->msi_base;
__be32 data;
int rc;
@@ -1365,22 +1386,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
}
msg->data = be32_to_cpu(data);
- /*
- * Change the IRQ chip for the MSI interrupts on PHB3.
- * The corresponding IRQ chip should be populated for
- * the first time.
- */
- if (phb->type == PNV_PHB_IODA2) {
- if (!phb->ioda.irq_chip_init) {
- idata = irq_get_irq_data(virq);
- ichip = irq_data_get_irq_chip(idata);
- phb->ioda.irq_chip_init = 1;
- phb->ioda.irq_chip = *ichip;
- phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi;
- }
-
- irq_set_chip(virq, &phb->ioda.irq_chip);
- }
+ set_msi_irq_chip(phb, virq);
pr_devel("%s: %s-bit MSI on hwirq %x (xive #%d),"
" address=%x_%08x data=%x PE# %d\n",
--
1.9.1
^ permalink raw reply related
* [PATCH v3 05/16] powerpc/mm: Export mmu_kernel_ssize and mmu_linear_psize
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
Export mmu_kernel_ssize and mmu_linear_psize. These are needed by the cxl
driver which has it's own MMU. To setup the MMU cxl need access to these.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/mm/hash_utils_64.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 5c0738d..bbdb054 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -98,6 +98,7 @@ unsigned long htab_size_bytes;
unsigned long htab_hash_mask;
EXPORT_SYMBOL_GPL(htab_hash_mask);
int mmu_linear_psize = MMU_PAGE_4K;
+EXPORT_SYMBOL_GPL(mmu_linear_psize);
int mmu_virtual_psize = MMU_PAGE_4K;
int mmu_vmalloc_psize = MMU_PAGE_4K;
#ifdef CONFIG_SPARSEMEM_VMEMMAP
@@ -105,6 +106,7 @@ int mmu_vmemmap_psize = MMU_PAGE_4K;
#endif
int mmu_io_psize = MMU_PAGE_4K;
int mmu_kernel_ssize = MMU_SEGSIZE_256M;
+EXPORT_SYMBOL_GPL(mmu_kernel_ssize);
int mmu_highuser_ssize = MMU_SEGSIZE_256M;
u16 mmu_slb_size = 64;
EXPORT_SYMBOL_GPL(mmu_slb_size);
--
1.9.1
^ permalink raw reply related
* [PATCH v3 04/16] powerpc/msi: Improve IRQ bitmap allocator
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
Currently msi_bitmap_alloc_hwirqs() will round up any IRQ allocation requests
to the nearest power of 2. eg. ask for 5 IRQs and you'll get 8. This wastes a
lot of IRQs which can be a scarce resource.
For cxl we may require multiple IRQs for every context that is attached to the
accelerator. There may be 1000s of contexts attached, hence we can easily run
out of IRQs, especially if we are needlessly wasting them.
This changes the msi_bitmap_alloc_hwirqs() to allocate only the required number
of IRQs, hence avoiding this wastage. It keeps the natural alignment
requirement though.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/sysdev/msi_bitmap.c | 33 ++++++++++++++++++++++-----------
1 file changed, 22 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c
index 2ff6302..56c8b13 100644
--- a/arch/powerpc/sysdev/msi_bitmap.c
+++ b/arch/powerpc/sysdev/msi_bitmap.c
@@ -20,32 +20,37 @@ int msi_bitmap_alloc_hwirqs(struct msi_bitmap *bmp, int num)
int offset, order = get_count_order(num);
spin_lock_irqsave(&bmp->lock, flags);
- /*
- * This is fast, but stricter than we need. We might want to add
- * a fallback routine which does a linear search with no alignment.
- */
- offset = bitmap_find_free_region(bmp->bitmap, bmp->irq_count, order);
+
+ offset = bitmap_find_next_zero_area(bmp->bitmap, bmp->irq_count, 0,
+ num, (1 << order) - 1);
+ if (offset > bmp->irq_count)
+ goto err;
+
+ bitmap_set(bmp->bitmap, offset, num);
spin_unlock_irqrestore(&bmp->lock, flags);
- pr_debug("msi_bitmap: allocated 0x%x (2^%d) at offset 0x%x\n",
- num, order, offset);
+ pr_debug("msi_bitmap: allocated 0x%x at offset 0x%x\n", num, offset);
return offset;
+err:
+ spin_unlock_irqrestore(&bmp->lock, flags);
+ return -ENOMEM;
}
+EXPORT_SYMBOL(msi_bitmap_alloc_hwirqs);
void msi_bitmap_free_hwirqs(struct msi_bitmap *bmp, unsigned int offset,
unsigned int num)
{
unsigned long flags;
- int order = get_count_order(num);
- pr_debug("msi_bitmap: freeing 0x%x (2^%d) at offset 0x%x\n",
- num, order, offset);
+ pr_debug("msi_bitmap: freeing 0x%x at offset 0x%x\n",
+ num, offset);
spin_lock_irqsave(&bmp->lock, flags);
- bitmap_release_region(bmp->bitmap, offset, order);
+ bitmap_clear(bmp->bitmap, offset, num);
spin_unlock_irqrestore(&bmp->lock, flags);
}
+EXPORT_SYMBOL(msi_bitmap_free_hwirqs);
void msi_bitmap_reserve_hwirq(struct msi_bitmap *bmp, unsigned int hwirq)
{
@@ -180,6 +185,12 @@ void __init test_basics(void)
msi_bitmap_free_hwirqs(&bmp, size / 2, 1);
check(msi_bitmap_alloc_hwirqs(&bmp, 1) == size / 2);
+ /* Check we get a naturally aligned offset */
+ check(msi_bitmap_alloc_hwirqs(&bmp, 2) % 2 == 0);
+ check(msi_bitmap_alloc_hwirqs(&bmp, 4) % 4 == 0);
+ check(msi_bitmap_alloc_hwirqs(&bmp, 8) % 8 == 0);
+ check(msi_bitmap_alloc_hwirqs(&bmp, 9) % 16 == 0);
+
msi_bitmap_free(&bmp);
/* Clients may check bitmap == NULL for "not-allocated" */
--
1.9.1
^ permalink raw reply related
* [PATCH v3 03/16] powerpc/cell: Make spu_flush_all_slbs() generic
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
This moves spu_flush_all_slbs() into a generic call copro_flush_all_slbs().
This will be useful when we add cxl which also needs a similar SLB flush call.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/include/asm/copro.h | 6 ++++++
arch/powerpc/mm/copro_fault.c | 9 +++++++++
arch/powerpc/mm/hash_utils_64.c | 10 +++-------
arch/powerpc/mm/slice.c | 10 +++-------
4 files changed, 21 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/include/asm/copro.h b/arch/powerpc/include/asm/copro.h
index 9badb09..6897431 100644
--- a/arch/powerpc/include/asm/copro.h
+++ b/arch/powerpc/include/asm/copro.h
@@ -20,4 +20,10 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
int copro_calc_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb);
+
+#ifdef CONFIG_PPC_COPRO_BASE
+void copro_flush_all_slbs(struct mm_struct *mm);
+#else
+static inline void copro_flush_all_slbs(struct mm_struct *mm) {}
+#endif
#endif /* _ASM_POWERPC_COPRO_H */
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 367ea01..222ef9b 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -25,6 +25,7 @@
#include <linux/export.h>
#include <asm/reg.h>
#include <asm/copro.h>
+#include <asm/spu.h>
/*
* This ought to be kept in sync with the powerpc specific do_page_fault
@@ -136,3 +137,11 @@ int copro_calc_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
return 0;
}
EXPORT_SYMBOL_GPL(copro_calc_slb);
+
+void copro_flush_all_slbs(struct mm_struct *mm)
+{
+#ifdef CONFIG_SPU_BASE
+ spu_flush_all_slbs(mm);
+#endif
+}
+EXPORT_SYMBOL_GPL(copro_flush_all_slbs);
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index daee7f4..5c0738d 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -51,7 +51,7 @@
#include <asm/cacheflush.h>
#include <asm/cputable.h>
#include <asm/sections.h>
-#include <asm/spu.h>
+#include <asm/copro.h>
#include <asm/udbg.h>
#include <asm/code-patching.h>
#include <asm/fadump.h>
@@ -901,9 +901,7 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
if (get_slice_psize(mm, addr) == MMU_PAGE_4K)
return;
slice_set_range_psize(mm, addr, 1, MMU_PAGE_4K);
-#ifdef CONFIG_SPU_BASE
- spu_flush_all_slbs(mm);
-#endif
+ copro_flush_all_slbs(mm);
if (get_paca_psize(addr) != MMU_PAGE_4K) {
get_paca()->context = mm->context;
slb_flush_and_rebolt();
@@ -1141,9 +1139,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
"to 4kB pages because of "
"non-cacheable mapping\n");
psize = mmu_vmalloc_psize = MMU_PAGE_4K;
-#ifdef CONFIG_SPU_BASE
- spu_flush_all_slbs(mm);
-#endif
+ copro_flush_all_slbs(mm);
}
}
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index b0c75cc..a81791c 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -32,7 +32,7 @@
#include <linux/export.h>
#include <asm/mman.h>
#include <asm/mmu.h>
-#include <asm/spu.h>
+#include <asm/copro.h>
/* some sanity checks */
#if (PGTABLE_RANGE >> 43) > SLICE_MASK_SIZE
@@ -232,9 +232,7 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz
spin_unlock_irqrestore(&slice_convert_lock, flags);
-#ifdef CONFIG_SPU_BASE
- spu_flush_all_slbs(mm);
-#endif
+ copro_flush_all_slbs(mm);
}
/*
@@ -671,9 +669,7 @@ void slice_set_psize(struct mm_struct *mm, unsigned long address,
spin_unlock_irqrestore(&slice_convert_lock, flags);
-#ifdef CONFIG_SPU_BASE
- spu_flush_all_slbs(mm);
-#endif
+ copro_flush_all_slbs(mm);
}
void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
--
1.9.1
^ permalink raw reply related
* [PATCH v3 02/16] powerpc/cell: Move data segment faulting code out of cell platform
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
__spu_trap_data_seg() currently contains code to determine the VSID and ESID
required for a particular EA and mm struct.
This code is generically useful for other co-processors. This moves the code
of the cell platform so it can be used by other powerpc code. It also adds 1TB
segment handling which Cell didn't have.
