summaryrefslogtreecommitdiff
path: root/arch/powerpc/platforms
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/platforms')
-rw-r--r--arch/powerpc/platforms/52xx/mpc52xx_gpt.c1
-rw-r--r--arch/powerpc/platforms/86xx/mpc86xx_smp.c4
-rw-r--r--arch/powerpc/platforms/Kconfig3
-rw-r--r--arch/powerpc/platforms/Kconfig.cputype15
-rw-r--r--arch/powerpc/platforms/Makefile2
-rw-r--r--arch/powerpc/platforms/book3s/Kconfig15
-rw-r--r--arch/powerpc/platforms/book3s/Makefile2
-rw-r--r--arch/powerpc/platforms/book3s/vas-api.c493
-rw-r--r--arch/powerpc/platforms/cell/spider-pci.c3
-rw-r--r--arch/powerpc/platforms/cell/spufs/switch.c6
-rw-r--r--arch/powerpc/platforms/embedded6xx/holly.c4
-rw-r--r--arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c4
-rw-r--r--arch/powerpc/platforms/microwatt/Kconfig13
-rw-r--r--arch/powerpc/platforms/microwatt/Makefile1
-rw-r--r--arch/powerpc/platforms/microwatt/rng.c48
-rw-r--r--arch/powerpc/platforms/microwatt/setup.c41
-rw-r--r--arch/powerpc/platforms/pasemi/idle.c4
-rw-r--r--arch/powerpc/platforms/powermac/bootx_init.c2
-rw-r--r--arch/powerpc/platforms/powermac/smp.c4
-rw-r--r--arch/powerpc/platforms/powernv/Kconfig14
-rw-r--r--arch/powerpc/platforms/powernv/Makefile2
-rw-r--r--arch/powerpc/platforms/powernv/opal-call.c4
-rw-r--r--arch/powerpc/platforms/powernv/opal.c2
-rw-r--r--arch/powerpc/platforms/powernv/pci.c2
-rw-r--r--arch/powerpc/platforms/powernv/subcore.c10
-rw-r--r--arch/powerpc/platforms/powernv/vas-api.c278
-rw-r--r--arch/powerpc/platforms/powernv/vas-debug.c27
-rw-r--r--arch/powerpc/platforms/powernv/vas-fault.c173
-rw-r--r--arch/powerpc/platforms/powernv/vas-trace.h4
-rw-r--r--arch/powerpc/platforms/powernv/vas-window.c264
-rw-r--r--arch/powerpc/platforms/powernv/vas.h50
-rw-r--r--arch/powerpc/platforms/ps3/Kconfig9
-rw-r--r--arch/powerpc/platforms/ps3/mm.c12
-rw-r--r--arch/powerpc/platforms/ps3/setup.c43
-rw-r--r--arch/powerpc/platforms/ps3/system-bus.c9
-rw-r--r--arch/powerpc/platforms/pseries/Makefile1
-rw-r--r--arch/powerpc/platforms/pseries/dlpar.c9
-rw-r--r--arch/powerpc/platforms/pseries/hotplug-memory.c92
-rw-r--r--arch/powerpc/platforms/pseries/hvCall.S29
-rw-r--r--arch/powerpc/platforms/pseries/papr_scm.c101
-rw-r--r--arch/powerpc/platforms/pseries/ras.c6
-rw-r--r--arch/powerpc/platforms/pseries/setup.c9
-rw-r--r--arch/powerpc/platforms/pseries/smp.c4
-rw-r--r--arch/powerpc/platforms/pseries/vas.c595
-rw-r--r--arch/powerpc/platforms/pseries/vas.h125
45 files changed, 1832 insertions, 707 deletions
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index 8c0d324f657e..3823df235f25 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -582,6 +582,7 @@ static long mpc52xx_wdt_ioctl(struct file *file, unsigned int cmd,
if (ret)
break;
/* fall through and return the timeout */
+ fallthrough;
case WDIOC_GETTIMEOUT:
/* we need to round here as to avoid e.g. the following
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_smp.c b/arch/powerpc/platforms/86xx/mpc86xx_smp.c
index 87f524e4b09c..8a7e55acf090 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_smp.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_smp.c
@@ -73,7 +73,7 @@ smp_86xx_kick_cpu(int nr)
/* Setup fake reset vector to call __secondary_start_mpc86xx. */
target = (unsigned long) __secondary_start_mpc86xx;
- patch_branch((struct ppc_inst *)vector, target, BRANCH_SET_LINK);
+ patch_branch(vector, target, BRANCH_SET_LINK);
/* Kick that CPU */
smp_86xx_release_core(nr);
@@ -83,7 +83,7 @@ smp_86xx_kick_cpu(int nr)
mdelay(1);
/* Restore the exception vector */
- patch_instruction((struct ppc_inst *)vector, ppc_inst(save_vector));
+ patch_instruction(vector, ppc_inst(save_vector));
local_irq_restore(flags);
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 7a5e8f4541e3..e02d29a9d12f 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -20,6 +20,8 @@ source "arch/powerpc/platforms/embedded6xx/Kconfig"
source "arch/powerpc/platforms/44x/Kconfig"
source "arch/powerpc/platforms/40x/Kconfig"
source "arch/powerpc/platforms/amigaone/Kconfig"
+source "arch/powerpc/platforms/book3s/Kconfig"
+source "arch/powerpc/platforms/microwatt/Kconfig"
config KVM_GUEST
bool "KVM Guest support"
@@ -49,6 +51,7 @@ config PPC_NATIVE
config PPC_OF_BOOT_TRAMPOLINE
bool "Support booting from Open Firmware or yaboot"
depends on PPC_BOOK3S_32 || PPC64
+ select RELOCATABLE if PPC64
default y
help
Support from booting from Open Firmware or yaboot using an
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 7d271de8fcbd..0e1bb1cedd13 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -61,6 +61,7 @@ config 44x
select 4xx_SOC
select HAVE_PCI
select PHYS_64BIT
+ select PPC_HAVE_KUEP
endchoice
@@ -390,7 +391,7 @@ config PPC_HAVE_KUEP
config PPC_KUEP
bool "Kernel Userspace Execution Prevention"
depends on PPC_HAVE_KUEP
- default y if !PPC_BOOK3S_32
+ default y
help
Enable support for Kernel Userspace Execution Prevention (KUEP)
@@ -402,7 +403,7 @@ config PPC_HAVE_KUAP
config PPC_KUAP
bool "Kernel Userspace Access Protection"
depends on PPC_HAVE_KUAP
- default y if !PPC_BOOK3S_32
+ default y
help
Enable support for Kernel Userspace Access Protection (KUAP)
@@ -425,10 +426,6 @@ config PPC_MMU_NOHASH
def_bool y
depends on !PPC_BOOK3S
-config PPC_MMU_NOHASH_32
- def_bool y
- depends on PPC_MMU_NOHASH && PPC32
-
config PPC_BOOK3E_MMU
def_bool y
depends on FSL_BOOKE || PPC_BOOK3E
@@ -477,9 +474,9 @@ config SMP
If you don't know what to do here, say N.
config NR_CPUS
- int "Maximum number of CPUs (2-8192)"
- range 2 8192
- depends on SMP
+ int "Maximum number of CPUs (2-8192)" if SMP
+ range 2 8192 if SMP
+ default "1" if !SMP
default "32" if PPC64
default "4"
diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile
index 143d4417f6cc..94470fb27c99 100644
--- a/arch/powerpc/platforms/Makefile
+++ b/arch/powerpc/platforms/Makefile
@@ -22,3 +22,5 @@ obj-$(CONFIG_PPC_CELL) += cell/
obj-$(CONFIG_PPC_PS3) += ps3/
obj-$(CONFIG_EMBEDDED6xx) += embedded6xx/
obj-$(CONFIG_AMIGAONE) += amigaone/
+obj-$(CONFIG_PPC_BOOK3S) += book3s/
+obj-$(CONFIG_PPC_MICROWATT) += microwatt/
diff --git a/arch/powerpc/platforms/book3s/Kconfig b/arch/powerpc/platforms/book3s/Kconfig
new file mode 100644
index 000000000000..34c931592ef0
--- /dev/null
+++ b/arch/powerpc/platforms/book3s/Kconfig
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0
+config PPC_VAS
+ bool "IBM Virtual Accelerator Switchboard (VAS)"
+ depends on (PPC_POWERNV || PPC_PSERIES) && PPC_64K_PAGES
+ default y
+ help
+ This enables support for IBM Virtual Accelerator Switchboard (VAS).
+
+ VAS devices are found in POWER9-based and later systems, they
+ provide access to accelerator coprocessors such as NX-GZIP and
+ NX-842. This config allows the kernel to use NX-842 accelerators,
+ and user-mode APIs for the NX-GZIP accelerator on POWER9 PowerNV
+ and POWER10 PowerVM platforms.
+
+ If unsure, say "N".
diff --git a/arch/powerpc/platforms/book3s/Makefile b/arch/powerpc/platforms/book3s/Makefile
new file mode 100644
index 000000000000..e790f1910f61
--- /dev/null
+++ b/arch/powerpc/platforms/book3s/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_PPC_VAS) += vas-api.o
diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c
new file mode 100644
index 000000000000..30172e52e16b
--- /dev/null
+++ b/arch/powerpc/platforms/book3s/vas-api.c
@@ -0,0 +1,493 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * VAS user space API for its accelerators (Only NX-GZIP is supported now)
+ * Copyright (C) 2019 Haren Myneni, IBM Corp
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/cdev.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/kthread.h>
+#include <linux/sched/signal.h>
+#include <linux/mmu_context.h>
+#include <linux/io.h>
+#include <asm/vas.h>
+#include <uapi/asm/vas-api.h>
+
+/*
+ * The driver creates the device node that can be used as follows:
+ * For NX-GZIP
+ *
+ * fd = open("/dev/crypto/nx-gzip", O_RDWR);
+ * rc = ioctl(fd, VAS_TX_WIN_OPEN, &attr);
+ * paste_addr = mmap(NULL, PAGE_SIZE, prot, MAP_SHARED, fd, 0ULL).
+ * vas_copy(&crb, 0, 1);
+ * vas_paste(paste_addr, 0, 1);
+ * close(fd) or exit process to close window.
+ *
+ * where "vas_copy" and "vas_paste" are defined in copy-paste.h.
+ * copy/paste returns to the user space directly. So refer NX hardware
+ * documententation for exact copy/paste usage and completion / error
+ * conditions.
+ */
+
+/*
+ * Wrapper object for the nx-gzip device - there is just one instance of
+ * this node for the whole system.
+ */
+static struct coproc_dev {
+ struct cdev cdev;
+ struct device *device;
+ char *name;
+ dev_t devt;
+ struct class *class;
+ enum vas_cop_type cop_type;
+ const struct vas_user_win_ops *vops;
+} coproc_device;
+
+struct coproc_instance {
+ struct coproc_dev *coproc;
+ struct vas_window *txwin;
+};
+
+static char *coproc_devnode(struct device *dev, umode_t *mode)
+{
+ return kasprintf(GFP_KERNEL, "crypto/%s", dev_name(dev));
+}
+
+/*
+ * Take reference to pid and mm
+ */
+int get_vas_user_win_ref(struct vas_user_win_ref *task_ref)
+{
+ /*
+ * Window opened by a child thread may not be closed when
+ * it exits. So take reference to its pid and release it
+ * when the window is free by parent thread.
+ * Acquire a reference to the task's pid to make sure
+ * pid will not be re-used - needed only for multithread
+ * applications.
+ */
+ task_ref->pid = get_task_pid(current, PIDTYPE_PID);
+ /*
+ * Acquire a reference to the task's mm.
+ */
+ task_ref->mm = get_task_mm(current);
+ if (!task_ref->mm) {
+ put_pid(task_ref->pid);
+ pr_err("VAS: pid(%d): mm_struct is not found\n",
+ current->pid);
+ return -EPERM;
+ }
+
+ mmgrab(task_ref->mm);
+ mmput(task_ref->mm);
+ /*
+ * Process closes window during exit. In the case of
+ * multithread application, the child thread can open
+ * window and can exit without closing it. So takes tgid
+ * reference until window closed to make sure tgid is not
+ * reused.
+ */
+ task_ref->tgid = find_get_pid(task_tgid_vnr(current));
+
+ return 0;
+}
+
+/*
+ * Successful return must release the task reference with
+ * put_task_struct
+ */
+static bool ref_get_pid_and_task(struct vas_user_win_ref *task_ref,
+ struct task_struct **tskp, struct pid **pidp)
+{
+ struct task_struct *tsk;
+ struct pid *pid;
+
+ pid = task_ref->pid;
+ tsk = get_pid_task(pid, PIDTYPE_PID);
+ if (!tsk) {
+ pid = task_ref->tgid;
+ tsk = get_pid_task(pid, PIDTYPE_PID);
+ /*
+ * Parent thread (tgid) will be closing window when it
+ * exits. So should not get here.
+ */
+ if (WARN_ON_ONCE(!tsk))
+ return false;
+ }
+
+ /* Return if the task is exiting. */
+ if (tsk->flags & PF_EXITING) {
+ put_task_struct(tsk);
+ return false;
+ }
+
+ *tskp = tsk;
+ *pidp = pid;
+
+ return true;
+}
+
+/*
+ * Update the CSB to indicate a translation error.
+ *
+ * User space will be polling on CSB after the request is issued.
+ * If NX can handle the request without any issues, it updates CSB.
+ * Whereas if NX encounters page fault, the kernel will handle the
+ * fault and update CSB with translation error.
+ *
+ * If we are unable to update the CSB means copy_to_user failed due to
+ * invalid csb_addr, send a signal to the process.
+ */
+void vas_update_csb(struct coprocessor_request_block *crb,
+ struct vas_user_win_ref *task_ref)
+{
+ struct coprocessor_status_block csb;
+ struct kernel_siginfo info;
+ struct task_struct *tsk;
+ void __user *csb_addr;
+ struct pid *pid;
+ int rc;
+
+ /*
+ * NX user space windows can not be opened for task->mm=NULL
+ * and faults will not be generated for kernel requests.
+ */
+ if (WARN_ON_ONCE(!task_ref->mm))
+ return;
+
+ csb_addr = (void __user *)be64_to_cpu(crb->csb_addr);
+
+ memset(&csb, 0, sizeof(csb));
+ csb.cc = CSB_CC_FAULT_ADDRESS;
+ csb.ce = CSB_CE_TERMINATION;
+ csb.cs = 0;
+ csb.count = 0;
+
+ /*
+ * NX operates and returns in BE format as defined CRB struct.
+ * So saves fault_storage_addr in BE as NX pastes in FIFO and
+ * expects user space to convert to CPU format.
+ */
+ csb.address = crb->stamp.nx.fault_storage_addr;
+ csb.flags = 0;
+
+ /*
+ * Process closes send window after all pending NX requests are
+ * completed. In multi-thread applications, a child thread can
+ * open a window and can exit without closing it. May be some
+ * requests are pending or this window can be used by other
+ * threads later. We should handle faults if NX encounters
+ * pages faults on these requests. Update CSB with translation
+ * error and fault address. If csb_addr passed by user space is
+ * invalid, send SEGV signal to pid saved in window. If the
+ * child thread is not running, send the signal to tgid.
+ * Parent thread (tgid) will close this window upon its exit.
+ *
+ * pid and mm references are taken when window is opened by
+ * process (pid). So tgid is used only when child thread opens
+ * a window and exits without closing it.
+ */
+
+ if (!ref_get_pid_and_task(task_ref, &tsk, &pid))
+ return;
+
+ kthread_use_mm(task_ref->mm);
+ rc = copy_to_user(csb_addr, &csb, sizeof(csb));
+ /*
+ * User space polls on csb.flags (first byte). So add barrier
+ * then copy first byte with csb flags update.
+ */
+ if (!rc) {
+ csb.flags = CSB_V;
+ /* Make sure update to csb.flags is visible now */
+ smp_mb();
+ rc = copy_to_user(csb_addr, &csb, sizeof(u8));
+ }
+ kthread_unuse_mm(task_ref->mm);
+ put_task_struct(tsk);
+
+ /* Success */
+ if (!rc)
+ return;
+
+
+ pr_debug("Invalid CSB address 0x%p signalling pid(%d)\n",
+ csb_addr, pid_vnr(pid));
+
+ clear_siginfo(&info);
+ info.si_signo = SIGSEGV;
+ info.si_errno = EFAULT;
+ info.si_code = SEGV_MAPERR;
+ info.si_addr = csb_addr;
+ /*
+ * process will be polling on csb.flags after request is sent to
+ * NX. So generally CSB update should not fail except when an
+ * application passes invalid csb_addr. So an error message will
+ * be displayed and leave it to user space whether to ignore or
+ * handle this signal.
+ */
+ rcu_read_lock();
+ rc = kill_pid_info(SIGSEGV, &info, pid);
+ rcu_read_unlock();
+
+ pr_devel("%s(): pid %d kill_proc_info() rc %d\n", __func__,
+ pid_vnr(pid), rc);
+}
+
+void vas_dump_crb(struct coprocessor_request_block *crb)
+{
+ struct data_descriptor_entry *dde;
+ struct nx_fault_stamp *nx;
+
+ dde = &crb->source;
+ pr_devel("SrcDDE: addr 0x%llx, len %d, count %d, idx %d, flags %d\n",
+ be64_to_cpu(dde->address), be32_to_cpu(dde->length),
+ dde->count, dde->index, dde->flags);
+
+ dde = &crb->target;
+ pr_devel("TgtDDE: addr 0x%llx, len %d, count %d, idx %d, flags %d\n",
+ be64_to_cpu(dde->address), be32_to_cpu(dde->length),
+ dde->count, dde->index, dde->flags);
+
+ nx = &crb->stamp.nx;
+ pr_devel("NX Stamp: PSWID 0x%x, FSA 0x%llx, flags 0x%x, FS 0x%x\n",
+ be32_to_cpu(nx->pswid),
+ be64_to_cpu(crb->stamp.nx.fault_storage_addr),
+ nx->flags, nx->fault_status);
+}
+
+static int coproc_open(struct inode *inode, struct file *fp)
+{
+ struct coproc_instance *cp_inst;
+
+ cp_inst = kzalloc(sizeof(*cp_inst), GFP_KERNEL);
+ if (!cp_inst)
+ return -ENOMEM;
+
+ cp_inst->coproc = container_of(inode->i_cdev, struct coproc_dev,
+ cdev);
+ fp->private_data = cp_inst;
+
+ return 0;
+}
+
+static int coproc_ioc_tx_win_open(struct file *fp, unsigned long arg)
+{
+ void __user *uptr = (void __user *)arg;
+ struct vas_tx_win_open_attr uattr;
+ struct coproc_instance *cp_inst;
+ struct vas_window *txwin;
+ int rc;
+
+ cp_inst = fp->private_data;
+
+ /*
+ * One window for file descriptor
+ */
+ if (cp_inst->txwin)
+ return -EEXIST;
+
+ rc = copy_from_user(&uattr, uptr, sizeof(uattr));
+ if (rc) {
+ pr_err("%s(): copy_from_user() returns %d\n", __func__, rc);
+ return -EFAULT;
+ }
+
+ if (uattr.version != 1) {
+ pr_err("Invalid window open API version\n");
+ return -EINVAL;
+ }
+
+ if (!cp_inst->coproc->vops && !cp_inst->coproc->vops->open_win) {
+ pr_err("VAS API is not registered\n");
+ return -EACCES;
+ }
+
+ txwin = cp_inst->coproc->vops->open_win(uattr.vas_id, uattr.flags,
+ cp_inst->coproc->cop_type);
+ if (IS_ERR(txwin)) {
+ pr_err("%s() VAS window open failed, %ld\n", __func__,
+ PTR_ERR(txwin));
+ return PTR_ERR(txwin);
+ }
+
+ cp_inst->txwin = txwin;
+
+ return 0;
+}
+
+static int coproc_release(struct inode *inode, struct file *fp)
+{
+ struct coproc_instance *cp_inst = fp->private_data;
+ int rc;
+
+ if (cp_inst->txwin) {
+ if (cp_inst->coproc->vops &&
+ cp_inst->coproc->vops->close_win) {
+ rc = cp_inst->coproc->vops->close_win(cp_inst->txwin);
+ if (rc)
+ return rc;
+ }
+ cp_inst->txwin = NULL;
+ }
+
+ kfree(cp_inst);
+ fp->private_data = NULL;
+
+ /*
+ * We don't know here if user has other receive windows
+ * open, so we can't really call clear_thread_tidr().
+ * So, once the process calls set_thread_tidr(), the
+ * TIDR value sticks around until process exits, resulting
+ * in an extra copy in restore_sprs().
+ */
+
+ return 0;
+}
+
+static int coproc_mmap(struct file *fp, struct vm_area_struct *vma)
+{
+ struct coproc_instance *cp_inst = fp->private_data;
+ struct vas_window *txwin;
+ unsigned long pfn;
+ u64 paste_addr;
+ pgprot_t prot;
+ int rc;
+
+ txwin = cp_inst->txwin;
+
+ if ((vma->vm_end - vma->vm_start) > PAGE_SIZE) {
+ pr_debug("%s(): size 0x%zx, PAGE_SIZE 0x%zx\n", __func__,
+ (vma->vm_end - vma->vm_start), PAGE_SIZE);
+ return -EINVAL;
+ }
+
+ /* Ensure instance has an open send window */
+ if (!txwin) {
+ pr_err("%s(): No send window open?\n", __func__);
+ return -EINVAL;
+ }
+
+ if (!cp_inst->coproc->vops && !cp_inst->coproc->vops->paste_addr) {
+ pr_err("%s(): VAS API is not registered\n", __func__);
+ return -EACCES;
+ }
+
+ paste_addr = cp_inst->coproc->vops->paste_addr(txwin);
+ if (!paste_addr) {
+ pr_err("%s(): Window paste address failed\n", __func__);
+ return -EINVAL;
+ }
+
+ pfn = paste_addr >> PAGE_SHIFT;
+
+ /* flags, page_prot from cxl_mmap(), except we want cachable */
+ vma->vm_flags |= VM_IO | VM_PFNMAP;
+ vma->vm_page_prot = pgprot_cached(vma->vm_page_prot);
+
+ prot = __pgprot(pgprot_val(vma->vm_page_prot) | _PAGE_DIRTY);
+
+ rc = remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff,
+ vma->vm_end - vma->vm_start, prot);
+
+ pr_devel("%s(): paste addr %llx at %lx, rc %d\n", __func__,
+ paste_addr, vma->vm_start, rc);
+
+ return rc;
+}
+
+static long coproc_ioctl(struct file *fp, unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case VAS_TX_WIN_OPEN:
+ return coproc_ioc_tx_win_open(fp, arg);
+ default:
+ return -EINVAL;
+ }
+}
+
+static struct file_operations coproc_fops = {
+ .open = coproc_open,
+ .release = coproc_release,
+ .mmap = coproc_mmap,
+ .unlocked_ioctl = coproc_ioctl,
+};
+
+/*
+ * Supporting only nx-gzip coprocessor type now, but this API code
+ * extended to other coprocessor types later.