This also moves the internal struct spu_slb to a generic struct copro_slb which
is now used in the spu and copro code. We use this new struct instead of the
us passing around esid and vsid parameters.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/include/asm/copro.h | 7 ++++-
arch/powerpc/include/asm/mmu-hash64.h | 7 ++++-
arch/powerpc/mm/copro_fault.c | 46 ++++++++++++++++++++++++++++
arch/powerpc/mm/slb.c | 3 --
arch/powerpc/platforms/cell/spu_base.c | 55 ++++++----------------------------
5 files changed, 67 insertions(+), 51 deletions(-)
diff --git a/arch/powerpc/include/asm/copro.h b/arch/powerpc/include/asm/copro.h
index 2858108..9badb09 100644
--- a/arch/powerpc/include/asm/copro.h
+++ b/arch/powerpc/include/asm/copro.h
@@ -10,9 +10,14 @@
#ifndef _ASM_POWERPC_COPRO_H
#define _ASM_POWERPC_COPRO_H
+struct copro_slb
+{
+ u64 esid, vsid;
+};
+
int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
unsigned long dsisr, unsigned *flt);
-int copro_data_segment(struct mm_struct *mm, u64 ea, u64 *esid, u64 *vsid);
+int copro_calc_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb);
#endif /* _ASM_POWERPC_COPRO_H */
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index d765144..6d0b7a2 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -189,7 +189,12 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
#define LP_MASK(i) ((0xFF >> (i)) << LP_SHIFT)
#ifndef __ASSEMBLY__
-
+static inline int slb_vsid_shift(int ssize)
+{
+ if (ssize == MMU_SEGSIZE_256M)
+ return SLB_VSID_SHIFT;
+ return SLB_VSID_SHIFT_1T;
+}
static inline int segment_shift(int ssize)
{
if (ssize == MMU_SEGSIZE_256M)
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index ba7df14..367ea01 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -24,6 +24,7 @@
#include <linux/mm.h>
#include <linux/export.h>
#include <asm/reg.h>
+#include <asm/copro.h>
/*
* This ought to be kept in sync with the powerpc specific do_page_fault
@@ -90,3 +91,48 @@ out_unlock:
return ret;
}
EXPORT_SYMBOL_GPL(copro_handle_mm_fault);
+
+int copro_calc_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
+{
+ u64 vsid;
+ int psize, ssize;
+
+ slb->esid = (ea & ESID_MASK) | SLB_ESID_V;
+
+ switch (REGION_ID(ea)) {
+ case USER_REGION_ID:
+ pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea);
+ psize = get_slice_psize(mm, ea);
+ ssize = user_segment_size(ea);
+ vsid = get_vsid(mm->context.id, ea, ssize);
+ break;
+ case VMALLOC_REGION_ID:
+ pr_devel("%s: 0x%llx -- VMALLOC_REGION_ID\n", __func__, ea);
+ if (ea < VMALLOC_END)
+ psize = mmu_vmalloc_psize;
+ else
+ psize = mmu_io_psize;
+ ssize = mmu_kernel_ssize;
+ vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+ break;
+ case KERNEL_REGION_ID:
+ pr_devel("%s: 0x%llx -- KERNEL_REGION_ID\n", __func__, ea);
+ psize = mmu_linear_psize;
+ ssize = mmu_kernel_ssize;
+ vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+ break;
+ default:
+ pr_debug("%s: invalid region access at %016llx\n", __func__, ea);
+ return 1;
+ }
+
+ vsid = (vsid << slb_vsid_shift(ssize)) | SLB_VSID_USER;
+
+ vsid |= mmu_psize_defs[psize].sllp |
+ ((ssize == MMU_SEGSIZE_1T) ? SLB_VSID_B_1T : 0);
+
+ slb->vsid = vsid;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(copro_calc_slb);
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 0399a67..6e450ca 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -46,9 +46,6 @@ static inline unsigned long mk_esid_data(unsigned long ea, int ssize,
return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | slot;
}
-#define slb_vsid_shift(ssize) \
- ((ssize) == MMU_SEGSIZE_256M? SLB_VSID_SHIFT: SLB_VSID_SHIFT_1T)
-
static inline unsigned long mk_vsid_data(unsigned long ea, int ssize,
unsigned long flags)
{
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index 2930d1e..bdb24de 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -76,10 +76,6 @@ static LIST_HEAD(spu_full_list);
static DEFINE_SPINLOCK(spu_full_list_lock);
static DEFINE_MUTEX(spu_full_list_mutex);
-struct spu_slb {
- u64 esid, vsid;
-};
-
void spu_invalidate_slbs(struct spu *spu)
{
struct spu_priv2 __iomem *priv2 = spu->priv2;
@@ -149,7 +145,7 @@ static void spu_restart_dma(struct spu *spu)
}
}
-static inline void spu_load_slb(struct spu *spu, int slbe, struct spu_slb *slb)
+static inline void spu_load_slb(struct spu *spu, int slbe, struct copro_slb *slb)
{
struct spu_priv2 __iomem *priv2 = spu->priv2;
@@ -167,45 +163,12 @@ static inline void spu_load_slb(struct spu *spu, int slbe, struct spu_slb *slb)
static int __spu_trap_data_seg(struct spu *spu, unsigned long ea)
{
- struct mm_struct *mm = spu->mm;
- struct spu_slb slb;
- int psize;
-
- pr_debug("%s\n", __func__);
-
- slb.esid = (ea & ESID_MASK) | SLB_ESID_V;
+ struct copro_slb slb;
+ int ret;
- switch(REGION_ID(ea)) {
- case USER_REGION_ID:
-#ifdef CONFIG_PPC_MM_SLICES
- psize = get_slice_psize(mm, ea);
-#else
- psize = mm->context.user_psize;
-#endif
- slb.vsid = (get_vsid(mm->context.id, ea, MMU_SEGSIZE_256M)
- << SLB_VSID_SHIFT) | SLB_VSID_USER;
- break;
- case VMALLOC_REGION_ID:
- if (ea < VMALLOC_END)
- psize = mmu_vmalloc_psize;
- else
- psize = mmu_io_psize;
- slb.vsid = (get_kernel_vsid(ea, MMU_SEGSIZE_256M)
- << SLB_VSID_SHIFT) | SLB_VSID_KERNEL;
- break;
- case KERNEL_REGION_ID:
- psize = mmu_linear_psize;
- slb.vsid = (get_kernel_vsid(ea, MMU_SEGSIZE_256M)
- << SLB_VSID_SHIFT) | SLB_VSID_KERNEL;
- break;
- default:
- /* Future: support kernel segments so that drivers
- * can use SPUs.
- */
- pr_debug("invalid region access at %016lx\n", ea);
- return 1;
- }
- slb.vsid |= mmu_psize_defs[psize].sllp;
+ ret = copro_calc_slb(spu->mm, ea, &slb);
+ if (ret)
+ return ret;
spu_load_slb(spu, spu->slb_replace, &slb);
@@ -253,7 +216,7 @@ static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr)
return 0;
}
-static void __spu_kernel_slb(void *addr, struct spu_slb *slb)
+static void __spu_kernel_slb(void *addr, struct copro_slb *slb)
{
unsigned long ea = (unsigned long)addr;
u64 llp;
@@ -272,7 +235,7 @@ static void __spu_kernel_slb(void *addr, struct spu_slb *slb)
* Given an array of @nr_slbs SLB entries, @slbs, return non-zero if the
* address @new_addr is present.
*/
-static inline int __slb_present(struct spu_slb *slbs, int nr_slbs,
+static inline int __slb_present(struct copro_slb *slbs, int nr_slbs,
void *new_addr)
{
unsigned long ea = (unsigned long)new_addr;
@@ -297,7 +260,7 @@ static inline int __slb_present(struct spu_slb *slbs, int nr_slbs,
void spu_setup_kernel_slbs(struct spu *spu, struct spu_lscsa *lscsa,
void *code, int code_size)
{
- struct spu_slb slbs[4];
+ struct copro_slb slbs[4];
int i, nr_slbs = 0;
/* start and end addresses of both mappings */
void *addrs[] = {
--
1.9.1
^ permalink raw reply related
* [PATCH v3 01/16] powerpc/cell: Move spu_handle_mm_fault() out of cell platform
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
In-Reply-To: <1412678902-18672-1-git-send-email-mikey@neuling.org>
From: Ian Munsie <imunsie@au1.ibm.com>
Currently spu_handle_mm_fault() is in the cell platform.
This code is generically useful for other non-cell co-processors on powerpc.
This patch moves this function out of the cell platform into arch/powerpc/mm so
that others may use it.
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/Kconfig | 4 ++++
arch/powerpc/include/asm/copro.h | 18 ++++++++++++++++++
arch/powerpc/include/asm/spu.h | 5 ++---
arch/powerpc/mm/Makefile | 1 +
.../{platforms/cell/spu_fault.c => mm/copro_fault.c} | 14 ++++++--------
arch/powerpc/platforms/cell/Kconfig | 1 +
arch/powerpc/platforms/cell/Makefile | 2 +-
arch/powerpc/platforms/cell/spufs/fault.c | 4 ++--
8 files changed, 35 insertions(+), 14 deletions(-)
create mode 100644 arch/powerpc/include/asm/copro.h
rename arch/powerpc/{platforms/cell/spu_fault.c => mm/copro_fault.c} (89%)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 4bc7b62..8f094e9 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -603,6 +603,10 @@ config PPC_SUBPAGE_PROT
to set access permissions (read/write, readonly, or no access)
on the 4k subpages of each 64k page.
+config PPC_COPRO_BASE
+ bool
+ default n
+
config SCHED_SMT
bool "SMT (Hyperthreading) scheduler support"
depends on PPC64 && SMP
diff --git a/arch/powerpc/include/asm/copro.h b/arch/powerpc/include/asm/copro.h
new file mode 100644
index 0000000..2858108
--- /dev/null
+++ b/arch/powerpc/include/asm/copro.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ASM_POWERPC_COPRO_H
+#define _ASM_POWERPC_COPRO_H
+
+int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
+ unsigned long dsisr, unsigned *flt);
+
+int copro_data_segment(struct mm_struct *mm, u64 ea, u64 *esid, u64 *vsid);
+
+#endif /* _ASM_POWERPC_COPRO_H */
diff --git a/arch/powerpc/include/asm/spu.h b/arch/powerpc/include/asm/spu.h
index 37b7ca3..a6e6e2b 100644
--- a/arch/powerpc/include/asm/spu.h
+++ b/arch/powerpc/include/asm/spu.h
@@ -27,6 +27,8 @@
#include <linux/workqueue.h>
#include <linux/device.h>
#include <linux/mutex.h>
+#include <asm/reg.h>
+#include <asm/copro.h>
#define LS_SIZE (256 * 1024)
#define LS_ADDR_MASK (LS_SIZE - 1)
@@ -277,9 +279,6 @@ void spu_remove_dev_attr(struct device_attribute *attr);
int spu_add_dev_attr_group(struct attribute_group *attrs);
void spu_remove_dev_attr_group(struct attribute_group *attrs);
-int spu_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
- unsigned long dsisr, unsigned *flt);
-
/*
* Notifier blocks:
*
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index d0130ff..325e861 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -34,3 +34,4 @@ obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += hugepage-hash64.o
obj-$(CONFIG_PPC_SUBPAGE_PROT) += subpage-prot.o
obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
obj-$(CONFIG_HIGHMEM) += highmem.o
+obj-$(CONFIG_PPC_COPRO_BASE) += copro_fault.o
diff --git a/arch/powerpc/platforms/cell/spu_fault.c b/arch/powerpc/mm/copro_fault.c
similarity index 89%
rename from arch/powerpc/platforms/cell/spu_fault.c
rename to arch/powerpc/mm/copro_fault.c
index 641e727..ba7df14 100644
--- a/arch/powerpc/platforms/cell/spu_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -1,5 +1,5 @@
/*
- * SPU mm fault handler
+ * CoProcessor (SPU/AFU) mm fault handler
*
* (C) Copyright IBM Deutschland Entwicklung GmbH 2007
*
@@ -23,16 +23,14 @@
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/export.h>
-
-#include <asm/spu.h>
-#include <asm/spu_csa.h>
+#include <asm/reg.h>
/*
* This ought to be kept in sync with the powerpc specific do_page_fault
* function. Currently, there are a few corner cases that we haven't had
* to handle fortunately.
*/
-int spu_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
+int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
unsigned long dsisr, unsigned *flt)
{
struct vm_area_struct *vma;
@@ -58,12 +56,12 @@ int spu_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
goto out_unlock;
}
- is_write = dsisr & MFC_DSISR_ACCESS_PUT;
+ is_write = dsisr & DSISR_ISSTORE;
if (is_write) {
if (!(vma->vm_flags & VM_WRITE))
goto out_unlock;
} else {
- if (dsisr & MFC_DSISR_ACCESS_DENIED)
+ if (dsisr & DSISR_PROTFAULT)
goto out_unlock;
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto out_unlock;
@@ -91,4 +89,4 @@ out_unlock:
up_read(&mm->mmap_sem);
return ret;
}
-EXPORT_SYMBOL_GPL(spu_handle_mm_fault);
+EXPORT_SYMBOL_GPL(copro_handle_mm_fault);
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 9978f59..870b6db 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -86,6 +86,7 @@ config SPU_FS_64K_LS
config SPU_BASE
bool
default n
+ select PPC_COPRO_BASE
config CBE_RAS
bool "RAS features for bare metal Cell BE"
diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile
index fe053e7..2d16884 100644
--- a/arch/powerpc/platforms/cell/Makefile
+++ b/arch/powerpc/platforms/cell/Makefile
@@ -20,7 +20,7 @@ spu-manage-$(CONFIG_PPC_CELL_COMMON) += spu_manage.o
obj-$(CONFIG_SPU_BASE) += spu_callbacks.o spu_base.o \
spu_notify.o \
- spu_syscalls.o spu_fault.o \
+ spu_syscalls.o \
$(spu-priv1-y) \
$(spu-manage-y) \
spufs/
diff --git a/arch/powerpc/platforms/cell/spufs/fault.c b/arch/powerpc/platforms/cell/spufs/fault.c
index 8cb6260..e45894a 100644
--- a/arch/powerpc/platforms/cell/spufs/fault.c
+++ b/arch/powerpc/platforms/cell/spufs/fault.c
@@ -138,7 +138,7 @@ int spufs_handle_class1(struct spu_context *ctx)
if (ctx->state == SPU_STATE_RUNNABLE)
ctx->spu->stats.hash_flt++;
- /* we must not hold the lock when entering spu_handle_mm_fault */
+ /* we must not hold the lock when entering copro_handle_mm_fault */
spu_release(ctx);
access = (_PAGE_PRESENT | _PAGE_USER);
@@ -149,7 +149,7 @@ int spufs_handle_class1(struct spu_context *ctx)
/* hashing failed, so try the actual fault handler */
if (ret)
- ret = spu_handle_mm_fault(current->mm, ea, dsisr, &flt);
+ ret = copro_handle_mm_fault(current->mm, ea, dsisr, &flt);
/*
* This is nasty: we need the state_mutex for all the bookkeeping even
--
1.9.1
^ permalink raw reply related
* [PATCH v3 0/16] POWER8 Coherent Accelerator device driver
From: Michael Neuling @ 2014-10-07 10:48 UTC (permalink / raw)
To: greg, arnd, mpe, benh
Cc: cbe-oss-dev, mikey, Aneesh Kumar K.V, imunsie, linux-kernel,
linuxppc-dev, jk, anton
This is the latest version of the cxl driver. Change log below:
v3:
- Updates based on comments from mpe, benh, aneesh and offline reviews.