+ */
+int vas_register_coproc_api(struct module *mod, enum vas_cop_type cop_type,
+ const char *name,
+ const struct vas_user_win_ops *vops)
+{
+ int rc = -EINVAL;
+ dev_t devno;
+
+ rc = alloc_chrdev_region(&coproc_device.devt, 1, 1, name);
+ if (rc) {
+ pr_err("Unable to allocate coproc major number: %i\n", rc);
+ return rc;
+ }
+
+ pr_devel("%s device allocated, dev [%i,%i]\n", name,
+ MAJOR(coproc_device.devt), MINOR(coproc_device.devt));
+
+ coproc_device.class = class_create(mod, name);
+ if (IS_ERR(coproc_device.class)) {
+ rc = PTR_ERR(coproc_device.class);
+ pr_err("Unable to create %s class %d\n", name, rc);
+ goto err_class;
+ }
+ coproc_device.class->devnode = coproc_devnode;
+ coproc_device.cop_type = cop_type;
+ coproc_device.vops = vops;
+
+ coproc_fops.owner = mod;
+ cdev_init(&coproc_device.cdev, &coproc_fops);
+
+ devno = MKDEV(MAJOR(coproc_device.devt), 0);
+ rc = cdev_add(&coproc_device.cdev, devno, 1);
+ if (rc) {
+ pr_err("cdev_add() failed %d\n", rc);
+ goto err_cdev;
+ }
+
+ coproc_device.device = device_create(coproc_device.class, NULL,
+ devno, NULL, name, MINOR(devno));
+ if (IS_ERR(coproc_device.device)) {
+ rc = PTR_ERR(coproc_device.device);
+ pr_err("Unable to create coproc-%d %d\n", MINOR(devno), rc);
+ goto err;
+ }
+
+ pr_devel("%s: Added dev [%d,%d]\n", __func__, MAJOR(devno),
+ MINOR(devno));
+
+ return 0;
+
+err:
+ cdev_del(&coproc_device.cdev);
+err_cdev:
+ class_destroy(coproc_device.class);
+err_class:
+ unregister_chrdev_region(coproc_device.devt, 1);
+ return rc;
+}
+
+void vas_unregister_coproc_api(void)
+{
+ dev_t devno;
+
+ cdev_del(&coproc_device.cdev);
+ devno = MKDEV(MAJOR(coproc_device.devt), 0);
+ device_destroy(coproc_device.class, devno);
+
+ class_destroy(coproc_device.class);
+ unregister_chrdev_region(coproc_device.devt, 1);
+}
diff --git a/arch/powerpc/platforms/cell/spider-pci.c b/arch/powerpc/platforms/cell/spider-pci.c
index 93ea41680f54..a1c293f42a1f 100644
--- a/arch/powerpc/platforms/cell/spider-pci.c
+++ b/arch/powerpc/platforms/cell/spider-pci.c
@@ -25,10 +25,9 @@ struct spiderpci_iowa_private {
static void spiderpci_io_flush(struct iowa_bus *bus)
{
struct spiderpci_iowa_private *priv;
- u32 val;
priv = bus->private;
- val = in_be32(priv->regs + SPIDER_PCI_DUMMY_READ);
+ in_be32(priv->regs + SPIDER_PCI_DUMMY_READ);
iosync();
}
diff --git a/arch/powerpc/platforms/cell/spufs/switch.c b/arch/powerpc/platforms/cell/spufs/switch.c
index d56b4e3241cd..b41e81b22fdc 100644
--- a/arch/powerpc/platforms/cell/spufs/switch.c
+++ b/arch/powerpc/platforms/cell/spufs/switch.c
@@ -1657,14 +1657,13 @@ static inline void restore_spu_mb(struct spu_state *csa, struct spu *spu)
static inline void check_ppu_mb_stat(struct spu_state *csa, struct spu *spu)
{
struct spu_problem __iomem *prob = spu->problem;
- u32 dummy = 0;
/* Restore, Step 66:
* If CSA.MB_Stat[P]=0 (mailbox empty) then
* read from the PPU_MB register.
*/
if ((csa->prob.mb_stat_R & 0xFF) == 0) {
- dummy = in_be32(&prob->pu_mb_R);
+ in_be32(&prob->pu_mb_R);
eieio();
}
}
@@ -1672,14 +1671,13 @@ static inline void check_ppu_mb_stat(struct spu_state *csa, struct spu *spu)
static inline void check_ppuint_mb_stat(struct spu_state *csa, struct spu *spu)
{
struct spu_priv2 __iomem *priv2 = spu->priv2;
- u64 dummy = 0UL;
/* Restore, Step 66:
* If CSA.MB_Stat[I]=0 (mailbox empty) then
* read from the PPUINT_MB register.
*/
if ((csa->prob.mb_stat_R & 0xFF0000) == 0) {
- dummy = in_be64(&priv2->puint_mb_R);
+ in_be64(&priv2->puint_mb_R);
eieio();
spu_int_stat_clear(spu, 2, CLASS2_ENABLE_MAILBOX_INTR);
eieio();
diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c
index 53065d564161..85521b3e7098 100644
--- a/arch/powerpc/platforms/embedded6xx/holly.c
+++ b/arch/powerpc/platforms/embedded6xx/holly.c
@@ -251,8 +251,8 @@ static int ppc750_machine_check_exception(struct pt_regs *regs)
/* Are we prepared to handle this fault */
if ((entry = search_exception_tables(regs->nip)) != NULL) {
tsi108_clear_pci_cfg_error();
- regs->msr |= MSR_RI;
- regs->nip = extable_fixup(entry);
+ regs_set_return_msr(regs, regs->msr | MSR_RI);
+ regs_set_return_ip(regs, extable_fixup(entry));
return 1;
}
return 0;
diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
index 5565647dc879..d8da6a483e59 100644
--- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
+++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
@@ -173,8 +173,8 @@ static int mpc7448_machine_check_exception(struct pt_regs *regs)
/* Are we prepared to handle this fault */
if ((entry = search_exception_tables(regs->nip)) != NULL) {
tsi108_clear_pci_cfg_error();
- regs->msr |= MSR_RI;
- regs->nip = extable_fixup(entry);
+ regs_set_return_msr(regs, regs->msr | MSR_RI);
+ regs_set_return_ip(regs, extable_fixup(entry));
return 1;
}
return 0;
diff --git a/arch/powerpc/platforms/microwatt/Kconfig b/arch/powerpc/platforms/microwatt/Kconfig
new file mode 100644
index 000000000000..8f6a81978461
--- /dev/null
+++ b/arch/powerpc/platforms/microwatt/Kconfig
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0
+config PPC_MICROWATT
+ depends on PPC_BOOK3S_64 && !SMP
+ bool "Microwatt SoC platform"
+ select PPC_XICS
+ select PPC_ICS_NATIVE
+ select PPC_ICP_NATIVE
+ select PPC_NATIVE
+ select PPC_UDBG_16550
+ select ARCH_RANDOM
+ help
+ This option enables support for FPGA-based Microwatt implementations.
+
diff --git a/arch/powerpc/platforms/microwatt/Makefile b/arch/powerpc/platforms/microwatt/Makefile
new file mode 100644
index 000000000000..116d6d3ad3f0
--- /dev/null
+++ b/arch/powerpc/platforms/microwatt/Makefile
@@ -0,0 +1 @@
+obj-y += setup.o rng.o
diff --git a/arch/powerpc/platforms/microwatt/rng.c b/arch/powerpc/platforms/microwatt/rng.c
new file mode 100644
index 000000000000..3d8ee6eb7dad
--- /dev/null
+++ b/arch/powerpc/platforms/microwatt/rng.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Derived from arch/powerpc/platforms/powernv/rng.c, which is:
+ * Copyright 2013, Michael Ellerman, IBM Corporation.
+ */
+
+#define pr_fmt(fmt) "microwatt-rng: " fmt
+
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <asm/archrandom.h>
+#include <asm/cputable.h>
+#include <asm/machdep.h>
+
+#define DARN_ERR 0xFFFFFFFFFFFFFFFFul
+
+int microwatt_get_random_darn(unsigned long *v)
+{
+ unsigned long val;
+
+ /* Using DARN with L=1 - 64-bit conditioned random number */
+ asm volatile(PPC_DARN(%0, 1) : "=r"(val));
+
+ if (val == DARN_ERR)
+ return 0;
+
+ *v = val;
+
+ return 1;
+}
+
+static __init int rng_init(void)
+{
+ unsigned long val;
+ int i;
+
+ for (i = 0; i < 10; i++) {
+ if (microwatt_get_random_darn(&val)) {
+ ppc_md.get_random_seed = microwatt_get_random_darn;
+ return 0;
+ }
+ }
+
+ pr_warn("Unable to use DARN for get_random_seed()\n");
+
+ return -EIO;
+}
+machine_subsys_initcall(, rng_init);
diff --git a/arch/powerpc/platforms/microwatt/setup.c b/arch/powerpc/platforms/microwatt/setup.c
new file mode 100644
index 000000000000..0b02603bdb74
--- /dev/null
+++ b/arch/powerpc/platforms/microwatt/setup.c
@@ -0,0 +1,41 @@
+/*
+ * Microwatt FPGA-based SoC platform setup code.
+ *
+ * Copyright 2020 Paul Mackerras (paulus@ozlabs.org), IBM Corp.
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/stddef.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+
+#include <asm/machdep.h>
+#include <asm/time.h>
+#include <asm/xics.h>
+#include <asm/udbg.h>
+
+static void __init microwatt_init_IRQ(void)
+{
+ xics_init();
+}
+
+static int __init microwatt_probe(void)
+{
+ return of_machine_is_compatible("microwatt-soc");
+}
+
+static int __init microwatt_populate(void)
+{
+ return of_platform_default_populate(NULL, NULL, NULL);
+}
+machine_arch_initcall(microwatt, microwatt_populate);
+
+define_machine(microwatt) {
+ .name = "microwatt",
+ .probe = microwatt_probe,
+ .init_IRQ = microwatt_init_IRQ,
+ .progress = udbg_progress,
+ .calibrate_decr = generic_calibrate_decr,
+};
diff --git a/arch/powerpc/platforms/pasemi/idle.c b/arch/powerpc/platforms/pasemi/idle.c
index 1c954c90b0f4..9b88e3cded7d 100644
--- a/arch/powerpc/platforms/pasemi/idle.c
+++ b/arch/powerpc/platforms/pasemi/idle.c
@@ -37,7 +37,7 @@ static int pasemi_system_reset_exception(struct pt_regs *regs)
*/
if (regs->msr & SRR1_WAKEMASK)
- regs->nip = regs->link;
+ regs_set_return_ip(regs, regs->link);
switch (regs->msr & SRR1_WAKEMASK) {
case SRR1_WAKEDEC:
@@ -58,7 +58,7 @@ static int pasemi_system_reset_exception(struct pt_regs *regs)
restore_astate(hard_smp_processor_id());
/* everything handled */
- regs->msr |= MSR_RI;
+ regs_set_return_msr(regs, regs->msr | MSR_RI);
return 1;
}
diff --git a/arch/powerpc/platforms/powermac/bootx_init.c b/arch/powerpc/platforms/powermac/bootx_init.c
index 9d4ecd292255..d20ef35e6d9d 100644
--- a/arch/powerpc/platforms/powermac/bootx_init.c
+++ b/arch/powerpc/platforms/powermac/bootx_init.c
@@ -433,7 +433,7 @@ static void __init btext_welcome(boot_infos_t *bi)
bootx_printf("\nframe buffer at : 0x%x", bi->dispDeviceBase);
bootx_printf(" (phys), 0x%x", bi->logicalDisplayBase);
bootx_printf(" (log)");
- bootx_printf("\nklimit : 0x%x",(unsigned long)klimit);
+ bootx_printf("\nklimit : 0x%x",(unsigned long)_end);
bootx_printf("\nboot_info at : 0x%x", bi);
__asm__ __volatile__ ("mfmsr %0" : "=r" (flags));
bootx_printf("\nMSR : 0x%x", flags);
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index adae2a6712e1..bdfea6d6ab69 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -810,7 +810,7 @@ static int smp_core99_kick_cpu(int nr)
* b __secondary_start_pmac_0 + nr*8
*/
target = (unsigned long) __secondary_start_pmac_0 + nr * 8;
- patch_branch((struct ppc_inst *)vector, target, BRANCH_SET_LINK);
+ patch_branch(vector, target, BRANCH_SET_LINK);
/* Put some life in our friend */
pmac_call_feature(PMAC_FTR_RESET_CPU, NULL, nr, 0);
@@ -823,7 +823,7 @@ static int smp_core99_kick_cpu(int nr)
mdelay(1);
/* Restore our exception vector */
- patch_instruction((struct ppc_inst *)vector, ppc_inst(save_vector));
+ patch_instruction(vector, ppc_inst(save_vector));
local_irq_restore(flags);
if (ppc_md.progress) ppc_md.progress("smp_core99_kick_cpu done", 0x347);
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index 619b093a0657..043eefbbdd28 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -33,20 +33,6 @@ config PPC_MEMTRACE
Enabling this option allows for runtime allocation of memory (RAM)
for hardware tracing.
-config PPC_VAS
- bool "IBM Virtual Accelerator Switchboard (VAS)"
- depends on PPC_POWERNV && PPC_64K_PAGES
- default y
- help
- This enables support for IBM Virtual Accelerator Switchboard (VAS).
-
- VAS allows accelerators in co-processors like NX-GZIP and NX-842
- to be accessible to kernel subsystems and user processes.
-
- VAS adapters are found in POWER9 based systems.
-
- If unsure, say N.
-
config SCOM_DEBUGFS
bool "Expose SCOM controllers via debugfs"
depends on DEBUG_FS
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index be2546b96816..dc7b37c23b60 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -18,7 +18,7 @@ obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o
obj-$(CONFIG_OPAL_PRD) += opal-prd.o
obj-$(CONFIG_PERF_EVENTS) += opal-imc.o
obj-$(CONFIG_PPC_MEMTRACE) += memtrace.o
-obj-$(CONFIG_PPC_VAS) += vas.o vas-window.o vas-debug.o vas-fault.o vas-api.o
+obj-$(CONFIG_PPC_VAS) += vas.o vas-window.o vas-debug.o vas-fault.o
obj-$(CONFIG_OCXL_BASE) += ocxl.o
obj-$(CONFIG_SCOM_DEBUGFS) += opal-xscom.o
obj-$(CONFIG_PPC_SECURE_BOOT) += opal-secvar.o
diff --git a/arch/powerpc/platforms/powernv/opal-call.c b/arch/powerpc/platforms/powernv/opal-call.c
index 01401e3da7ca..f812c74c61e5 100644
--- a/arch/powerpc/platforms/powernv/opal-call.c
+++ b/arch/powerpc/platforms/powernv/opal-call.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/percpu.h>
#include <linux/jump_label.h>
+#include <asm/interrupt.h>
#include <asm/opal-api.h>
#include <asm/trace.h>
#include <asm/asm-prototypes.h>
@@ -100,6 +101,9 @@ static int64_t opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3,
bool mmu = (msr & (MSR_IR|MSR_DR));
int64_t ret;
+ /* OPAL call / firmware may use SRR and/or HSRR */
+ srr_regs_clobbered();
+
msr &= ~MSR_EE;
if (unlikely(!mmu))
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 303d7c775740..2835376e61a4 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -773,7 +773,7 @@ bool opal_mce_check_early_recovery(struct pt_regs *regs)
* Setup regs->nip to rfi into fixup address.
*/
if (recover_addr)
- regs->nip = recover_addr;
+ regs_set_return_ip(regs, recover_addr);
out:
return !!recover_addr;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index b18468dc31ff..6bb3c52633fb 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -711,7 +711,7 @@ int pnv_pci_cfg_write(struct pci_dn *pdn,
return PCIBIOS_SUCCESSFUL;
}
-#if CONFIG_EEH
+#ifdef CONFIG_EEH
static bool pnv_pci_cfg_check(struct pci_dn *pdn)
{
struct eeh_dev *edev = NULL;
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index 73207b53dc2b..7e98b00ea2e8 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -169,6 +169,16 @@ static void update_hid_in_slw(u64 hid0)
}
}
+static inline void update_power8_hid0(unsigned long hid0)
+{
+ /*
+ * The HID0 update on Power8 should at the very least be
+ * preceded by a SYNC instruction followed by an ISYNC
+ * instruction
+ */
+ asm volatile("sync; mtspr %0,%1; isync":: "i"(SPRN_HID0), "r"(hid0));
+}
+
static void unsplit_core(void)
{
u64 hid0, mask;
diff --git a/arch/powerpc/platforms/powernv/vas-api.c b/arch/powerpc/platforms/powernv/vas-api.c
deleted file mode 100644
index 98ed5d8c5441..000000000000
--- a/arch/powerpc/platforms/powernv/vas-api.c
+++ /dev/null
@@ -1,278 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * VAS user space API for its accelerators (Only NX-GZIP is supported now)
- * Copyright (C) 2019 Haren Myneni, IBM Corp
- */
-
-#include <linux/kernel.h>
-#include <linux/device.h>
-#include <linux/cdev.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
-#include <asm/vas.h>
-#include <uapi/asm/vas-api.h>
-#include "vas.h"
-
-/*
- * The driver creates the device node that can be used as follows:
- * For NX-GZIP
- *
- * fd = open("/dev/crypto/nx-gzip", O_RDWR);
- * rc = ioctl(fd, VAS_TX_WIN_OPEN, &attr);
- * paste_addr = mmap(NULL, PAGE_SIZE, prot, MAP_SHARED, fd, 0ULL).
- * vas_copy(&crb, 0, 1);
- * vas_paste(paste_addr, 0, 1);
- * close(fd) or exit process to close window.
- *
- * where "vas_copy" and "vas_paste" are defined in copy-paste.h.
- * copy/paste returns to the user space directly. So refer NX hardware
- * documententation for exact copy/paste usage and completion / error
- * conditions.
- */
-
-/*
- * Wrapper object for the nx-gzip device - there is just one instance of
- * this node for the whole system.
- */
-static struct coproc_dev {
- struct cdev cdev;
- struct device *device;
- char *name;
- dev_t devt;
- struct class *class;
- enum vas_cop_type cop_type;
-} coproc_device;
-
-struct coproc_instance {
- struct coproc_dev *coproc;
- struct vas_window *txwin;
-};
-
-static char *coproc_devnode(struct device *dev, umode_t *mode)
-{
- return kasprintf(GFP_KERNEL, "crypto/%s", dev_name(dev));
-}
-
-static int coproc_open(struct inode *inode, struct file *fp)
-{
- struct coproc_instance *cp_inst;
-
- cp_inst = kzalloc(sizeof(*cp_inst), GFP_KERNEL);
- if (!cp_inst)
- return -ENOMEM;
-
- cp_inst->coproc = container_of(inode->i_cdev, struct coproc_dev,
- cdev);
- fp->private_data = cp_inst;
-
- return 0;
-}
-
-static int coproc_ioc_tx_win_open(struct file *fp, unsigned long arg)
-{
- void __user *uptr = (void __user *)arg;
- struct vas_tx_win_attr txattr = {};
- struct vas_tx_win_open_attr uattr;
- struct coproc_instance *cp_inst;
- struct vas_window *txwin;
- int rc, vasid;
-
- cp_inst = fp->private_data;
-
- /*
- * One window for file descriptor
- */
- if (cp_inst->txwin)
- return -EEXIST;
-
- rc = copy_from_user(&uattr, uptr, sizeof(uattr));
- if (rc) {
- pr_err("%s(): copy_from_user() returns %d\n", __func__, rc);
- return -EFAULT;
- }
-
- if (uattr.version != 1) {
- pr_err("Invalid version\n");
- return -EINVAL;
- }
-
- vasid = uattr.vas_id;
-
- vas_init_tx_win_attr(&txattr, cp_inst->coproc->cop_type);
-
- txattr.lpid = mfspr(SPRN_LPID);
- txattr.pidr = mfspr(SPRN_PID);
- txattr.user_win = true;
- txattr.rsvd_txbuf_count = false;
- txattr.pswid = false;
-
- pr_devel("Pid %d: Opening txwin, PIDR %ld\n", txattr.pidr,
- mfspr(SPRN_PID));
-
- txwin = vas_tx_win_open(vasid, cp_inst->coproc->cop_type, &txattr);
- if (IS_ERR(txwin)) {
- pr_err("%s() vas_tx_win_open() failed, %ld\n", __func__,
- PTR_ERR(txwin));
- return PTR_ERR(txwin);
- }
-
- cp_inst->txwin = txwin;
-
- return 0;
-}
-
-static int coproc_release(struct inode *inode, struct file *fp)
-{
- struct coproc_instance *cp_inst = fp->private_data;
-
- if (cp_inst->txwin) {
- vas_win_close(cp_inst->txwin);
- cp_inst->txwin = NULL;
- }
-
- kfree(cp_inst);
- fp->private_data = NULL;
-
- /*
- * We don't know here if user has other receive windows
- * open, so we can't really call clear_thread_tidr().
- * So, once the process calls set_thread_tidr(), the
- * TIDR value sticks around until process exits, resulting
- * in an extra copy in restore_sprs().
- */
-
- return 0;
-}
-
-static int coproc_mmap(struct file *fp, struct vm_area_struct *vma)
-{
- struct coproc_instance *cp_inst = fp->private_data;
- struct vas_window *txwin;
- unsigned long pfn;
- u64 paste_addr;
- pgprot_t prot;
- int rc;
-
- txwin = cp_inst->txwin;
-
- if ((vma->vm_end - vma->vm_start) > PAGE_SIZE) {
- pr_debug("%s(): size 0x%zx, PAGE_SIZE 0x%zx\n", __func__,
- (vma->vm_end - vma->vm_start), PAGE_SIZE);
- return -EINVAL;
- }
-
- /* Ensure instance has an open send window */
- if (!txwin) {
- pr_err("%s(): No send window open?\n", __func__);
- return -EINVAL;
- }
-
- vas_win_paste_addr(txwin, &paste_addr, NULL);
- pfn = paste_addr >> PAGE_SHIFT;
-
- /* flags, page_prot from cxl_mmap(), except we want cachable */
- vma->vm_flags |= VM_IO | VM_PFNMAP;
- vma->vm_page_prot = pgprot_cached(vma->vm_page_prot);
-
- prot = __pgprot(pgprot_val(vma->vm_page_prot) | _PAGE_DIRTY);
-
- rc = remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff,
- vma->vm_end - vma->vm_start, prot);
-
- pr_devel("%s(): paste addr %llx at %lx, rc %d\n", __func__,
- paste_addr, vma->vm_start, rc);
-
- return rc;
-}
-
-static long coproc_ioctl(struct file *fp, unsigned int cmd, unsigned long arg)
-{
- switch (cmd) {
- case VAS_TX_WIN_OPEN:
- return coproc_ioc_tx_win_open(fp, arg);
- default:
- return -EINVAL;
- }
-}
-
-static struct file_operations coproc_fops = {
- .open = coproc_open,
- .release = coproc_release,
- .mmap = coproc_mmap,
- .unlocked_ioctl = coproc_ioctl,
-};
-
-/*
- * Supporting only nx-gzip coprocessor type now, but this API code
- * extended to other coprocessor types later.