- Fixed bug freeing AFU IRQs that also freed the multiplexed PSL IRQ
- Change copro_flush_all_slbs to a static inline as suggested by mpe
- Implement sanitisation routines to clear out more registers and do full
adapter wide tlbia and slbia when initialising hardware
- Add self testcase to msi_bitmap to test allocations are aligned to a power of
2 and cleanup comment as suggested by mpe
- Clean up cxl_use_count
- Split out detach_process_native into two logical functions
- Improve comment in set_msi_irq_chip as requested by mpe
- Move cxl functions in pci-ioda.c to be under just one #ifdef CONFIG_CXL_BASE
- Cleanup hash_page and hash_page_mm from mpes and Aneesh' reviews
- Remove dead code in cxl_alloc_sst
- Add timeout in afu_slbia_native
- Remove cxl backend and driver ops abstractions
- Removed separate cxl-pci module
- Merged cxl pci module init calls into main driver init
- Refactor afu_read() to be a bit simpler and more closely follow exising
patterns in the kernel
- Userspace API updates from reviews:
- Added ioctl to get the process element number, and removed it as a return
from the start work ioctl
- Alter cxl_event to have one common header struct
- Dropped check error ioctl
- Added current and binary compatible API version numbers to sysfs
- read() now takes a 4K (or greater) buffer
- Pack event structs to reduce unecessary reserved fields
- Event sizes can now differ
- All event sizes are 64bit multiples to allow future event coalescing
- Add flags fields to indicate which fields contain valid data
- Add BUILD_BUG_ONs to protect against inadvertantly changing API without
bumping version number and/or flags
- Update documentation
- Skip CXL SLBIA codepath if CXL is not in use
- Split cxl_slbia_core into two functions to be easier to read
- Refactor copro_data_segment (renamed to copro_calc_slb) since we are no
longer merging with hash_page and cleaned up parameters.
- Some renames:
- struct cxl_t -> struct cxl
- struct cxl_afu_t -> struct cxl_afu
- struct cxl_context_t -> struct cxl_context
- copro_data_segment -> copro_calc_slb
- ctx->ph -> ctx->pe
- Added ctx->status mutex lock around for start and release context
v2:
- Updates based on comments from, Anton, Gavin, Aneesh, jk and offline reviews
- Simplified copro_data_segment() and merged code with hash_page_mm()
(New patch 10/17)
- PCIe code simplifications based on Gavin's review
- Removed redundant comment in msi_bitmap_alloc_hwirqs()
- Fix for locking in idr_remove in core driver
- Ensure PSL is enabled when PHB is flipped to CXL mode
- Added CONFIG_PPC_COPRO_BASE to compile copro_fault.c
- Merged SPU and cxl slb flushing calls into copro_flush_all_slbs()
(New patch 03/17)
- Moved slb_vsid_shift() to static inline from #define
- Don't write paca->context when demoting segments and mm != current
- Fix minor typos in documentation
v1:
- Initial post
This add support for the Coherent Accelerator (cxl) attached to POWER8
processors. This coherent accelerator interface is designed to allow the
coherent connection of FPGA based accelerators (and other devices) to a POWER
systems.
IBM refers to this as the Coherent Accelerator Processor Interface or CAPI. In
this driver it's referred to by the name cxl to avoid confusion with the ISDN
CAPI subsystem.
An overview of the patches:
Patches 1-3: Split some of the old Cell co-processor code out so it can be
reused.
Patches 4-10: Add infrastructure to arch/powerpc needed by cxl.
Patches 11: Add call backs needed for invalidating cxl mm contexts.
Patch 12: Add cxl specific support that needs to be built in to the
kernel (can't be a module).
Patches 13-15: Add the majority of the device driver and API header.
Patch 16: Documentation.
The documentation in this last patch gives an overview of the hardware
architecture as well as the userspace API.
The cxl driver has a user-space interface described in include/uapi/misc/cxl.h
and Documentation/powerpc/cxl.txt. There are two ioctls which can be used to
talk to the driver once the new /dev/cxl/afu0.0 device is opened. This device
can also be read and mmaped.
There's also sysfs entries used to communicate information about the cxl
configuration to userspace. These are documented in
Documentation/ABI/testing/sysfs-class-cxl.
Many contributed to this device driver but Ian Munsie is the principal author.
Driver can also be found here (based on 3.17-rc5):
git://github.com/mikey/linux.git cxl
https://github.com/mikey/linux/commits/cxl
(Series rebases on recent linux-next with one trivial include file conflict)
Please consider for inclusion. Feedback welcome!
Regards,
Mikey
^ permalink raw reply
* [PATCH] powerpc/book3s: Don't clear MSR_RI in hmi handler.
From: Mahesh J Salgaonkar @ 2014-10-07 10:25 UTC (permalink / raw)
To: Michael Ellerman, linuxppc-dev, Benjamin Herrenschmidt; +Cc: Paul Mackerras
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
In HMI interrupt handler we don't touch SRR0/SRR1, instead we touch
HSRR0/HSRR1. Hence we don't need to clear MSR_RI bit.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/kernel/exceptions-64s.S | 5 -----
1 file changed, 5 deletions(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 050f79a..72e783e 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1270,11 +1270,6 @@ hmi_exception_early:
addi r3,r1,STACK_FRAME_OVERHEAD
bl hmi_exception_realmode
/* Windup the stack. */
- /* Clear MSR_RI before setting SRR0 and SRR1. */
- li r0,MSR_RI
- mfmsr r9 /* get MSR value */
- andc r9,r9,r0
- mtmsrd r9,1 /* Clear MSR_RI */
/* Move original HSRR0 and HSRR1 into the respective regs */
ld r9,_MSR(r1)
mtspr SPRN_HSRR1,r9
^ permalink raw reply related
* Re: [PATCH v2 3/5] powerpc/powernv: Add winkle infrastructure
From: Shreyas B Prabhu @ 2014-10-07 9:56 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: linuxppc-dev, Paul Mackerras, linux-kernel
In-Reply-To: <1412660033.30859.154.camel@pasglop>
On Tuesday 07 October 2014 11:03 AM, Benjamin Herrenschmidt wrote:
> On Wed, 2014-10-01 at 13:16 +0530, Shreyas B. Prabhu wrote:
>> Winkle causes power to be gated off to the entire chiplet. Hence the
>> hypervisor/firmware state in the entire chiplet is lost.
>>
>> This patch adds necessary infrastructure to support waking up from
>> hypervisor state loss. Specifically does following:
>> - Before entering winkle, save state of registers that need to be
>> restored on wake up (SDR1, HFSCR)
>
> Add ... to your list, it's not exhaustive, is it ?
I use interrupt stack frame for only SDR1 and HFSCR. The rest of the
SPRs are restored via PORE in the next patch. I'll change the comments
to better reflect this.
>
>> - SRR1 bits 46:47 which is used to identify which power saving mode cpu
>> woke up from is '11' for both winkle and sleep. Hence introduce a flag
>> in PACA to distinguish b/w winkle and sleep.
>>
>> - Upon waking up, restore all saved registers, recover slb
>>
>> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
>> Cc: Paul Mackerras <paulus@samba.org>
>> Cc: Michael Ellerman <mpe@ellerman.id.au>
>> Cc: linuxppc-dev@lists.ozlabs.org
>> Suggested-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
>> Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
>> ---
>> arch/powerpc/include/asm/machdep.h | 1 +
>> arch/powerpc/include/asm/paca.h | 3 ++
>> arch/powerpc/include/asm/ppc-opcode.h | 2 +
>> arch/powerpc/include/asm/processor.h | 2 +
>> arch/powerpc/kernel/asm-offsets.c | 1 +
>> arch/powerpc/kernel/exceptions-64s.S | 8 ++--
>> arch/powerpc/kernel/idle.c | 11 +++++
>> arch/powerpc/kernel/idle_power7.S | 81 +++++++++++++++++++++++++++++++++-
>> arch/powerpc/platforms/powernv/setup.c | 24 ++++++++++
>> 9 files changed, 127 insertions(+), 6 deletions(-)
>>
>> diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
>> index f37014f..0a3ced9 100644
>> --- a/arch/powerpc/include/asm/machdep.h
>> +++ b/arch/powerpc/include/asm/machdep.h
>> @@ -301,6 +301,7 @@ struct machdep_calls {
>> /* Idle handlers */
>> void (*setup_idle)(void);
>> unsigned long (*power7_sleep)(void);
>> + unsigned long (*power7_winkle)(void);
>> };
>
> Why does it need to be ppc_md ? Same comments as for sleep
>
>> extern void e500_idle(void);
>> diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
>> index a5139ea..3358f09 100644
>> --- a/arch/powerpc/include/asm/paca.h
>> +++ b/arch/powerpc/include/asm/paca.h
>> @@ -158,6 +158,9 @@ struct paca_struct {
>> * early exception handler for use by high level C handler
>> */
>> struct opal_machine_check_event *opal_mc_evt;
>> +
>> + /* Flag to distinguish b/w sleep and winkle */
>> + u8 offline_state;
>
> Not fan of the name. I'd rather you call it "wakeup_state_loss" or
> something a bit more explicit about what that actually means if it's
> going to be a boolean value. Otherwise make it an enumeration of
> constants.
>
Okay. I'll change this.
>> #endif
>> #ifdef CONFIG_PPC_BOOK3S_64
>> /* Exclusive emergency stack pointer for machine check exception. */
>> diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
>> index 6f85362..5155be7 100644
>> --- a/arch/powerpc/include/asm/ppc-opcode.h
>> +++ b/arch/powerpc/include/asm/ppc-opcode.h
>> @@ -194,6 +194,7 @@
>>
>> #define PPC_INST_NAP 0x4c000364
>> #define PPC_INST_SLEEP 0x4c0003a4
>> +#define PPC_INST_WINKLE 0x4c0003e4
>>
>> /* A2 specific instructions */
>> #define PPC_INST_ERATWE 0x7c0001a6
>> @@ -374,6 +375,7 @@
>>
>> #define PPC_NAP stringify_in_c(.long PPC_INST_NAP)
>> #define PPC_SLEEP stringify_in_c(.long PPC_INST_SLEEP)
>> +#define PPC_WINKLE stringify_in_c(.long PPC_INST_WINKLE)
>>
>> /* BHRB instructions */
>> #define PPC_CLRBHRB stringify_in_c(.long PPC_INST_CLRBHRB)
>> diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
>> index 41953cd..00e3df9 100644
>> --- a/arch/powerpc/include/asm/processor.h
>> +++ b/arch/powerpc/include/asm/processor.h
>> @@ -455,6 +455,8 @@ extern void arch_setup_idle(void);
>> extern void power7_nap(int check_irq);
>> extern unsigned long power7_sleep(void);
>> extern unsigned long __power7_sleep(void);
>> +extern unsigned long power7_winkle(void);
>> +extern unsigned long __power7_winkle(void);
>> extern void flush_instruction_cache(void);
>> extern void hard_reset_now(void);
>> extern void poweroff_now(void);
>> diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
>> index 9d7dede..ea98817 100644
>> --- a/arch/powerpc/kernel/asm-offsets.c
>> +++ b/arch/powerpc/kernel/asm-offsets.c
>> @@ -731,6 +731,7 @@ int main(void)
>> DEFINE(OPAL_MC_SRR0, offsetof(struct opal_machine_check_event, srr0));
>> DEFINE(OPAL_MC_SRR1, offsetof(struct opal_machine_check_event, srr1));
>> DEFINE(PACA_OPAL_MC_EVT, offsetof(struct paca_struct, opal_mc_evt));
>> + DEFINE(PACAOFFLINESTATE, offsetof(struct paca_struct, offline_state));
>> #endif
>>
>> return 0;
>> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
>> index c64f3cc0..261f348 100644
>> --- a/arch/powerpc/kernel/exceptions-64s.S
>> +++ b/arch/powerpc/kernel/exceptions-64s.S
>> @@ -115,9 +115,7 @@ BEGIN_FTR_SECTION
>> #endif
>>
>> /* Running native on arch 2.06 or later, check if we are
>> - * waking up from nap. We only handle no state loss and
>> - * supervisor state loss. We do -not- handle hypervisor
>> - * state loss at this time.