- */
-int vas_register_coproc_api(struct module *mod, enum vas_cop_type cop_type,
- const char *name)
-{
- int rc = -EINVAL;
- dev_t devno;
-
- rc = alloc_chrdev_region(&coproc_device.devt, 1, 1, name);
- if (rc) {
- pr_err("Unable to allocate coproc major number: %i\n", rc);
- return rc;
- }
-
- pr_devel("%s device allocated, dev [%i,%i]\n", name,
- MAJOR(coproc_device.devt), MINOR(coproc_device.devt));
-
- coproc_device.class = class_create(mod, name);
- if (IS_ERR(coproc_device.class)) {
- rc = PTR_ERR(coproc_device.class);
- pr_err("Unable to create %s class %d\n", name, rc);
- goto err_class;
- }
- coproc_device.class->devnode = coproc_devnode;
- coproc_device.cop_type = cop_type;
-
- coproc_fops.owner = mod;
- cdev_init(&coproc_device.cdev, &coproc_fops);
-
- devno = MKDEV(MAJOR(coproc_device.devt), 0);
- rc = cdev_add(&coproc_device.cdev, devno, 1);
- if (rc) {
- pr_err("cdev_add() failed %d\n", rc);
- goto err_cdev;
- }
-
- coproc_device.device = device_create(coproc_device.class, NULL,
- devno, NULL, name, MINOR(devno));
- if (IS_ERR(coproc_device.device)) {
- rc = PTR_ERR(coproc_device.device);
- pr_err("Unable to create coproc-%d %d\n", MINOR(devno), rc);
- goto err;
- }
-
- pr_devel("%s: Added dev [%d,%d]\n", __func__, MAJOR(devno),
- MINOR(devno));
-
- return 0;
-
-err:
- cdev_del(&coproc_device.cdev);
-err_cdev:
- class_destroy(coproc_device.class);
-err_class:
- unregister_chrdev_region(coproc_device.devt, 1);
- return rc;
-}
-EXPORT_SYMBOL_GPL(vas_register_coproc_api);
-
-void vas_unregister_coproc_api(void)
-{
- dev_t devno;
-
- cdev_del(&coproc_device.cdev);
- devno = MKDEV(MAJOR(coproc_device.devt), 0);
- device_destroy(coproc_device.class, devno);
-
- class_destroy(coproc_device.class);
- unregister_chrdev_region(coproc_device.devt, 1);
-}
-EXPORT_SYMBOL_GPL(vas_unregister_coproc_api);
diff --git a/arch/powerpc/platforms/powernv/vas-debug.c b/arch/powerpc/platforms/powernv/vas-debug.c
index 41fa90d2f4ab..3ce89a4b54be 100644
--- a/arch/powerpc/platforms/powernv/vas-debug.c
+++ b/arch/powerpc/platforms/powernv/vas-debug.c
@@ -9,6 +9,7 @@
#include <linux/slab.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
+#include <asm/vas.h>
#include "vas.h"
static struct dentry *vas_debugfs;
@@ -28,7 +29,7 @@ static char *cop_to_str(int cop)
static int info_show(struct seq_file *s, void *private)
{
- struct vas_window *window = s->private;
+ struct pnv_vas_window *window = s->private;
mutex_lock(&vas_mutex);
@@ -36,9 +37,9 @@ static int info_show(struct seq_file *s, void *private)
if (!window->hvwc_map)
goto unlock;
- seq_printf(s, "Type: %s, %s\n", cop_to_str(window->cop),
+ seq_printf(s, "Type: %s, %s\n", cop_to_str(window->vas_win.cop),
window->tx_win ? "Send" : "Receive");
- seq_printf(s, "Pid : %d\n", vas_window_pid(window));
+ seq_printf(s, "Pid : %d\n", vas_window_pid(&window->vas_win));
unlock:
mutex_unlock(&vas_mutex);
@@ -47,7 +48,7 @@ unlock:
DEFINE_SHOW_ATTRIBUTE(info);
-static inline void print_reg(struct seq_file *s, struct vas_window *win,
+static inline void print_reg(struct seq_file *s, struct pnv_vas_window *win,
char *name, u32 reg)
{
seq_printf(s, "0x%016llx %s\n", read_hvwc_reg(win, name, reg), name);
@@ -55,7 +56,7 @@ static inline void print_reg(struct seq_file *s, struct vas_window *win,
static int hvwc_show(struct seq_file *s, void *private)
{
- struct vas_window *window = s->private;
+ struct pnv_vas_window *window = s->private;
mutex_lock(&vas_mutex);
@@ -103,8 +104,10 @@ unlock:
DEFINE_SHOW_ATTRIBUTE(hvwc);
-void vas_window_free_dbgdir(struct vas_window *window)
+void vas_window_free_dbgdir(struct pnv_vas_window *pnv_win)
{
+ struct vas_window *window = &pnv_win->vas_win;
+
if (window->dbgdir) {
debugfs_remove_recursive(window->dbgdir);
kfree(window->dbgname);
@@ -113,21 +116,21 @@ void vas_window_free_dbgdir(struct vas_window *window)
}
}
-void vas_window_init_dbgdir(struct vas_window *window)
+void vas_window_init_dbgdir(struct pnv_vas_window *window)
{
struct dentry *d;
if (!window->vinst->dbgdir)
return;
- window->dbgname = kzalloc(16, GFP_KERNEL);
- if (!window->dbgname)
+ window->vas_win.dbgname = kzalloc(16, GFP_KERNEL);
+ if (!window->vas_win.dbgname)
return;
- snprintf(window->dbgname, 16, "w%d", window->winid);
+ snprintf(window->vas_win.dbgname, 16, "w%d", window->vas_win.winid);
- d = debugfs_create_dir(window->dbgname, window->vinst->dbgdir);
- window->dbgdir = d;
+ d = debugfs_create_dir(window->vas_win.dbgname, window->vinst->dbgdir);
+ window->vas_win.dbgdir = d;
debugfs_create_file("info", 0444, d, window, &info_fops);
debugfs_create_file("hvwc", 0444, d, window, &hvwc_fops);
diff --git a/arch/powerpc/platforms/powernv/vas-fault.c b/arch/powerpc/platforms/powernv/vas-fault.c
index 3d21fce254b7..a7aabc18039e 100644
--- a/arch/powerpc/platforms/powernv/vas-fault.c
+++ b/arch/powerpc/platforms/powernv/vas-fault.c
@@ -26,150 +26,6 @@
*/
#define VAS_FAULT_WIN_FIFO_SIZE (4 << 20)
-static void dump_crb(struct coprocessor_request_block *crb)
-{
- struct data_descriptor_entry *dde;
- struct nx_fault_stamp *nx;
-
- dde = &crb->source;
- pr_devel("SrcDDE: addr 0x%llx, len %d, count %d, idx %d, flags %d\n",
- be64_to_cpu(dde->address), be32_to_cpu(dde->length),
- dde->count, dde->index, dde->flags);
-
- dde = &crb->target;
- pr_devel("TgtDDE: addr 0x%llx, len %d, count %d, idx %d, flags %d\n",
- be64_to_cpu(dde->address), be32_to_cpu(dde->length),
- dde->count, dde->index, dde->flags);
-
- nx = &crb->stamp.nx;
- pr_devel("NX Stamp: PSWID 0x%x, FSA 0x%llx, flags 0x%x, FS 0x%x\n",
- be32_to_cpu(nx->pswid),
- be64_to_cpu(crb->stamp.nx.fault_storage_addr),
- nx->flags, nx->fault_status);
-}
-
-/*
- * Update the CSB to indicate a translation error.
- *
- * User space will be polling on CSB after the request is issued.
- * If NX can handle the request without any issues, it updates CSB.
- * Whereas if NX encounters page fault, the kernel will handle the
- * fault and update CSB with translation error.
- *
- * If we are unable to update the CSB means copy_to_user failed due to
- * invalid csb_addr, send a signal to the process.
- */
-static void update_csb(struct vas_window *window,
- struct coprocessor_request_block *crb)
-{
- struct coprocessor_status_block csb;
- struct kernel_siginfo info;
- struct task_struct *tsk;
- void __user *csb_addr;
- struct pid *pid;
- int rc;
-
- /*
- * NX user space windows can not be opened for task->mm=NULL
- * and faults will not be generated for kernel requests.
- */
- if (WARN_ON_ONCE(!window->mm || !window->user_win))
- return;
-
- csb_addr = (void __user *)be64_to_cpu(crb->csb_addr);
-
- memset(&csb, 0, sizeof(csb));
- csb.cc = CSB_CC_FAULT_ADDRESS;
- csb.ce = CSB_CE_TERMINATION;
- csb.cs = 0;
- csb.count = 0;
-
- /*
- * NX operates and returns in BE format as defined CRB struct.
- * So saves fault_storage_addr in BE as NX pastes in FIFO and
- * expects user space to convert to CPU format.
- */
- csb.address = crb->stamp.nx.fault_storage_addr;
- csb.flags = 0;
-
- pid = window->pid;
- tsk = get_pid_task(pid, PIDTYPE_PID);
- /*
- * Process closes send window after all pending NX requests are
- * completed. In multi-thread applications, a child thread can
- * open a window and can exit without closing it. May be some
- * requests are pending or this window can be used by other
- * threads later. We should handle faults if NX encounters
- * pages faults on these requests. Update CSB with translation
- * error and fault address. If csb_addr passed by user space is
- * invalid, send SEGV signal to pid saved in window. If the
- * child thread is not running, send the signal to tgid.
- * Parent thread (tgid) will close this window upon its exit.
- *
- * pid and mm references are taken when window is opened by
- * process (pid). So tgid is used only when child thread opens
- * a window and exits without closing it.
- */
- if (!tsk) {
- pid = window->tgid;
- tsk = get_pid_task(pid, PIDTYPE_PID);
- /*
- * Parent thread (tgid) will be closing window when it
- * exits. So should not get here.
- */
- if (WARN_ON_ONCE(!tsk))
- return;
- }
-
- /* Return if the task is exiting. */
- if (tsk->flags & PF_EXITING) {
- put_task_struct(tsk);
- return;
- }
-
- kthread_use_mm(window->mm);
- rc = copy_to_user(csb_addr, &csb, sizeof(csb));
- /*
- * User space polls on csb.flags (first byte). So add barrier
- * then copy first byte with csb flags update.