>> + * waking up from power saving mode.
>> */
>> mfspr r13,SPRN_SRR1
>> rlwinm. r13,r13,47-31,30,31
>> @@ -133,8 +131,8 @@ BEGIN_FTR_SECTION
>> b power7_wakeup_noloss
>> 2: b power7_wakeup_loss
>>
>> - /* Fast Sleep wakeup on PowerNV */
>> -8: b power7_wakeup_tb_loss
>> + /* Fast Sleep / Winkle wakeup on PowerNV */
>> +8: b power7_wakeup_hv_state_loss
>>
>> 9:
>> END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
>> diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
>> index 1f268e0..ed46217 100644
>> --- a/arch/powerpc/kernel/idle.c
>> +++ b/arch/powerpc/kernel/idle.c
>> @@ -98,6 +98,17 @@ unsigned long power7_sleep(void)
>> return ret;
>> }
>>
>> +unsigned long power7_winkle(void)
>> +{
>> + unsigned long ret;
>> +
>> + if (ppc_md.power7_winkle)
>> + ret = ppc_md.power7_winkle();
>> + else
>> + ret = __power7_winkle();
>> + return ret;
>> +}
>> +
>> int powersave_nap;
>>
>> #ifdef CONFIG_SYSCTL
>> diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
>> index c3481c9..87b2556 100644
>> --- a/arch/powerpc/kernel/idle_power7.S
>> +++ b/arch/powerpc/kernel/idle_power7.S
>> @@ -18,6 +18,13 @@
>> #include <asm/hw_irq.h>
>> #include <asm/kvm_book3s_asm.h>
>> #include <asm/opal.h>
>> +#include <asm/mmu-hash64.h>
>> +
>> +/*
>> + * Use volatile GPRs' space to save essential SPRs before entering winkle
>> + */
>> +#define _SDR1 GPR3
>> +#define _TSCR GPR4
>>
>> #undef DEBUG
>>
>> @@ -39,6 +46,7 @@
>> * Pass requested state in r3:
>> * 0 - nap
>> * 1 - sleep
>> + * 2 - winkle
>> *
>> * To check IRQ_HAPPENED in r4
>> * 0 - don't check
>> @@ -109,9 +117,27 @@ _GLOBAL(power7_enter_nap_mode)
>> #endif
>> cmpwi cr0,r3,1
>> beq 2f
>> + cmpwi cr0,r3,2
>> + beq 3f
>> IDLE_STATE_ENTER_SEQ(PPC_NAP)
>> /* No return */
>> -2: IDLE_STATE_ENTER_SEQ(PPC_SLEEP)
>> +2:
>> + li r4,1
>> + stb r4,PACAOFFLINESTATE(r13)
>> + IDLE_STATE_ENTER_SEQ(PPC_SLEEP)
>> + /* No return */
>> +
>> +3:
>> + mfspr r4,SPRN_SDR1
>> + std r4,_SDR1(r1)
>> +
>> + mfspr r4,SPRN_TSCR
>> + std r4,_TSCR(r1)
>> +
>> + /* Enter winkle */
>> + li r4,0
>> + stb r4,PACAOFFLINESTATE(r13)
>> + IDLE_STATE_ENTER_SEQ(PPC_WINKLE)
>> /* No return */
>>
>> _GLOBAL(power7_idle)
>> @@ -187,6 +213,59 @@ ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66); \
>> 20: nop;
>>
>>
>> +_GLOBAL(__power7_winkle)
>> + li r3,2
>> + li r4,1
>> + b power7_powersave_common
>> + /* No return */
>> +
>> +_GLOBAL(power7_wakeup_hv_state_loss)
>> + /* Check paca flag to diffentiate b/w fast sleep and winkle */
>> + lbz r4,PACAOFFLINESTATE(13)
>> + cmpwi cr0,r4,0
>> + bne power7_wakeup_tb_loss
>> +
>> + ld r2,PACATOC(r13);
>> + ld r1,PACAR1(r13)
>> +
>> + bl __restore_cpu_power8
>
> So if I understand correctly, you use a per-cpu flag not a per-core flag
> which means we will assume a pessimistic case of having to restore stuff
> even if the core didn't actually enter winkle (because the last thread
> to go down went to sleep). This is sub-optimal. Also see below:
>
>> + /* Time base re-sync */
>> + li r3,OPAL_RESYNC_TIMEBASE
>> + bl opal_call_realmode;
>
> You will also resync the timebase (and restore all the core shared SPRs)
> for each thread. This is problematic, especially with KVM as you could
> have a situation where:
>
> - The first thread comes out and starts diving into KVM
>
> - The other threads start coming out while the first one is doing the
> above.
>
> Thus the first thread might already be manipulating some core registers
> (SDR1 etc...) while the secondaries come back and ... whack it. Worse,
> the primary might have applied the TB offset using TBU40 while the
> secondaries resync the timebase back to the host value, incurring a
> loss of TB for the guest.
>
Such a race is prevented with kvm_hstate.hwthread_req and
kvm_hstate.hwthread_state paca flags.
The current flow when a guest is scheduled on a core :
-> Primary thread sets kvm_hstate.hwthread_req paca flag for all the
secondary threads.
-> Waits for all the secondary threads to to change state to
!KVM_HWTHREAD_IN_KERNEL
-> and later call __kvmppc_vcore_entry which down the line changes SDR1
and other per core registers. Therefore kvm_hstate.hwthread_req is set
to 1 for all the threads in the core *before* SDR1 is switched.
And when a secondary thread is woken up to execute guest, in 0x100 we
check hwthread_req and branch to kvm_start_guest if set. Therefore
secondary threads woken up for guest do not execute the
power7_wakeup_hv_state_loss and therefore there is no danger of
overwriting SDR1 or TBU40.
Now lets consider the case where a guest is scheduled on the core and a
secondary thread is woken up even though there is no vcpu to run on it.
(Say its woken up by a stray IPI). In this case, again in 0x100 we
branch to kvm_start_guest, and here when there is no vcpu to run, it
executes nap. So again there no danger of overwriting SDR1.
>> + /* Restore SLB from PACA */
>> + ld r8,PACA_SLBSHADOWPTR(r13)
>> +
>> + .rept SLB_NUM_BOLTED
>> + li r3, SLBSHADOW_SAVEAREA
>> + LDX_BE r5, r8, r3
>> + addi r3, r3, 8
>> + LDX_BE r6, r8, r3
>> + andis. r7,r5,SLB_ESID_V@h
>> + beq 1f
>> + slbmte r6,r5
>> +1: addi r8,r8,16
>> + .endr
>> +
>> + ld r4,_SDR1(r1)
>> + mtspr SPRN_SDR1,r4
>> +
>> + ld r4,_TSCR(r1)
>> + mtspr SPRN_TSCR,r4
>> +
>> + REST_NVGPRS(r1)
>> + REST_GPR(2, r1)
>> + ld r3,_CCR(r1)
>> + ld r4,_MSR(r1)
>> + ld r5,_NIP(r1)
>> + addi r1,r1,INT_FRAME_SIZE
>> + mtcr r3
>> + mfspr r3,SPRN_SRR1 /* Return SRR1 */
>> + mtspr SPRN_SRR1,r4
>> + mtspr SPRN_SRR0,r5
>> + rfid
>> +
>> _GLOBAL(power7_wakeup_tb_loss)
>> ld r2,PACATOC(r13);
>> ld r1,PACAR1(r13)
>> diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
>> index 9d9a898..f45b52d 100644
>> --- a/arch/powerpc/platforms/powernv/setup.c
>> +++ b/arch/powerpc/platforms/powernv/setup.c
>> @@ -370,6 +370,29 @@ static unsigned long pnv_power7_sleep(void)
>> return srr1;
>> }
>>
>> +/*
>> + * We need to keep track of offline cpus also for calling
>> + * fastsleep workaround appropriately
>> + */
>> +static unsigned long pnv_power7_winkle(void)
>> +{
>> + int cpu, primary_thread;
>> + unsigned long srr1;
>> +
>> + cpu = smp_processor_id();
>> + primary_thread = cpu_first_thread_sibling(cpu);
>> +
>> + if (need_fastsleep_workaround) {
>> + pnv_apply_fastsleep_workaround(1, primary_thread);
>> + srr1 = __power7_winkle();
>> + pnv_apply_fastsleep_workaround(0, primary_thread);
>> + } else {
>> + srr1 = __power7_winkle();
>> + }
>> + return srr1;
>> +}
>> +
>> +
>> static void __init pnv_setup_machdep_opal(void)
>> {
>> ppc_md.get_boot_time = opal_get_boot_time;
>> @@ -384,6 +407,7 @@ static void __init pnv_setup_machdep_opal(void)
>> ppc_md.handle_hmi_exception = opal_handle_hmi_exception;
>> ppc_md.setup_idle = pnv_setup_idle;
>> ppc_md.power7_sleep = pnv_power7_sleep;
>> + ppc_md.power7_winkle = pnv_power7_winkle;
>> }
>>
>> #ifdef CONFIG_PPC_POWERNV_RTAS
>
>
^ permalink raw reply
* Re: [v2] powerpc/vphn: fix endian issue in NUMA device node code
From: Michael Ellerman @ 2014-10-07 9:28 UTC (permalink / raw)
To: Greg Kurz, linuxppc-dev; +Cc: Nishanth Aravamudan
In-Reply-To: <20141003091250.28354.13766.stgit@bahia.local>
On Fri, 2014-03-10 at 09:13:17 UTC, Greg Kurz wrote:
> The associativity domain numbers are obtained from the hypervisor through
> registers and written into memory by the guest: the packed array passed to
> vphn_unpack_associativity() is then native-endian, unlike what was assumed
> in the following commit:
>
> This patch does two things:
> - extract values from the packed array with shifts, in order to be endian
> neutral
> - convert the resulting values to be32 as expected
>
> Suggested-by: Anton Blanchard <anton@samba.org>
> Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
> Reviewed-by: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
> Tested-by: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
Hi Greg,
I'm a bit dense, it's after 8pm, but this seems like it's more complicated than
it needs to be?
We get six 64-bit registers back from the hypervisor, they're cpu endian
obviously, and each is defined to consist of four 2 byte fields.
So to unpack them, can't we just iterate over those six 64-bit values, which if
we load them as 64-bit values will be back in cpu endian?
cheers
^ permalink raw reply
* Re: [PATCH 35/44] m68k: Register with kernel poweroff handler
From: Geert Uytterhoeven @ 2014-10-07 9:19 UTC (permalink / raw)
To: Guenter Roeck
Cc: linux-m32r-ja, Linux MIPS Mailing List, linux-efi,
linux-ia64@vger.kernel.org, linux-xtensa@linux-xtensa.org,
driverdevel, linux-s390, lguest, linux-c6x-dev,
open list:QUALCOMM HEXAGON..., Linux-sh list,
ACPI Devel Maling List, xen-devel, devicetree@vger.kernel.org,
uml-devel, Linux PM list,
adi-buildroot-devel@lists.sourceforge.net, linux-m68k,
moderated list:PANASONIC MN10300..., linux-tegra,
openipmi-developer, open list:METAG ARCHITECTURE,
linux-arm-kernel@lists.infradead.org, Parisc List, Cris,
linux-kernel@vger.kernel.org, alpha,
linuxppc-dev@lists.ozlabs.org, Joshua Thompson
In-Reply-To: <1412659726-29957-36-git-send-email-linux@roeck-us.net>
On Tue, Oct 7, 2014 at 7:28 AM, Guenter Roeck <linux@roeck-us.net> wrote:
> Register with kernel poweroff handler instead of setting pm_power_off
> directly.
>
> Cc: Geert Uytterhoeven <geert@linux-m68k.org>
> Cc: Joshua Thompson <funaho@jurai.org>
> Signed-off-by: Guenter Roeck <linux@roeck-us.net>
As someone already mentioned, having #defines instead of hardcoded
numbers for the priorities would be nice.