- */
- if (!rc) {
- csb.flags = CSB_V;
- /* Make sure update to csb.flags is visible now */
- smp_mb();
- rc = copy_to_user(csb_addr, &csb, sizeof(u8));
- }
- kthread_unuse_mm(window->mm);
- put_task_struct(tsk);
-
- /* Success */
- if (!rc)
- return;
-
- pr_debug("Invalid CSB address 0x%p signalling pid(%d)\n",
- csb_addr, pid_vnr(pid));
-
- clear_siginfo(&info);
- info.si_signo = SIGSEGV;
- info.si_errno = EFAULT;
- info.si_code = SEGV_MAPERR;
- info.si_addr = csb_addr;
-
- /*
- * process will be polling on csb.flags after request is sent to
- * NX. So generally CSB update should not fail except when an
- * application passes invalid csb_addr. So an error message will
- * be displayed and leave it to user space whether to ignore or
- * handle this signal.
- */
- rcu_read_lock();
- rc = kill_pid_info(SIGSEGV, &info, pid);
- rcu_read_unlock();
-
- pr_devel("%s(): pid %d kill_proc_info() rc %d\n", __func__,
- pid_vnr(pid), rc);
-}
-
static void dump_fifo(struct vas_instance *vinst, void *entry)
{
unsigned long *end = vinst->fault_fifo + vinst->fault_fifo_size;
@@ -212,7 +68,7 @@ irqreturn_t vas_fault_thread_fn(int irq, void *data)
struct vas_instance *vinst = data;
struct coprocessor_request_block *crb, *entry;
struct coprocessor_request_block buf;
- struct vas_window *window;
+ struct pnv_vas_window *window;
unsigned long flags;
void *fifo;
@@ -272,7 +128,7 @@ irqreturn_t vas_fault_thread_fn(int irq, void *data)
vinst->vas_id, vinst->fault_fifo, fifo,
vinst->fault_crbs);
- dump_crb(crb);
+ vas_dump_crb(crb);
window = vas_pswid_to_window(vinst,
be32_to_cpu(crb->stamp.nx.pswid));
@@ -293,7 +149,14 @@ irqreturn_t vas_fault_thread_fn(int irq, void *data)
WARN_ON_ONCE(1);
} else {
- update_csb(window, crb);
+ /*
+ * NX sees faults only with user space windows.
+ */
+ if (window->user_win)
+ vas_update_csb(crb, &window->vas_win.task_ref);
+ else
+ WARN_ON_ONCE(!window->user_win);
+
/*
* Return credit for send window after processing
* fault CRB.
@@ -336,6 +199,7 @@ irqreturn_t vas_fault_handler(int irq, void *dev_id)
int vas_setup_fault_window(struct vas_instance *vinst)
{
struct vas_rx_win_attr attr;
+ struct vas_window *win;
vinst->fault_fifo_size = VAS_FAULT_WIN_FIFO_SIZE;
vinst->fault_fifo = kzalloc(vinst->fault_fifo_size, GFP_KERNEL);
@@ -364,18 +228,17 @@ int vas_setup_fault_window(struct vas_instance *vinst)
attr.lnotify_pid = mfspr(SPRN_PID);
attr.lnotify_tid = mfspr(SPRN_PID);
- vinst->fault_win = vas_rx_win_open(vinst->vas_id, VAS_COP_TYPE_FAULT,
- &attr);
-
- if (IS_ERR(vinst->fault_win)) {
- pr_err("VAS: Error %ld opening FaultWin\n",
- PTR_ERR(vinst->fault_win));
+ win = vas_rx_win_open(vinst->vas_id, VAS_COP_TYPE_FAULT, &attr);
+ if (IS_ERR(win)) {
+ pr_err("VAS: Error %ld opening FaultWin\n", PTR_ERR(win));
kfree(vinst->fault_fifo);
- return PTR_ERR(vinst->fault_win);
+ return PTR_ERR(win);
}
+ vinst->fault_win = container_of(win, struct pnv_vas_window, vas_win);
+
pr_devel("VAS: Created FaultWin %d, LPID/PID/TID [%d/%d/%d]\n",
- vinst->fault_win->winid, attr.lnotify_lpid,
+ vinst->fault_win->vas_win.winid, attr.lnotify_lpid,
attr.lnotify_pid, attr.lnotify_tid);
return 0;
diff --git a/arch/powerpc/platforms/powernv/vas-trace.h b/arch/powerpc/platforms/powernv/vas-trace.h
index a449b9f0c12e..ca2e08f2ddc0 100644
--- a/arch/powerpc/platforms/powernv/vas-trace.h
+++ b/arch/powerpc/platforms/powernv/vas-trace.h
@@ -80,7 +80,7 @@ TRACE_EVENT( vas_tx_win_open,
TRACE_EVENT( vas_paste_crb,
TP_PROTO(struct task_struct *tsk,
- struct vas_window *win),
+ struct pnv_vas_window *win),
TP_ARGS(tsk, win),
@@ -96,7 +96,7 @@ TRACE_EVENT( vas_paste_crb,
TP_fast_assign(
__entry->pid = tsk->pid;
__entry->vasid = win->vinst->vas_id;
- __entry->winid = win->winid;
+ __entry->winid = win->vas_win.winid;
__entry->paste_kaddr = (unsigned long)win->paste_kaddr
),
diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index 5f5fe63a3d1c..0f8d39fbf2b2 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -16,6 +16,7 @@
#include <linux/mmu_context.h>
#include <asm/switch_to.h>
#include <asm/ppc-opcode.h>
+#include <asm/vas.h>
#include "vas.h"
#include "copy-paste.h"
@@ -26,14 +27,14 @@
* Compute the paste address region for the window @window using the
* ->paste_base_addr and ->paste_win_id_shift we got from device tree.
*/
-void vas_win_paste_addr(struct vas_window *window, u64 *addr, int *len)
+void vas_win_paste_addr(struct pnv_vas_window *window, u64 *addr, int *len)
{
int winid;
u64 base, shift;
base = window->vinst->paste_base_addr;
shift = window->vinst->paste_win_id_shift;
- winid = window->winid;
+ winid = window->vas_win.winid;
*addr = base + (winid << shift);
if (len)
@@ -42,23 +43,23 @@ void vas_win_paste_addr(struct vas_window *window, u64 *addr, int *len)
pr_debug("Txwin #%d: Paste addr 0x%llx\n", winid, *addr);
}
-static inline void get_hvwc_mmio_bar(struct vas_window *window,
+static inline void get_hvwc_mmio_bar(struct pnv_vas_window *window,
u64 *start, int *len)
{
u64 pbaddr;
pbaddr = window->vinst->hvwc_bar_start;
- *start = pbaddr + window->winid * VAS_HVWC_SIZE;
+ *start = pbaddr + window->vas_win.winid * VAS_HVWC_SIZE;
*len = VAS_HVWC_SIZE;
}
-static inline void get_uwc_mmio_bar(struct vas_window *window,
+static inline void get_uwc_mmio_bar(struct pnv_vas_window *window,
u64 *start, int *len)
{
u64 pbaddr;
pbaddr = window->vinst->uwc_bar_start;
- *start = pbaddr + window->winid * VAS_UWC_SIZE;
+ *start = pbaddr + window->vas_win.winid * VAS_UWC_SIZE;
*len = VAS_UWC_SIZE;
}
@@ -67,7 +68,7 @@ static inline void get_uwc_mmio_bar(struct vas_window *window,
* space. Unlike MMIO regions (map_mmio_region() below), paste region must
* be mapped cache-able and is only applicable to send windows.
*/
-static void *map_paste_region(struct vas_window *txwin)
+static void *map_paste_region(struct pnv_vas_window *txwin)
{
int len;
void *map;
@@ -75,7 +76,7 @@ static void *map_paste_region(struct vas_window *txwin)
u64 start;
name = kasprintf(GFP_KERNEL, "window-v%d-w%d", txwin->vinst->vas_id,
- txwin->winid);
+ txwin->vas_win.winid);
if (!name)
goto free_name;
@@ -132,7 +133,7 @@ static void unmap_region(void *addr, u64 start, int len)
/*
* Unmap the paste address region for a window.
*/
-static void unmap_paste_region(struct vas_window *window)
+static void unmap_paste_region(struct pnv_vas_window *window)
{
int len;
u64 busaddr_start;
@@ -153,7 +154,7 @@ static void unmap_paste_region(struct vas_window *window)
* path, just minimize the time we hold the mutex for now. We can add
* a per-instance mutex later if necessary.
*/
-static void unmap_winctx_mmio_bars(struct vas_window *window)
+static void unmap_winctx_mmio_bars(struct pnv_vas_window *window)
{
int len;
void *uwc_map;
@@ -186,7 +187,7 @@ static void unmap_winctx_mmio_bars(struct vas_window *window)
* OS/User Window Context (UWC) MMIO Base Address Region for the given window.
* Map these bus addresses and save the mapped kernel addresses in @window.
*/
-static int map_winctx_mmio_bars(struct vas_window *window)
+static int map_winctx_mmio_bars(struct pnv_vas_window *window)
{
int len;
u64 start;
@@ -214,7 +215,7 @@ static int map_winctx_mmio_bars(struct vas_window *window)
* registers are not sequential. And, we can only write to offsets
* with valid registers.
*/
-static void reset_window_regs(struct vas_window *window)
+static void reset_window_regs(struct pnv_vas_window *window)
{
write_hvwc_reg(window, VREG(LPID), 0ULL);
write_hvwc_reg(window, VREG(PID), 0ULL);
@@ -270,7 +271,7 @@ static void reset_window_regs(struct vas_window *window)
* want to add fields to vas_winctx and move the initialization to
* init_vas_winctx_regs().
*/
-static void init_xlate_regs(struct vas_window *window, bool user_win)
+static void init_xlate_regs(struct pnv_vas_window *window, bool user_win)
{
u64 lpcr, val;
@@ -335,7 +336,7 @@ static void init_xlate_regs(struct vas_window *window, bool user_win)
*
* TODO: Reserved (aka dedicated) send buffers are not supported yet.
*/
-static void init_rsvd_tx_buf_count(struct vas_window *txwin,
+static void init_rsvd_tx_buf_count(struct pnv_vas_window *txwin,
struct vas_winctx *winctx)
{
write_hvwc_reg(txwin, VREG(TX_RSVD_BUF_COUNT), 0ULL);
@@ -357,7 +358,7 @@ static void init_rsvd_tx_buf_count(struct vas_window *txwin,
* as a one-time task? That could work for NX but what about other
* receivers? Let the receivers tell us the rx-fifo buffers for now.
*/
-static void init_winctx_regs(struct vas_window *window,
+static void init_winctx_regs(struct pnv_vas_window *window,
struct vas_winctx *winctx)
{
u64 val;
@@ -519,10 +520,10 @@ static int vas_assign_window_id(struct ida *ida)
return winid;
}
-static void vas_window_free(struct vas_window *window)
+static void vas_window_free(struct pnv_vas_window *window)
{
- int winid = window->winid;
struct vas_instance *vinst = window->vinst;
+ int winid = window->vas_win.winid;
unmap_winctx_mmio_bars(window);
@@ -533,10 +534,10 @@ static void vas_window_free(struct vas_window *window)
vas_release_window_id(&vinst->ida, winid);
}
-static struct vas_window *vas_window_alloc(struct vas_instance *vinst)
+static struct pnv_vas_window *vas_window_alloc(struct vas_instance *vinst)
{
int winid;
- struct vas_window *window;
+ struct pnv_vas_window *window;
winid = vas_assign_window_id(&vinst->ida);
if (winid < 0)
@@ -547,7 +548,7 @@ static struct vas_window *vas_window_alloc(struct vas_instance *vinst)
goto out_free;
window->vinst = vinst;
- window->winid = winid;
+ window->vas_win.winid = winid;
if (map_winctx_mmio_bars(window))
goto out_free;
@@ -562,7 +563,7 @@ out_free:
return ERR_PTR(-ENOMEM);
}
-static void put_rx_win(struct vas_window *rxwin)
+static void put_rx_win(struct pnv_vas_window *rxwin)
{
/* Better not be a send window! */
WARN_ON_ONCE(rxwin->tx_win);
@@ -578,10 +579,11 @@ static void put_rx_win(struct vas_window *rxwin)
*
* NOTE: We access ->windows[] table and assume that vinst->mutex is held.