Apart from that:
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
> + register_poweroff_handler_simple(nf_poweroff, 128);
> + register_poweroff_handler_simple(mac_poweroff, 128);
Gr{oetje,eeting}s,
Geert
--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org
In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
-- Linus Torvalds
^ permalink raw reply
* Re: [PATCH 08/44] kernel: Move pm_power_off to common code
From: Geert Uytterhoeven @ 2014-10-07 8:32 UTC (permalink / raw)
To: Guenter Roeck
Cc: linux-m32r-ja, Linux MIPS Mailing List, linux-efi,
linux-ia64@vger.kernel.org, Steven Miao,
linux-xtensa@linux-xtensa.org, Boris Ostrovsky, Catalin Marinas,
Will Deacon, David Howells, Max Filippov, Paul Mackerras,
Ralf Baechle, Pavel Machek, H. Peter Anvin, Guan Xuetao,
Thomas Gleixner, Lennox Wu, Hans-Christian Egtvedt, driverdevel,
linux-s390, Jesper Nilsson, lguest, Russell King, linux-c6x-dev,
Len Brown, David S. Miller, open list:QUALCOMM HEXAGON...,
Hirokazu Takata, Linux-sh list, James E.J. Bottomley,
ACPI Devel Maling List, Ingo Molnar, Mark Salter, xen-devel,
Matt Turner, Chen Liqin, Jonas Bonn, Haavard Skinnemoen,
devicetree@vger.kernel.org, James Hogan, uml-devel, Linux PM list,
Aurelien Jacquiot, Heiko Carstens, Jeff Dike,
adi-buildroot-devel@lists.sourceforge.net, Chris Metcalf,
Konrad Rzeszutek Wilk, Mikael Starvik, Richard Weinberger,
linux-m68k, moderated list:PANASONIC MN10300..., Ivan Kokshaysky,
linux-tegra, openipmi-developer, open list:METAG ARCHITECTURE,
linux-arm-kernel@lists.infradead.org, Richard Henderson,
Chris Zankel, Michal Simek, Tony Luck, Parisc List, Cris,
Vineet Gupta, Rafael J. Wysocki, linux-kernel@vger.kernel.org,
Fenghua Yu, Richard Kuo, David Vrabel, alpha, Martin Schwidefsky,
Koichi Yasutake, linuxppc-dev@lists.ozlabs.org, Helge Deller
In-Reply-To: <1412659726-29957-9-git-send-email-linux@roeck-us.net>
On Tue, Oct 7, 2014 at 7:28 AM, Guenter Roeck <linux@roeck-us.net> wrote:
> pm_power_off is defined for all architectures. Move it to common code.
>
> Have all architectures call do_kernel_poweroff instead of pm_power_off.
> Some architectures point pm_power_off to machine_power_off. For those,
> call do_kernel_poweroff from machine_power_off instead.
> arch/m68k/kernel/process.c | 6 +-----
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Gr{oetje,eeting}s,
Geert
--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org
In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
-- Linus Torvalds
^ permalink raw reply
* Re: [PATCH 04/44] m68k: Replace mach_power_off with pm_power_off
From: Geert Uytterhoeven @ 2014-10-07 8:29 UTC (permalink / raw)
To: Guenter Roeck
Cc: linux-m32r-ja, Linux MIPS Mailing List, linux-efi,
linux-ia64@vger.kernel.org, linux-xtensa@linux-xtensa.org,
Greg Ungerer, driverdevel, linux-s390, lguest, linux-c6x-dev,
open list:QUALCOMM HEXAGON..., Linux-sh list,
ACPI Devel Maling List, xen-devel, devicetree@vger.kernel.org,
uml-devel, Linux PM list,
adi-buildroot-devel@lists.sourceforge.net, linux-m68k,
moderated list:PANASONIC MN10300..., linux-tegra,
openipmi-developer, open list:METAG ARCHITECTURE,
linux-arm-kernel@lists.infradead.org, Parisc List, Cris,
linux-kernel@vger.kernel.org, alpha,
linuxppc-dev@lists.ozlabs.org, Joshua Thompson
In-Reply-To: <1412659726-29957-5-git-send-email-linux@roeck-us.net>
On Tue, Oct 7, 2014 at 7:28 AM, Guenter Roeck <linux@roeck-us.net> wrote:
> Replace mach_power_off with pm_power_off to simplify the subsequent
> move of pm_power_off to generic code.
Thanks!
> Cc: Geert Uytterhoeven <geert@linux-m68k.org>
> Cc: Greg Ungerer <gerg@uclinux.org>
> Cc: Joshua Thompson <funaho@jurai.org>
> Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Looks OK, so since you said it builds ;-)
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Gr{oetje,eeting}s,
Geert
--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org
In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
-- Linus Torvalds
^ permalink raw reply
* [PATCH] powerpc/book3s: Fix an issue where guest is paused on receiving HMI.
From: Mahesh J Salgaonkar @ 2014-10-07 8:17 UTC (permalink / raw)
To: Michael Ellerman, linuxppc-dev, Benjamin Herrenschmidt; +Cc: Paul Mackerras
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
When we get an HMI while in guest enter/exit path, we see that guest enters
into paused state. The reason is, in kvmppc_handle_exit_hv it falls through
default path and returns to host instead of resuming guest. This causes
guest to enter into paused state. HMI is hypervisor only interrupt and it
is safe to resume guest since host has handled it already. This patch adds
switch case to handle HMI and resume guest.
Without this patch we see guest entering into pasued state with following
console messages:
[ 3003.329351] Severe Hypervisor Maintenance interrupt [Recovered]
[ 3003.329356] Error detail: Timer facility experienced an error
[ 3003.329359] HMER: 0840000000000000
[ 3003.329360] TFMR: 4a12000980a84000
[ 3003.329366] vcpu c0000007c35094c0 (40):
[ 3003.329368] pc = c0000000000c2ba0 msr = 8000000000009032 trap = e60
[ 3003.329370] r 0 = c00000000021ddc0 r16 = 0000000000000046
[ 3003.329372] r 1 = c00000007a02bbd0 r17 = 00003ffff27d5d98
[ 3003.329375] r 2 = c0000000010980b8 r18 = 00001fffffc9a0b0
[ 3003.329377] r 3 = c00000000142d6b8 r19 = c00000000142d6b8
[ 3003.329379] r 4 = 0000000000000002 r20 = 0000000000000000
[ 3003.329381] r 5 = c00000000524a110 r21 = 0000000000000000
[ 3003.329383] r 6 = 0000000000000001 r22 = 0000000000000000
[ 3003.329386] r 7 = 0000000000000000 r23 = c00000000524a110
[ 3003.329388] r 8 = 0000000000000000 r24 = 0000000000000001
[ 3003.329391] r 9 = 0000000000000001 r25 = c00000007c31da38
[ 3003.329393] r10 = c0000000014280b8 r26 = 0000000000000002
[ 3003.329395] r11 = 746f6f6c2f68656c r27 = c00000000524a110
[ 3003.329397] r12 = 0000000028004484 r28 = c00000007c31da38
[ 3003.329399] r13 = c00000000fe01400 r29 = 0000000000000002
[ 3003.329401] r14 = 0000000000000046 r30 = c000000003011e00
[ 3003.329403] r15 = ffffffffffffffba r31 = 0000000000000002
[ 3003.329404] ctr = c00000000041a670 lr = c000000000272520
[ 3003.329405] srr0 = c00000000007e8d8 srr1 = 9000000000001002
[ 3003.329406] sprg0 = 0000000000000000 sprg1 = c00000000fe01400
[ 3003.329407] sprg2 = c00000000fe01400 sprg3 = 0000000000000005
[ 3003.329408] cr = 48004482 xer = 2000000000000000 dsisr = 42000000
[ 3003.329409] dar = 0000010015020048
[ 3003.329410] fault dar = 0000010015020048 dsisr = 42000000
[ 3003.329411] SLB (8 entries):
[ 3003.329412] ESID = c000000008000000 VSID = 40016e7779000510
[ 3003.329413] ESID = d000000008000001 VSID = 400142add1000510
[ 3003.329414] ESID = f000000008000004 VSID = 4000eb1a81000510
[ 3003.329415] ESID = 00001f000800000b VSID = 40004fda0a000d90
[ 3003.329416] ESID = 00003f000800000c VSID = 400039f536000d90
[ 3003.329417] ESID = 000000001800000d VSID = 0001251b35150d90
[ 3003.329417] ESID = 000001000800000e VSID = 4001e46090000d90
[ 3003.329418] ESID = d000080008000019 VSID = 40013d349c000400
[ 3003.329419] lpcr = c048800001847001 sdr1 = 0000001b19000006 last_inst = ffffffff
[ 3003.329421] trap=0xe60 | pc=0xc0000000000c2ba0 | msr=0x8000000000009032
[ 3003.329524] Severe Hypervisor Maintenance interrupt [Recovered]
[ 3003.329526] Error detail: Timer facility experienced an error
[ 3003.329527] HMER: 0840000000000000
[ 3003.329527] TFMR: 4a12000980a94000
[ 3006.359786] Severe Hypervisor Maintenance interrupt [Recovered]
[ 3006.359792] Error detail: Timer facility experienced an error
[ 3006.359795] HMER: 0840000000000000
[ 3006.359797] TFMR: 4a12000980a84000
# virsh list --all
Id Name State
----------------------------------------------------
2 guest2 running
3 guest3 paused
4 guest4 running
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/kvm/book3s_hv.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 27cced9..c2d30be 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -745,6 +745,8 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
vcpu->stat.ext_intr_exits++;
r = RESUME_GUEST;
break;
+ /* HMI is hypervisor interrupt and host has handled it. Resume guest.*/
+ case BOOK3S_INTERRUPT_HMI:
case BOOK3S_INTERRUPT_PERFMON:
r = RESUME_GUEST;
break;
^ permalink raw reply related
* Re: [PATCH 31/44] arm: Register with kernel poweroff handler
From: Nicolas Ferre @ 2014-10-07 8:04 UTC (permalink / raw)
To: Guenter Roeck, linux-kernel, Alexandre Belloni, Boris BREZILLON
Cc: linux-m32r-ja, linux-mips, linux-efi, linux-ia64, Anton Vorontsov,
Stephen Warren, linux-xtensa, Tony Lindgren, Linus Walleij,
Andrew Lunn, Kukjin Kim, Robert Jarzmik, Stefano Stabellini,
devel, linux-s390, lguest, Russell King, linux-c6x-dev,
Marek Vasut, linux-hexagon, linux-sh, Andrew Victor, linux-acpi,
Shawn Guo, xen-devel, Jean-Christophe Plagniol-Villard,
Rob Herring, Sebastian Hesselbarth, devicetree, Jason Cooper,
user-mode-linux-devel, linux-pm, adi-buildroot-devel, Matt Porter,
linux-m68k, linux-am33-list, Haojian Zhuang, Ben Dooks,
linux-tegra, openipmi-developer, linux-metag, linux-arm-kernel,
Eric Miao, linux-parisc, linux-cris-kernel, Christian Daudt,
Tony Prisk, Sascha Hauer, linux-alpha, linuxppc-dev,
Krzysztof Halasa
In-Reply-To: <1412659726-29957-32-git-send-email-linux@roeck-us.net>
On 07/10/2014 07:28, Guenter Roeck :
> Register with kernel poweroff handler instead of setting pm_power_off
> directly. Always use register_poweroff_handler_simple as there is no
> indication that more than one poweroff handler is registered.
>
> If the poweroff handler only resets the system or puts the CPU in sleep mode,
> select a priority of 0 to indicate that the poweroff handler is one of last
> resort. If the poweroff handler powers off the system, select a priority
> of 128.
>
> Cc: Russell King <linux@arm.linux.org.uk>
> Cc: Andrew Victor <linux@maxim.org.za>
> Cc: Nicolas Ferre <nicolas.ferre@atmel.com>
> Cc: Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com>
> Cc: Stephen Warren <swarren@wwwdotorg.org>
> Cc: Christian Daudt <bcm@fixthebug.org>
> Cc: Matt Porter <mporter@linaro.org>
> Cc: Anton Vorontsov <anton@enomsg.org>
> Cc: Rob Herring <robh@kernel.org>
> Cc: Shawn Guo <shawn.guo@freescale.com>
> Cc: Sascha Hauer <kernel@pengutronix.de>
> Cc: Imre Kaloz <kaloz@openwrt.org>
> Cc: Krzysztof Halasa <khc@pm.waw.pl>
> Cc: Tony Lindgren <tony@atomide.com>
> Cc: Jason Cooper <jason@lakedaemon.net>
> Cc: Andrew Lunn <andrew@lunn.ch>
> Cc: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
> Cc: Eric Miao <eric.y.miao@gmail.com>
> Cc: Haojian Zhuang <haojian.zhuang@gmail.com>
> Cc: Robert Jarzmik <robert.jarzmik@free.fr>
> Cc: Marek Vasut <marek.vasut@gmail.com>
> Cc: Ben Dooks <ben-linux@fluff.org>
> Cc: Kukjin Kim <kgene.kim@samsung.com>
> Cc: Linus Walleij <linus.walleij@linaro.org>
> Cc: Tony Prisk <linux@prisktech.co.nz>
> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
> Signed-off-by: Guenter Roeck <linux@roeck-us.net>
> ---
> arch/arm/kernel/psci.c | 2 +-
> arch/arm/mach-at91/board-gsia18s.c | 2 +-
> arch/arm/mach-at91/setup.c | 4 ++--
For the 2 files above: NAK just because:
for the first one -> this file will be removed during 3.19 dev cycle.
for the second one -> the poweroff handlers are removed during the 3.18
cycle and converted in the appropriate poweroff drivers (in
drivers/power/reset/at91-poweroff.c).