*/
-static struct vas_window *get_user_rxwin(struct vas_instance *vinst, u32 pswid)
+static struct pnv_vas_window *get_user_rxwin(struct vas_instance *vinst,
+ u32 pswid)
{
int vasid, winid;
- struct vas_window *rxwin;
+ struct pnv_vas_window *rxwin;
decode_pswid(pswid, &vasid, &winid);
@@ -590,7 +592,7 @@ static struct vas_window *get_user_rxwin(struct vas_instance *vinst, u32 pswid)
rxwin = vinst->windows[winid];
- if (!rxwin || rxwin->tx_win || rxwin->cop != VAS_COP_TYPE_FTW)
+ if (!rxwin || rxwin->tx_win || rxwin->vas_win.cop != VAS_COP_TYPE_FTW)
return ERR_PTR(-EINVAL);
return rxwin;
@@ -602,10 +604,10 @@ static struct vas_window *get_user_rxwin(struct vas_instance *vinst, u32 pswid)
*
* See also function header of set_vinst_win().
*/
-static struct vas_window *get_vinst_rxwin(struct vas_instance *vinst,
+static struct pnv_vas_window *get_vinst_rxwin(struct vas_instance *vinst,
enum vas_cop_type cop, u32 pswid)
{
- struct vas_window *rxwin;
+ struct pnv_vas_window *rxwin;
mutex_lock(&vinst->mutex);
@@ -638,9 +640,9 @@ static struct vas_window *get_vinst_rxwin(struct vas_instance *vinst,
* window, we also save the window in the ->rxwin[] table.
*/
static void set_vinst_win(struct vas_instance *vinst,
- struct vas_window *window)
+ struct pnv_vas_window *window)
{
- int id = window->winid;
+ int id = window->vas_win.winid;
mutex_lock(&vinst->mutex);
@@ -649,8 +651,8 @@ static void set_vinst_win(struct vas_instance *vinst,
* unless its a user (FTW) window.
*/
if (!window->user_win && !window->tx_win) {
- WARN_ON_ONCE(vinst->rxwin[window->cop]);
- vinst->rxwin[window->cop] = window;
+ WARN_ON_ONCE(vinst->rxwin[window->vas_win.cop]);
+ vinst->rxwin[window->vas_win.cop] = window;
}
WARN_ON_ONCE(vinst->windows[id] != NULL);
@@ -663,16 +665,16 @@ static void set_vinst_win(struct vas_instance *vinst,
* Clear this window from the table(s) of windows for this VAS instance.
* See also function header of set_vinst_win().
*/
-static void clear_vinst_win(struct vas_window *window)
+static void clear_vinst_win(struct pnv_vas_window *window)
{
- int id = window->winid;
+ int id = window->vas_win.winid;
struct vas_instance *vinst = window->vinst;
mutex_lock(&vinst->mutex);
if (!window->user_win && !window->tx_win) {
- WARN_ON_ONCE(!vinst->rxwin[window->cop]);
- vinst->rxwin[window->cop] = NULL;
+ WARN_ON_ONCE(!vinst->rxwin[window->vas_win.cop]);
+ vinst->rxwin[window->vas_win.cop] = NULL;
}
WARN_ON_ONCE(vinst->windows[id] != window);
@@ -681,7 +683,7 @@ static void clear_vinst_win(struct vas_window *window)
mutex_unlock(&vinst->mutex);
}
-static void init_winctx_for_rxwin(struct vas_window *rxwin,
+static void init_winctx_for_rxwin(struct pnv_vas_window *rxwin,
struct vas_rx_win_attr *rxattr,
struct vas_winctx *winctx)
{
@@ -702,7 +704,7 @@ static void init_winctx_for_rxwin(struct vas_window *rxwin,
winctx->rx_fifo = rxattr->rx_fifo;
winctx->rx_fifo_size = rxattr->rx_fifo_size;
- winctx->wcreds_max = rxwin->wcreds_max;
+ winctx->wcreds_max = rxwin->vas_win.wcreds_max;
winctx->pin_win = rxattr->pin_win;
winctx->nx_win = rxattr->nx_win;
@@ -851,7 +853,7 @@ EXPORT_SYMBOL_GPL(vas_init_rx_win_attr);
struct vas_window *vas_rx_win_open(int vasid, enum vas_cop_type cop,
struct vas_rx_win_attr *rxattr)
{
- struct vas_window *rxwin;
+ struct pnv_vas_window *rxwin;
struct vas_winctx winctx;
struct vas_instance *vinst;
@@ -870,21 +872,21 @@ struct vas_window *vas_rx_win_open(int vasid, enum vas_cop_type cop,
rxwin = vas_window_alloc(vinst);
if (IS_ERR(rxwin)) {
pr_devel("Unable to allocate memory for Rx window\n");
- return rxwin;
+ return (struct vas_window *)rxwin;
}
rxwin->tx_win = false;
rxwin->nx_win = rxattr->nx_win;
rxwin->user_win = rxattr->user_win;
- rxwin->cop = cop;
- rxwin->wcreds_max = rxattr->wcreds_max;
+ rxwin->vas_win.cop = cop;
+ rxwin->vas_win.wcreds_max = rxattr->wcreds_max;
init_winctx_for_rxwin(rxwin, rxattr, &winctx);
init_winctx_regs(rxwin, &winctx);
set_vinst_win(vinst, rxwin);
- return rxwin;
+ return &rxwin->vas_win;
}
EXPORT_SYMBOL_GPL(vas_rx_win_open);
@@ -905,7 +907,7 @@ void vas_init_tx_win_attr(struct vas_tx_win_attr *txattr, enum vas_cop_type cop)
}
EXPORT_SYMBOL_GPL(vas_init_tx_win_attr);
-static void init_winctx_for_txwin(struct vas_window *txwin,
+static void init_winctx_for_txwin(struct pnv_vas_window *txwin,
struct vas_tx_win_attr *txattr,
struct vas_winctx *winctx)
{
@@ -926,7 +928,7 @@ static void init_winctx_for_txwin(struct vas_window *txwin,
*/
memset(winctx, 0, sizeof(struct vas_winctx));
- winctx->wcreds_max = txwin->wcreds_max;
+ winctx->wcreds_max = txwin->vas_win.wcreds_max;
winctx->user_win = txattr->user_win;
winctx->nx_win = txwin->rxwin->nx_win;
@@ -946,13 +948,13 @@ static void init_winctx_for_txwin(struct vas_window *txwin,
winctx->lpid = txattr->lpid;
winctx->pidr = txattr->pidr;
- winctx->rx_win_id = txwin->rxwin->winid;
+ winctx->rx_win_id = txwin->rxwin->vas_win.winid;
/*
* IRQ and fault window setup is successful. Set fault window
* for the send window so that ready to handle faults.
*/
if (txwin->vinst->virq)
- winctx->fault_win_id = txwin->vinst->fault_win->winid;
+ winctx->fault_win_id = txwin->vinst->fault_win->vas_win.winid;
winctx->dma_type = VAS_DMA_TYPE_INJECT;
winctx->tc_mode = txattr->tc_mode;
@@ -962,7 +964,8 @@ static void init_winctx_for_txwin(struct vas_window *txwin,
winctx->irq_port = txwin->vinst->irq_port;
winctx->pswid = txattr->pswid ? txattr->pswid :
- encode_pswid(txwin->vinst->vas_id, txwin->winid);
+ encode_pswid(txwin->vinst->vas_id,
+ txwin->vas_win.winid);
}
static bool tx_win_args_valid(enum vas_cop_type cop,
@@ -993,8 +996,8 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop,
struct vas_tx_win_attr *attr)
{
int rc;
- struct vas_window *txwin;
- struct vas_window *rxwin;
+ struct pnv_vas_window *txwin;
+ struct pnv_vas_window *rxwin;
struct vas_winctx winctx;
struct vas_instance *vinst;
@@ -1020,7 +1023,7 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop,
rxwin = get_vinst_rxwin(vinst, cop, attr->pswid);
if (IS_ERR(rxwin)) {
pr_devel("No RxWin for vasid %d, cop %d\n", vasid, cop);
- return rxwin;
+ return (struct vas_window *)rxwin;
}
txwin = vas_window_alloc(vinst);
@@ -1029,12 +1032,12 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop,
goto put_rxwin;
}
- txwin->cop = cop;
+ txwin->vas_win.cop = cop;
txwin->tx_win = 1;
txwin->rxwin = rxwin;
txwin->nx_win = txwin->rxwin->nx_win;
txwin->user_win = attr->user_win;
- txwin->wcreds_max = attr->wcreds_max ?: VAS_WCREDS_DEFAULT;
+ txwin->vas_win.wcreds_max = attr->wcreds_max ?: VAS_WCREDS_DEFAULT;
init_winctx_for_txwin(txwin, attr, &winctx);
@@ -1064,56 +1067,16 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop,
rc = -ENODEV;
goto free_window;
}
-
- /*
- * Window opened by a child thread may not be closed when
- * it exits. So take reference to its pid and release it
- * when the window is free by parent thread.
- * Acquire a reference to the task's pid to make sure
- * pid will not be re-used - needed only for multithread
- * applications.
- */
- txwin->pid = get_task_pid(current, PIDTYPE_PID);
- /*
- * Acquire a reference to the task's mm.
- */
- txwin->mm = get_task_mm(current);
-
- if (!txwin->mm) {
- put_pid(txwin->pid);
- pr_err("VAS: pid(%d): mm_struct is not found\n",
- current->pid);
- rc = -EPERM;
+ rc = get_vas_user_win_ref(&txwin->vas_win.task_ref);
+ if (rc)
goto free_window;
- }
- mmgrab(txwin->mm);
- mmput(txwin->mm);
- mm_context_add_vas_window(txwin->mm);
- /*
- * Process closes window during exit. In the case of
- * multithread application, the child thread can open
- * window and can exit without closing it. Expects parent
- * thread to use and close the window. So do not need
- * to take pid reference for parent thread.
- */
- txwin->tgid = find_get_pid(task_tgid_vnr(current));
- /*
- * Even a process that has no foreign real address mapping can
- * use an unpaired COPY instruction (to no real effect). Issue
- * CP_ABORT to clear any pending COPY and prevent a covert
- * channel.
- *
- * __switch_to() will issue CP_ABORT on future context switches
- * if process / thread has any open VAS window (Use
- * current->mm->context.vas_windows).