So, can you remove these changes from your patch?
Thanks for your work, bye.
> arch/arm/mach-bcm/board_bcm2835.c | 2 +-
> arch/arm/mach-cns3xxx/cns3420vb.c | 2 +-
> arch/arm/mach-cns3xxx/core.c | 2 +-
> arch/arm/mach-highbank/highbank.c | 2 +-
> arch/arm/mach-imx/mach-mx31moboard.c | 2 +-
> arch/arm/mach-iop32x/em7210.c | 2 +-
> arch/arm/mach-iop32x/glantank.c | 2 +-
> arch/arm/mach-iop32x/iq31244.c | 2 +-
> arch/arm/mach-iop32x/n2100.c | 2 +-
> arch/arm/mach-ixp4xx/dsmg600-setup.c | 2 +-
> arch/arm/mach-ixp4xx/nas100d-setup.c | 2 +-
> arch/arm/mach-ixp4xx/nslu2-setup.c | 2 +-
> arch/arm/mach-omap2/board-omap3touchbook.c | 2 +-
> arch/arm/mach-orion5x/board-mss2.c | 2 +-
> arch/arm/mach-orion5x/dns323-setup.c | 6 +++---
> arch/arm/mach-orion5x/kurobox_pro-setup.c | 2 +-
> arch/arm/mach-orion5x/ls-chl-setup.c | 2 +-
> arch/arm/mach-orion5x/ls_hgl-setup.c | 2 +-
> arch/arm/mach-orion5x/lsmini-setup.c | 2 +-
> arch/arm/mach-orion5x/mv2120-setup.c | 2 +-
> arch/arm/mach-orion5x/net2big-setup.c | 2 +-
> arch/arm/mach-orion5x/terastation_pro2-setup.c | 2 +-
> arch/arm/mach-orion5x/ts209-setup.c | 2 +-
> arch/arm/mach-orion5x/ts409-setup.c | 2 +-
> arch/arm/mach-pxa/corgi.c | 2 +-
> arch/arm/mach-pxa/mioa701.c | 2 +-
> arch/arm/mach-pxa/poodle.c | 2 +-
> arch/arm/mach-pxa/spitz.c | 2 +-
> arch/arm/mach-pxa/tosa.c | 2 +-
> arch/arm/mach-pxa/viper.c | 2 +-
> arch/arm/mach-pxa/z2.c | 6 +++---
> arch/arm/mach-pxa/zeus.c | 6 +++---
> arch/arm/mach-s3c24xx/mach-gta02.c | 2 +-
> arch/arm/mach-s3c24xx/mach-jive.c | 2 +-
> arch/arm/mach-s3c24xx/mach-vr1000.c | 2 +-
> arch/arm/mach-s3c64xx/mach-smartq.c | 2 +-
> arch/arm/mach-sa1100/generic.c | 2 +-
> arch/arm/mach-sa1100/simpad.c | 2 +-
> arch/arm/mach-u300/regulator.c | 2 +-
> arch/arm/mach-vt8500/vt8500.c | 2 +-
> arch/arm/xen/enlighten.c | 2 +-
> 44 files changed, 51 insertions(+), 51 deletions(-)
>
> diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c
> index f73891b..dd58d86 100644
> --- a/arch/arm/kernel/psci.c
> +++ b/arch/arm/kernel/psci.c
> @@ -264,7 +264,7 @@ static int psci_0_2_init(struct device_node *np)
>
> arm_pm_restart = psci_sys_reset;
>
> - pm_power_off = psci_sys_poweroff;
> + register_poweroff_handler_simple(psci_sys_poweroff, 128);
>
> out_put_node:
> of_node_put(np);
> diff --git a/arch/arm/mach-at91/board-gsia18s.c b/arch/arm/mach-at91/board-gsia18s.c
> index b729dd1..6722e66 100644
> --- a/arch/arm/mach-at91/board-gsia18s.c
> +++ b/arch/arm/mach-at91/board-gsia18s.c
> @@ -521,7 +521,7 @@ static void gsia18s_power_off(void)
>
> static int __init gsia18s_power_off_init(void)
> {
> - pm_power_off = gsia18s_power_off;
> + register_poweroff_handler_simple(gsia18s_power_off, 128);
> return 0;
> }
>
> diff --git a/arch/arm/mach-at91/setup.c b/arch/arm/mach-at91/setup.c
> index f7a07a5..9989e88 100644
> --- a/arch/arm/mach-at91/setup.c
> +++ b/arch/arm/mach-at91/setup.c
> @@ -329,7 +329,7 @@ void __init at91_ioremap_shdwc(u32 base_addr)
> at91_shdwc_base = ioremap(base_addr, 16);
> if (!at91_shdwc_base)
> panic("Impossible to ioremap at91_shdwc_base\n");
> - pm_power_off = at91sam9_poweroff;
> + register_poweroff_handler_simple(at91sam9_poweroff, 128);
> }
>
> void __iomem *at91_rstc_base;
> @@ -482,7 +482,7 @@ static void at91_dt_shdwc(void)
> at91_shdwc_write(AT91_SHDW_MR, wakeup_mode | mode);
>
> end:
> - pm_power_off = at91sam9_poweroff;
> + register_poweroff_handler_simple(at91sam9_poweroff, 128);
>
> of_node_put(np);
> }
> diff --git a/arch/arm/mach-bcm/board_bcm2835.c b/arch/arm/mach-bcm/board_bcm2835.c
> index 70f2f39..7d5784f 100644
> --- a/arch/arm/mach-bcm/board_bcm2835.c
> +++ b/arch/arm/mach-bcm/board_bcm2835.c
> @@ -111,7 +111,7 @@ static void __init bcm2835_init(void)
>
> bcm2835_setup_restart();
> if (wdt_regs)
> - pm_power_off = bcm2835_power_off;
> + register_poweroff_handler_simple(bcm2835_power_off, 0);
>
> bcm2835_init_clocks();
>
> diff --git a/arch/arm/mach-cns3xxx/cns3420vb.c b/arch/arm/mach-cns3xxx/cns3420vb.c
> index d863d87..136b7c6 100644
> --- a/arch/arm/mach-cns3xxx/cns3420vb.c
> +++ b/arch/arm/mach-cns3xxx/cns3420vb.c
> @@ -224,7 +224,7 @@ static void __init cns3420_init(void)
> cns3xxx_ahci_init();
> cns3xxx_sdhci_init();
>
> - pm_power_off = cns3xxx_power_off;
> + register_poweroff_handler_simple(cns3xxx_power_off, 128);
> }
>
> static struct map_desc cns3420_io_desc[] __initdata = {
> diff --git a/arch/arm/mach-cns3xxx/core.c b/arch/arm/mach-cns3xxx/core.c
> index f85449a..79e6ead 100644
> --- a/arch/arm/mach-cns3xxx/core.c
> +++ b/arch/arm/mach-cns3xxx/core.c
> @@ -386,7 +386,7 @@ static void __init cns3xxx_init(void)
> cns3xxx_pwr_soft_rst(CNS3XXX_PWR_SOFTWARE_RST(SDIO));
> }
>
> - pm_power_off = cns3xxx_power_off;
> + register_poweroff_handler_simple(cns3xxx_power_off, 128);
>
> of_platform_populate(NULL, of_default_bus_match_table,
> cns3xxx_auxdata, NULL);
> diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
> index 8c35ae4..25d0134 100644
> --- a/arch/arm/mach-highbank/highbank.c
> +++ b/arch/arm/mach-highbank/highbank.c
> @@ -155,7 +155,7 @@ static void __init highbank_init(void)
> sregs_base = of_iomap(np, 0);
> WARN_ON(!sregs_base);
>
> - pm_power_off = highbank_power_off;
> + register_poweroff_handler_simple(highbank_power_off, 0);
> highbank_pm_init();
>
> bus_register_notifier(&platform_bus_type, &highbank_platform_nb);
> diff --git a/arch/arm/mach-imx/mach-mx31moboard.c b/arch/arm/mach-imx/mach-mx31moboard.c
> index bb6f8a5..9b3616f 100644
> --- a/arch/arm/mach-imx/mach-mx31moboard.c
> +++ b/arch/arm/mach-imx/mach-mx31moboard.c
> @@ -559,7 +559,7 @@ static void __init mx31moboard_init(void)
>
> imx_add_platform_device("imx_mc13783", 0, NULL, 0, NULL, 0);
>
> - pm_power_off = mx31moboard_poweroff;
> + register_poweroff_handler_simple(mx31moboard_poweroff, 128);
>
> switch (mx31moboard_baseboard) {
> case MX31NOBOARD:
> diff --git a/arch/arm/mach-iop32x/em7210.c b/arch/arm/mach-iop32x/em7210.c
> index 77e1ff0..beeeb0c2 100644
> --- a/arch/arm/mach-iop32x/em7210.c
> +++ b/arch/arm/mach-iop32x/em7210.c
> @@ -201,7 +201,7 @@ static int __init em7210_request_gpios(void)
> return 0;
> }
>
> - pm_power_off = em7210_power_off;
> + register_poweroff_handler_simple(em7210_power_off, 128);
>
> return 0;
> }
> diff --git a/arch/arm/mach-iop32x/glantank.c b/arch/arm/mach-iop32x/glantank.c
> index 547b234..050a8e6 100644
> --- a/arch/arm/mach-iop32x/glantank.c
> +++ b/arch/arm/mach-iop32x/glantank.c
> @@ -199,7 +199,7 @@ static void __init glantank_init_machine(void)
> i2c_register_board_info(0, glantank_i2c_devices,
> ARRAY_SIZE(glantank_i2c_devices));
>
> - pm_power_off = glantank_power_off;
> + register_poweroff_handler_simple(glantank_power_off, 128);
> }
>
> MACHINE_START(GLANTANK, "GLAN Tank")
> diff --git a/arch/arm/mach-iop32x/iq31244.c b/arch/arm/mach-iop32x/iq31244.c
> index 0e1392b..4e9b972 100644
> --- a/arch/arm/mach-iop32x/iq31244.c
> +++ b/arch/arm/mach-iop32x/iq31244.c
> @@ -293,7 +293,7 @@ static void __init iq31244_init_machine(void)
> platform_device_register(&iop3xx_dma_1_channel);
>
> if (is_ep80219())
> - pm_power_off = ep80219_power_off;
> + register_poweroff_handler_simple(ep80219_power_off, 128);
>
> if (!is_80219())
> platform_device_register(&iop3xx_aau_channel);
> diff --git a/arch/arm/mach-iop32x/n2100.c b/arch/arm/mach-iop32x/n2100.c
> index c1cd80e..171d496 100644
> --- a/arch/arm/mach-iop32x/n2100.c
> +++ b/arch/arm/mach-iop32x/n2100.c
> @@ -356,7 +356,7 @@ static void __init n2100_init_machine(void)
> i2c_register_board_info(0, n2100_i2c_devices,
> ARRAY_SIZE(n2100_i2c_devices));
>
> - pm_power_off = n2100_power_off;
> + register_poweroff_handler_simple(n2100_power_off, 128);
> }
>
> MACHINE_START(N2100, "Thecus N2100")
> diff --git a/arch/arm/mach-ixp4xx/dsmg600-setup.c b/arch/arm/mach-ixp4xx/dsmg600-setup.c
> index 43ee06d..6fb5072 100644
> --- a/arch/arm/mach-ixp4xx/dsmg600-setup.c
> +++ b/arch/arm/mach-ixp4xx/dsmg600-setup.c
> @@ -281,7 +281,7 @@ static void __init dsmg600_init(void)
>
> platform_add_devices(dsmg600_devices, ARRAY_SIZE(dsmg600_devices));
>
> - pm_power_off = dsmg600_power_off;
> + register_poweroff_handler_simple(dsmg600_power_off, 128);
> }
>
> MACHINE_START(DSMG600, "D-Link DSM-G600 RevA")
> diff --git a/arch/arm/mach-ixp4xx/nas100d-setup.c b/arch/arm/mach-ixp4xx/nas100d-setup.c
> index 4e0f762..bd9a8d6 100644
> --- a/arch/arm/mach-ixp4xx/nas100d-setup.c
> +++ b/arch/arm/mach-ixp4xx/nas100d-setup.c
> @@ -292,7 +292,7 @@ static void __init nas100d_init(void)
>
> platform_add_devices(nas100d_devices, ARRAY_SIZE(nas100d_devices));
>
> - pm_power_off = nas100d_power_off;
> + register_poweroff_handler_simple(nas100d_power_off, 128);
>
> if (request_irq(gpio_to_irq(NAS100D_RB_GPIO), &nas100d_reset_handler,
> IRQF_TRIGGER_LOW, "NAS100D reset button", NULL) < 0) {
> diff --git a/arch/arm/mach-ixp4xx/nslu2-setup.c b/arch/arm/mach-ixp4xx/nslu2-setup.c
> index 88c025f..c4c5475 100644
> --- a/arch/arm/mach-ixp4xx/nslu2-setup.c
> +++ b/arch/arm/mach-ixp4xx/nslu2-setup.c
> @@ -262,7 +262,7 @@ static void __init nslu2_init(void)
>
> platform_add_devices(nslu2_devices, ARRAY_SIZE(nslu2_devices));
>
> - pm_power_off = nslu2_power_off;
> + register_poweroff_handler_simple(nslu2_power_off, 128);
>
> if (request_irq(gpio_to_irq(NSLU2_RB_GPIO), &nslu2_reset_handler,
> IRQF_TRIGGER_LOW, "NSLU2 reset button", NULL) < 0) {
> diff --git a/arch/arm/mach-omap2/board-omap3touchbook.c b/arch/arm/mach-omap2/board-omap3touchbook.c
> index 70b904c..0c0a0e2 100644
> --- a/arch/arm/mach-omap2/board-omap3touchbook.c
> +++ b/arch/arm/mach-omap2/board-omap3touchbook.c
> @@ -344,7 +344,7 @@ static void __init omap3_touchbook_init(void)
> {
> omap3_mux_init(board_mux, OMAP_PACKAGE_CBB);
>
> - pm_power_off = omap3_touchbook_poweroff;
> + register_poweroff_handler_simple(omap3_touchbook_poweroff, 128);
>
> if (system_rev >= 0x20 && system_rev <= 0x34301000) {
> omap_mux_init_gpio(23, OMAP_PIN_INPUT);
> diff --git a/arch/arm/mach-orion5x/board-mss2.c b/arch/arm/mach-orion5x/board-mss2.c
> index 66f9c3b..3840d66 100644
> --- a/arch/arm/mach-orion5x/board-mss2.c
> +++ b/arch/arm/mach-orion5x/board-mss2.c
> @@ -86,5 +86,5 @@ static void mss2_power_off(void)
> void __init mss2_init(void)
> {
> /* register mss2 specific power-off method */
> - pm_power_off = mss2_power_off;
> + register_poweroff_handler_simple(mss2_power_off, 0);
> }
> diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c
> index 56edeab..353ca3d 100644
> --- a/arch/arm/mach-orion5x/dns323-setup.c
> +++ b/arch/arm/mach-orion5x/dns323-setup.c
> @@ -669,7 +669,7 @@ static void __init dns323_init(void)
> if (gpio_request(DNS323_GPIO_POWER_OFF, "POWEROFF") != 0 ||
> gpio_direction_output(DNS323_GPIO_POWER_OFF, 0) != 0)
> pr_err("DNS-323: failed to setup power-off GPIO\n");
> - pm_power_off = dns323a_power_off;
> + register_poweroff_handler_simple(dns323a_power_off, 128);
> break;
> case DNS323_REV_B1:
> /* 5182 built-in SATA init */
> @@ -686,7 +686,7 @@ static void __init dns323_init(void)
> if (gpio_request(DNS323_GPIO_POWER_OFF, "POWEROFF") != 0 ||
> gpio_direction_output(DNS323_GPIO_POWER_OFF, 0) != 0)
> pr_err("DNS-323: failed to setup power-off GPIO\n");
> - pm_power_off = dns323b_power_off;
> + register_poweroff_handler_simple(dns323b_power_off, 128);
> break;
> case DNS323_REV_C1:
> /* 5182 built-in SATA init */
> @@ -696,7 +696,7 @@ static void __init dns323_init(void)
> if (gpio_request(DNS323C_GPIO_POWER_OFF, "POWEROFF") != 0 ||
> gpio_direction_output(DNS323C_GPIO_POWER_OFF, 0) != 0)
> pr_err("DNS-323: failed to setup power-off GPIO\n");
> - pm_power_off = dns323c_power_off;
> + register_poweroff_handler_simple(dns323c_power_off, 128);
>
> /* Now, -this- should theorically be done by the sata_mv driver
> * once I figure out what's going on there. Maybe the behaviour
> diff --git a/arch/arm/mach-orion5x/kurobox_pro-setup.c b/arch/arm/mach-orion5x/kurobox_pro-setup.c
> index fe6a48a..c4101f1 100644
> --- a/arch/arm/mach-orion5x/kurobox_pro-setup.c
> +++ b/arch/arm/mach-orion5x/kurobox_pro-setup.c
> @@ -376,7 +376,7 @@ static void __init kurobox_pro_init(void)
> i2c_register_board_info(0, &kurobox_pro_i2c_rtc, 1);
>
> /* register Kurobox Pro specific power-off method */
> - pm_power_off = kurobox_pro_power_off;
> + register_poweroff_handler_simple(kurobox_pro_power_off, 128);
> }
>
> #ifdef CONFIG_MACH_KUROBOX_PRO
> diff --git a/arch/arm/mach-orion5x/ls-chl-setup.c b/arch/arm/mach-orion5x/ls-chl-setup.c
> index 028ea03..005bb04 100644
> --- a/arch/arm/mach-orion5x/ls-chl-setup.c
> +++ b/arch/arm/mach-orion5x/ls-chl-setup.c
> @@ -312,7 +312,7 @@ static void __init lschl_init(void)
> gpio_set_value(LSCHL_GPIO_USB_POWER, 1);
>
> /* register power-off method */
> - pm_power_off = lschl_power_off;
> + register_poweroff_handler_simple(lschl_power_off, 0);
>
> pr_info("%s: finished\n", __func__);
> }
> diff --git a/arch/arm/mach-orion5x/ls_hgl-setup.c b/arch/arm/mach-orion5x/ls_hgl-setup.c
> index 32b7129..37c29a0 100644
> --- a/arch/arm/mach-orion5x/ls_hgl-setup.c
> +++ b/arch/arm/mach-orion5x/ls_hgl-setup.c
> @@ -259,7 +259,7 @@ static void __init ls_hgl_init(void)
> gpio_set_value(LS_HGL_GPIO_USB_POWER, 1);
>
> /* register power-off method */
> - pm_power_off = ls_hgl_power_off;
> + register_poweroff_handler_simple(ls_hgl_power_off, 0);
>
> pr_info("%s: finished\n", __func__);
> }
> diff --git a/arch/arm/mach-orion5x/lsmini-setup.c b/arch/arm/mach-orion5x/lsmini-setup.c
> index a6493e7..ffec72f 100644
> --- a/arch/arm/mach-orion5x/lsmini-setup.c
> +++ b/arch/arm/mach-orion5x/lsmini-setup.c
> @@ -260,7 +260,7 @@ static void __init lsmini_init(void)
> gpio_set_value(LSMINI_GPIO_USB_POWER, 1);
>
> /* register power-off method */
> - pm_power_off = lsmini_power_off;
> + register_poweroff_handler_simple(lsmini_power_off, 0);
>
> pr_info("%s: finished\n", __func__);
> }
> diff --git a/arch/arm/mach-orion5x/mv2120-setup.c b/arch/arm/mach-orion5x/mv2120-setup.c
> index e032f01..dadc2b9 100644
> --- a/arch/arm/mach-orion5x/mv2120-setup.c
> +++ b/arch/arm/mach-orion5x/mv2120-setup.c
> @@ -225,7 +225,7 @@ static void __init mv2120_init(void)
> if (gpio_request(MV2120_GPIO_POWER_OFF, "POWEROFF") != 0 ||
> gpio_direction_output(MV2120_GPIO_POWER_OFF, 1) != 0)
> pr_err("mv2120: failed to setup power-off GPIO\n");
> - pm_power_off = mv2120_power_off;
> + register_poweroff_handler_simple(mv2120_power_off, 128);
> }
>
> /* Warning: HP uses a wrong mach-type (=526) in their bootloader */
> diff --git a/arch/arm/mach-orion5x/net2big-setup.c b/arch/arm/mach-orion5x/net2big-setup.c
> index ba73dc7..3a73dce 100644
> --- a/arch/arm/mach-orion5x/net2big-setup.c
> +++ b/arch/arm/mach-orion5x/net2big-setup.c
> @@ -413,7 +413,7 @@ static void __init net2big_init(void)
>
> if (gpio_request(NET2BIG_GPIO_POWER_OFF, "power-off") == 0 &&
> gpio_direction_output(NET2BIG_GPIO_POWER_OFF, 0) == 0)
> - pm_power_off = net2big_power_off;
> + register_poweroff_handler_simple(net2big_power_off, 128);
> else
> pr_err("net2big: failed to configure power-off GPIO\n");
>
> diff --git a/arch/arm/mach-orion5x/terastation_pro2-setup.c b/arch/arm/mach-orion5x/terastation_pro2-setup.c
> index 6208d12..2a234cb 100644
> --- a/arch/arm/mach-orion5x/terastation_pro2-setup.c
> +++ b/arch/arm/mach-orion5x/terastation_pro2-setup.c
> @@ -353,7 +353,7 @@ static void __init tsp2_init(void)
> i2c_register_board_info(0, &tsp2_i2c_rtc, 1);
>
> /* register Terastation Pro II specific power-off method */
> - pm_power_off = tsp2_power_off;
> + register_poweroff_handler_simple(tsp2_power_off, 128);
> }
>
> MACHINE_START(TERASTATION_PRO2, "Buffalo Terastation Pro II/Live")
> diff --git a/arch/arm/mach-orion5x/ts209-setup.c b/arch/arm/mach-orion5x/ts209-setup.c
> index 9136797..50bdfbc 100644
> --- a/arch/arm/mach-orion5x/ts209-setup.c
> +++ b/arch/arm/mach-orion5x/ts209-setup.c
> @@ -318,7 +318,7 @@ static void __init qnap_ts209_init(void)
> i2c_register_board_info(0, &qnap_ts209_i2c_rtc, 1);
>
> /* register tsx09 specific power-off method */
> - pm_power_off = qnap_tsx09_power_off;
> + register_poweroff_handler_simple(qnap_tsx09_power_off, 128);
> }
>
> MACHINE_START(TS209, "QNAP TS-109/TS-209")
> diff --git a/arch/arm/mach-orion5x/ts409-setup.c b/arch/arm/mach-orion5x/ts409-setup.c
> index 5c079d31..06a7cc0 100644
> --- a/arch/arm/mach-orion5x/ts409-setup.c
> +++ b/arch/arm/mach-orion5x/ts409-setup.c
> @@ -307,7 +307,7 @@ static void __init qnap_ts409_init(void)
> platform_device_register(&ts409_leds);
>
> /* register tsx09 specific power-off method */
> - pm_power_off = qnap_tsx09_power_off;
> + register_poweroff_handler_simple(qnap_tsx09_power_off, 128);
> }
>
> MACHINE_START(TS409, "QNAP TS-409")
> diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c
> index 06022b2..a93bac0 100644
> --- a/arch/arm/mach-pxa/corgi.c
> +++ b/arch/arm/mach-pxa/corgi.c
> @@ -718,7 +718,7 @@ static void corgi_restart(enum reboot_mode mode, const char *cmd)
>
> static void __init corgi_init(void)
> {
> - pm_power_off = corgi_poweroff;
> + register_poweroff_handler_simple(corgi_poweroff, 0);
>
> /* Stop 3.6MHz and drive HIGH to PCMCIA and CS */
> PCFR |= PCFR_OPDE;
> diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c
> index 29997bd..c4345a4 100644
> --- a/arch/arm/mach-pxa/mioa701.c
> +++ b/arch/arm/mach-pxa/mioa701.c
> @@ -750,7 +750,7 @@ static void __init mioa701_machine_init(void)
> pxa_set_keypad_info(&mioa701_keypad_info);
> pxa_set_udc_info(&mioa701_udc_info);
> pxa_set_ac97_info(&mioa701_ac97_info);
> - pm_power_off = mioa701_poweroff;
> + register_poweroff_handler_simple(mioa701_poweroff, 0);
> platform_add_devices(devices, ARRAY_SIZE(devices));
> gsm_init();
>
> diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c
> index 1319916..c9536ed 100644
> --- a/arch/arm/mach-pxa/poodle.c
> +++ b/arch/arm/mach-pxa/poodle.c
> @@ -432,7 +432,7 @@ static void __init poodle_init(void)
> {
> int ret = 0;
>
> - pm_power_off = poodle_poweroff;
> + register_poweroff_handler_simple(poodle_poweroff, 0);
>
> PCFR |= PCFR_OPDE;
>
> diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
> index 840c3a4..09f0de8 100644
> --- a/arch/arm/mach-pxa/spitz.c
> +++ b/arch/arm/mach-pxa/spitz.c
> @@ -944,7 +944,7 @@ static void spitz_restart(enum reboot_mode mode, const char *cmd)
> static void __init spitz_init(void)
> {
> init_gpio_reset(SPITZ_GPIO_ON_RESET, 1, 0);
> - pm_power_off = spitz_poweroff;
> + register_poweroff_handler_simple(spitz_poweroff, 0);
>
> PMCR = 0x00;
>
> diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
> index c158a6e..3a4af1d 100644
> --- a/arch/arm/mach-pxa/tosa.c
> +++ b/arch/arm/mach-pxa/tosa.c
> @@ -940,7 +940,7 @@ static void __init tosa_init(void)
>
> init_gpio_reset(TOSA_GPIO_ON_RESET, 0, 0);
>
> - pm_power_off = tosa_poweroff;
> + register_poweroff_handler_simple(tosa_poweroff, 0);
>
> PCFR |= PCFR_OPDE;
>
> diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
> index de3b080..679c8ea 100644
> --- a/arch/arm/mach-pxa/viper.c
> +++ b/arch/arm/mach-pxa/viper.c
> @@ -919,7 +919,7 @@ static void __init viper_init(void)
> {
> u8 version;
>
> - pm_power_off = viper_power_off;
> + register_poweroff_handler_simple(viper_power_off, 128);
>
> pxa2xx_mfp_config(ARRAY_AND_SIZE(viper_pin_config));
>
> diff --git a/arch/arm/mach-pxa/z2.c b/arch/arm/mach-pxa/z2.c
> index e1a121b..e0195ac 100644
> --- a/arch/arm/mach-pxa/z2.c
> +++ b/arch/arm/mach-pxa/z2.c
> @@ -693,8 +693,6 @@ static void z2_power_off(void)
> pxa27x_set_pwrmode(PWRMODE_DEEPSLEEP);
> pxa27x_cpu_pm_enter(PM_SUSPEND_MEM);
> }
> -#else
> -#define z2_power_off NULL
> #endif
>
> /******************************************************************************
> @@ -719,7 +717,9 @@ static void __init z2_init(void)
> z2_keys_init();
> z2_pmic_init();
>
> - pm_power_off = z2_power_off;
> +#ifdef CONFIG_PM
> + register_poweroff_handler_simple(z2_power_off, 0);
> +#endif
> }
>
> MACHINE_START(ZIPIT2, "Zipit Z2")
> diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
> index 205f9bf..6118fd5 100644
> --- a/arch/arm/mach-pxa/zeus.c
> +++ b/arch/arm/mach-pxa/zeus.c
> @@ -690,8 +690,6 @@ static void zeus_power_off(void)
> local_irq_disable();
> cpu_suspend(PWRMODE_DEEPSLEEP, pxa27x_finish_suspend);
> }
> -#else
> -#define zeus_power_off NULL
> #endif
>
> #ifdef CONFIG_APM_EMULATION
> @@ -847,7 +845,9 @@ static void __init zeus_init(void)
> __raw_writel(msc0, MSC0);
> __raw_writel(msc1, MSC1);
>
> - pm_power_off = zeus_power_off;
> +#ifdef CONFIG_PM
> + register_poweroff_handler_simple(zeus_power_off, 0);
> +#endif
> zeus_setup_apm();
>
> pxa2xx_mfp_config(ARRAY_AND_SIZE(zeus_pin_config));
> diff --git a/arch/arm/mach-s3c24xx/mach-gta02.c b/arch/arm/mach-s3c24xx/mach-gta02.c
> index fc3a08d..ca78150 100644
> --- a/arch/arm/mach-s3c24xx/mach-gta02.c
> +++ b/arch/arm/mach-s3c24xx/mach-gta02.c
> @@ -579,7 +579,7 @@ static void __init gta02_machine_init(void)
> i2c_register_board_info(0, gta02_i2c_devs, ARRAY_SIZE(gta02_i2c_devs));
>
> platform_add_devices(gta02_devices, ARRAY_SIZE(gta02_devices));
> - pm_power_off = gta02_poweroff;
> + register_poweroff_handler_simple(gta02_poweroff, 128);
>
> regulator_has_full_constraints();
> }
> diff --git a/arch/arm/mach-s3c24xx/mach-jive.c b/arch/arm/mach-s3c24xx/mach-jive.c
> index 7804d3c..5a828a3 100644
> --- a/arch/arm/mach-s3c24xx/mach-jive.c
> +++ b/arch/arm/mach-s3c24xx/mach-jive.c
> @@ -657,7 +657,7 @@ static void __init jive_machine_init(void)
> s3c_i2c0_set_platdata(&jive_i2c_cfg);
> i2c_register_board_info(0, jive_i2c_devs, ARRAY_SIZE(jive_i2c_devs));
>
> - pm_power_off = jive_power_off;
> + register_poweroff_handler_simple(jive_power_off, 128);
>
> platform_add_devices(jive_devices, ARRAY_SIZE(jive_devices));
> }
> diff --git a/arch/arm/mach-s3c24xx/mach-vr1000.c b/arch/arm/mach-s3c24xx/mach-vr1000.c
> index f88c584..40d7655 100644
> --- a/arch/arm/mach-s3c24xx/mach-vr1000.c
> +++ b/arch/arm/mach-s3c24xx/mach-vr1000.c
> @@ -306,7 +306,7 @@ static void vr1000_power_off(void)
>
> static void __init vr1000_map_io(void)
> {
> - pm_power_off = vr1000_power_off;
> + register_poweroff_handler_simple(vr1000_power_off, 128);
>
> s3c24xx_init_io(vr1000_iodesc, ARRAY_SIZE(vr1000_iodesc));
> s3c24xx_init_uarts(vr1000_uartcfgs, ARRAY_SIZE(vr1000_uartcfgs));
> diff --git a/arch/arm/mach-s3c64xx/mach-smartq.c b/arch/arm/mach-s3c64xx/mach-smartq.c
> index b3d1353..61f0893 100644
> --- a/arch/arm/mach-s3c64xx/mach-smartq.c
> +++ b/arch/arm/mach-s3c64xx/mach-smartq.c
> @@ -291,7 +291,7 @@ static int __init smartq_power_off_init(void)
> /* leave power on */
> gpio_direction_output(S3C64XX_GPK(15), 0);
>
> - pm_power_off = smartq_power_off;
> + register_poweroff_handler_simple(smartq_power_off, 128);
>
> return ret;
> }
> diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c
> index d4ea142..6b839cf 100644
> --- a/arch/arm/mach-sa1100/generic.c
> +++ b/arch/arm/mach-sa1100/generic.c
> @@ -311,7 +311,7 @@ static struct platform_device *sa11x0_devices[] __initdata = {
>
> static int __init sa1100_init(void)
> {
> - pm_power_off = sa1100_power_off;
> + register_poweroff_handler_simple(sa1100_power_off, 0);
> return platform_add_devices(sa11x0_devices, ARRAY_SIZE(sa11x0_devices));
> }
>
> diff --git a/arch/arm/mach-sa1100/simpad.c b/arch/arm/mach-sa1100/simpad.c
> index 41e476e..a65ca58 100644
> --- a/arch/arm/mach-sa1100/simpad.c
> +++ b/arch/arm/mach-sa1100/simpad.c
> @@ -373,7 +373,7 @@ static int __init simpad_init(void)
> if (ret)
> printk(KERN_WARNING "simpad: Unable to register cs3 GPIO device");
>
> - pm_power_off = simpad_power_off;
> + register_poweroff_handler_simple(simpad_power_off, 0);
>
> sa11x0_ppc_configure_mcp();
> sa11x0_register_mtd(&simpad_flash_data, simpad_flash_resources,
> diff --git a/arch/arm/mach-u300/regulator.c b/arch/arm/mach-u300/regulator.c
> index 0493a84..c98eb6e 100644
> --- a/arch/arm/mach-u300/regulator.c
> +++ b/arch/arm/mach-u300/regulator.c
> @@ -98,7 +98,7 @@ static int __init __u300_init_boardpower(struct platform_device *pdev)
> U300_SYSCON_PMCR_DCON_ENABLE, 0);
>
> /* Register globally exported PM poweroff hook */
> - pm_power_off = u300_pm_poweroff;
> + register_poweroff_handler_simple(u300_pm_poweroff, 128);
>
> return 0;
> }
> diff --git a/arch/arm/mach-vt8500/vt8500.c b/arch/arm/mach-vt8500/vt8500.c
> index 2da7be3..515946b 100644
> --- a/arch/arm/mach-vt8500/vt8500.c
> +++ b/arch/arm/mach-vt8500/vt8500.c
> @@ -155,7 +155,7 @@ static void __init vt8500_init(void)
> pr_err("%s:ioremap(power_off) failed\n", __func__);
> }
> if (pmc_base)
> - pm_power_off = &vt8500_power_off;
> + register_poweroff_handler_simple(vt8500_power_off, 0);
> else
> pr_err("%s: PMC Hibernation register could not be remapped, not enabling power off!\n", __func__);
>
> diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
> index 0e15f01..0da639b 100644
> --- a/arch/arm/xen/enlighten.c
> +++ b/arch/arm/xen/enlighten.c
> @@ -336,7 +336,7 @@ static int __init xen_pm_init(void)
> if (!xen_domain())
> return -ENODEV;
>
> - pm_power_off = xen_power_off;
> + register_poweroff_handler_simple(xen_power_off, 128);
> arm_pm_restart = xen_restart;
>
> return 0;
>
--
Nicolas Ferre
^ permalink raw reply
* Re: [PATCH 12/44] mfd: ab8500-sysctrl: Register with kernel poweroff handler
From: Lee Jones @ 2014-10-07 8:00 UTC (permalink / raw)
To: Guenter Roeck
Cc: linux-m32r-ja, linux-mips, linux-efi, linux-ia64, linux-xtensa,
Linus Walleij, devel, linux-s390, lguest, linux-c6x-dev,
linux-hexagon, linux-sh, linux-acpi, xen-devel, devicetree,
user-mode-linux-devel, linux-pm, adi-buildroot-devel, linux-m68k,
linux-am33-list, linux-tegra, openipmi-developer, linux-metag,
linux-arm-kernel, Samuel Ortiz, linux-parisc, linux-cris-kernel,
linux-kernel, linux-alpha, linuxppc-dev
In-Reply-To: <1412659726-29957-13-git-send-email-linux@roeck-us.net>
On Mon, 06 Oct 2014, Guenter Roeck wrote:
> Register with kernel poweroff handler instead of setting pm_power_off
> directly. Register with a low priority value of 64 to reflect that
> the original code only sets pm_power_off if it was not already set.
>
> Cc: Linus Walleij <linus.walleij@linaro.org>
> Cc: Lee Jones <lee.jones@linaro.org>
> Cc: Samuel Ortiz <sameo@linux.intel.com>
> Signed-off-by: Guenter Roeck <linux@roeck-us.net>
> ---
> drivers/mfd/ab8500-sysctrl.c | 26 +++++++++++++++-----------
> 1 file changed, 15 insertions(+), 11 deletions(-)
>
> diff --git a/drivers/mfd/ab8500-sysctrl.c b/drivers/mfd/ab8500-sysctrl.c
> index 8e0dae5..677438f 100644
> --- a/drivers/mfd/ab8500-sysctrl.c
> +++ b/drivers/mfd/ab8500-sysctrl.c
> @@ -6,6 +6,7 @@
[...]
> +static int ab8500_power_off(struct notifier_block *this, unsigned long unused1,
> + void *unused2)
> {
> sigset_t old;
> sigset_t all;
> @@ -34,11 +36,6 @@ static void ab8500_power_off(void)
> struct power_supply *psy;
> int ret;
>
> - if (sysctrl_dev == NULL) {
> - pr_err("%s: sysctrl not initialized\n", __func__);
> - return;
> - }
Can you explain the purpose of this change please?
> /*
> * If we have a charger connected and we're powering off,
> * reboot into charge-only mode.
> @@ -83,8 +80,15 @@ shutdown:
> AB8500_STW4500CTRL1_SWRESET4500N);
> (void)sigprocmask(SIG_SETMASK, &old, NULL);
> }
> +
> + return NOTIFY_DONE;
> }
--
Lee Jones
Linaro STMicroelectronics Landing Team Lead
Linaro.org │ Open source software for ARM SoCs
Follow Linaro: Facebook | Twitter | Blog
^ 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