- */
- asm volatile(PPC_CP_ABORT);
+ vas_user_win_add_mm_context(&txwin->vas_win.task_ref);
}
set_vinst_win(vinst, txwin);
- return txwin;
+ return &txwin->vas_win;
free_window:
vas_window_free(txwin);
@@ -1132,12 +1095,14 @@ int vas_copy_crb(void *crb, int offset)
EXPORT_SYMBOL_GPL(vas_copy_crb);
#define RMA_LSMP_REPORT_ENABLE PPC_BIT(53)
-int vas_paste_crb(struct vas_window *txwin, int offset, bool re)
+int vas_paste_crb(struct vas_window *vwin, int offset, bool re)
{
+ struct pnv_vas_window *txwin;
int rc;
void *addr;
uint64_t val;
+ txwin = container_of(vwin, struct pnv_vas_window, vas_win);
trace_vas_paste_crb(current, txwin);
/*
@@ -1167,7 +1132,7 @@ int vas_paste_crb(struct vas_window *txwin, int offset, bool re)
else
rc = -EINVAL;
- pr_debug("Txwin #%d: Msg count %llu\n", txwin->winid,
+ pr_debug("Txwin #%d: Msg count %llu\n", txwin->vas_win.winid,
read_hvwc_reg(txwin, VREG(LRFIFO_PUSH)));
return rc;
@@ -1187,7 +1152,7 @@ EXPORT_SYMBOL_GPL(vas_paste_crb);
* user space. (NX-842 driver waits for CSB and Fast thread-wakeup
* doesn't use credit checking).
*/
-static void poll_window_credits(struct vas_window *window)
+static void poll_window_credits(struct pnv_vas_window *window)
{
u64 val;
int creds, mode;
@@ -1217,7 +1182,7 @@ retry:
* and issue CRB Kill to stop all pending requests. Need only
* if there is a bug in NX or fault handling in kernel.
*/
- if (creds < window->wcreds_max) {
+ if (creds < window->vas_win.wcreds_max) {
val = 0;
set_current_state(TASK_UNINTERRUPTIBLE);
schedule_timeout(msecs_to_jiffies(10));
@@ -1228,7 +1193,8 @@ retry:
*/
if (!(count % 1000))
pr_warn_ratelimited("VAS: pid %d stuck. Waiting for credits returned for Window(%d). creds %d, Retries %d\n",
- vas_window_pid(window), window->winid,
+ vas_window_pid(&window->vas_win),
+ window->vas_win.winid,
creds, count);
goto retry;
@@ -1240,7 +1206,7 @@ retry:
* short time to queue a CRB, so window should not be busy for too long.
* Trying 5ms intervals.
*/
-static void poll_window_busy_state(struct vas_window *window)
+static void poll_window_busy_state(struct pnv_vas_window *window)
{
int busy;
u64 val;
@@ -1260,7 +1226,8 @@ retry:
*/
if (!(count % 1000))
pr_warn_ratelimited("VAS: pid %d stuck. Window (ID=%d) is in busy state. Retries %d\n",
- vas_window_pid(window), window->winid, count);
+ vas_window_pid(&window->vas_win),
+ window->vas_win.winid, count);
goto retry;
}
@@ -1282,7 +1249,7 @@ retry:
* casting out becomes necessary we should consider offloading the
* job to a worker thread, so the window close can proceed quickly.
*/
-static void poll_window_castout(struct vas_window *window)
+static void poll_window_castout(struct pnv_vas_window *window)
{
/* stub for now */
}
@@ -1291,7 +1258,7 @@ static void poll_window_castout(struct vas_window *window)
* Unpin and close a window so no new requests are accepted and the
* hardware can evict this window from cache if necessary.
*/
-static void unpin_close_window(struct vas_window *window)
+static void unpin_close_window(struct pnv_vas_window *window)
{
u64 val;
@@ -1313,11 +1280,15 @@ static void unpin_close_window(struct vas_window *window)
*
* Besides the hardware, kernel has some bookkeeping of course.
*/
-int vas_win_close(struct vas_window *window)
+int vas_win_close(struct vas_window *vwin)
{
- if (!window)
+ struct pnv_vas_window *window;
+
+ if (!vwin)
return 0;
+ window = container_of(vwin, struct pnv_vas_window, vas_win);
+
if (!window->tx_win && atomic_read(&window->num_txwins) != 0) {
pr_devel("Attempting to close an active Rx window!\n");
WARN_ON_ONCE(1);
@@ -1339,12 +1310,8 @@ int vas_win_close(struct vas_window *window)
/* if send window, drop reference to matching receive window */
if (window->tx_win) {
if (window->user_win) {
- /* Drop references to pid and mm */
- put_pid(window->pid);
- if (window->mm) {
- mm_context_remove_vas_window(window->mm);
- mmdrop(window->mm);
- }
+ put_vas_user_win_ref(&vwin->task_ref);
+ mm_context_remove_vas_window(vwin->task_ref.mm);
}
put_rx_win(window->rxwin);
}
@@ -1377,7 +1344,7 @@ EXPORT_SYMBOL_GPL(vas_win_close);
* - The kernel with return credit on fault window after reading entry
* from fault FIFO.
*/
-void vas_return_credit(struct vas_window *window, bool tx)
+void vas_return_credit(struct pnv_vas_window *window, bool tx)
{
uint64_t val;
@@ -1391,10 +1358,10 @@ void vas_return_credit(struct vas_window *window, bool tx)
}
}
-struct vas_window *vas_pswid_to_window(struct vas_instance *vinst,
+struct pnv_vas_window *vas_pswid_to_window(struct vas_instance *vinst,
uint32_t pswid)
{
- struct vas_window *window;
+ struct pnv_vas_window *window;
int winid;
if (!pswid) {
@@ -1431,13 +1398,74 @@ struct vas_window *vas_pswid_to_window(struct vas_instance *vinst,
* by NX).
*/
if (!window->tx_win || !window->user_win || !window->nx_win ||
- window->cop == VAS_COP_TYPE_FAULT ||
- window->cop == VAS_COP_TYPE_FTW) {
+ window->vas_win.cop == VAS_COP_TYPE_FAULT ||
+ window->vas_win.cop == VAS_COP_TYPE_FTW) {
pr_err("PSWID decode: id %d, tx %d, user %d, nx %d, cop %d\n",
winid, window->tx_win, window->user_win,
- window->nx_win, window->cop);
+ window->nx_win, window->vas_win.cop);
WARN_ON(1);
}
return window;
}
+
+static struct vas_window *vas_user_win_open(int vas_id, u64 flags,
+ enum vas_cop_type cop_type)
+{
+ struct vas_tx_win_attr txattr = {};
+
+ vas_init_tx_win_attr(&txattr, cop_type);
+
+ txattr.lpid = mfspr(SPRN_LPID);
+ txattr.pidr = mfspr(SPRN_PID);
+ txattr.user_win = true;
+ txattr.rsvd_txbuf_count = false;
+ txattr.pswid = false;
+
+ pr_devel("Pid %d: Opening txwin, PIDR %ld\n", txattr.pidr,
+ mfspr(SPRN_PID));
+
+ return vas_tx_win_open(vas_id, cop_type, &txattr);
+}
+
+static u64 vas_user_win_paste_addr(struct vas_window *txwin)
+{
+ struct pnv_vas_window *win;
+ u64 paste_addr;
+
+ win = container_of(txwin, struct pnv_vas_window, vas_win);
+ vas_win_paste_addr(win, &paste_addr, NULL);
+
+ return paste_addr;
+}
+
+static int vas_user_win_close(struct vas_window *txwin)
+{
+ vas_win_close(txwin);
+
+ return 0;
+}
+
+static const struct vas_user_win_ops vops = {
+ .open_win = vas_user_win_open,
+ .paste_addr = vas_user_win_paste_addr,
+ .close_win = vas_user_win_close,
+};
+
+/*
+ * Supporting only nx-gzip coprocessor type now, but this API code
+ * extended to other coprocessor types later.
+ */
+int vas_register_api_powernv(struct module *mod, enum vas_cop_type cop_type,
+ const char *name)
+{
+
+ return vas_register_coproc_api(mod, cop_type, name, &vops);
+}
+EXPORT_SYMBOL_GPL(vas_register_api_powernv);
+
+void vas_unregister_api_powernv(void)
+{
+ vas_unregister_coproc_api();
+}
+EXPORT_SYMBOL_GPL(vas_unregister_api_powernv);
diff --git a/arch/powerpc/platforms/powernv/vas.h b/arch/powerpc/platforms/powernv/vas.h
index c7db3190baca..8bb08e395de0 100644
--- a/arch/powerpc/platforms/powernv/vas.h
+++ b/arch/powerpc/platforms/powernv/vas.h
@@ -334,11 +334,11 @@ struct vas_instance {
int fifo_in_progress; /* To wake up thread or return IRQ_HANDLED */
spinlock_t fault_lock; /* Protects fifo_in_progress update */
void *fault_fifo;
- struct vas_window *fault_win; /* Fault window */
+ struct pnv_vas_window *fault_win; /* Fault window */
struct mutex mutex;
- struct vas_window *rxwin[VAS_COP_TYPE_MAX];
- struct vas_window *windows[VAS_WINDOWS_PER_CHIP];
+ struct pnv_vas_window *rxwin[VAS_COP_TYPE_MAX];
+ struct pnv_vas_window *windows[VAS_WINDOWS_PER_CHIP];
char *name;
char *dbgname;
@@ -346,32 +346,24 @@ struct vas_instance {
};
/*
- * In-kernel state a VAS window. One per window.
+ * In-kernel state a VAS window on PowerNV. One per window.
*/
-struct vas_window {
+struct pnv_vas_window {
+ struct vas_window vas_win;
/* Fields common to send and receive windows */
struct vas_instance *vinst;
- int winid;
bool tx_win; /* True if send window */
bool nx_win; /* True if NX window */
bool user_win; /* True if user space window */
void *hvwc_map; /* HV window context */
void *uwc_map; /* OS/User window context */
- struct pid *pid; /* Linux process id of owner */
- struct pid *tgid; /* Thread group ID of owner */
- struct mm_struct *mm; /* Linux process mm_struct */
- int wcreds_max; /* Window credits */
-
- char *dbgname;
- struct dentry *dbgdir;
/* Fields applicable only to send windows */
void *paste_kaddr;
char *paste_addr_name;
- struct vas_window *rxwin;
+ struct pnv_vas_window *rxwin;
- /* Feilds applicable only to receive windows */
- enum vas_cop_type cop;
+ /* Fields applicable only to receive windows */
atomic_t num_txwins;
};
@@ -430,32 +422,32 @@ extern struct mutex vas_mutex;
extern struct vas_instance *find_vas_instance(int vasid);
extern void vas_init_dbgdir(void);
extern void vas_instance_init_dbgdir(struct vas_instance *vinst);
-extern void vas_window_init_dbgdir(struct vas_window *win);
-extern void vas_window_free_dbgdir(struct vas_window *win);
+extern void vas_window_init_dbgdir(struct pnv_vas_window *win);
+extern void vas_window_free_dbgdir(struct pnv_vas_window *win);
extern int vas_setup_fault_window(struct vas_instance *vinst);
extern irqreturn_t vas_fault_thread_fn(int irq, void *data);
extern irqreturn_t vas_fault_handler(int irq, void *dev_id);
-extern void vas_return_credit(struct vas_window *window, bool tx);
-extern struct vas_window *vas_pswid_to_window(struct vas_instance *vinst,
+extern void vas_return_credit(struct pnv_vas_window *window, bool tx);
+extern struct pnv_vas_window *vas_pswid_to_window(struct vas_instance *vinst,
uint32_t pswid);
-extern void vas_win_paste_addr(struct vas_window *window, u64 *addr,
- int *len);
+extern void vas_win_paste_addr(struct pnv_vas_window *window, u64 *addr,
+ int *len);
static inline int vas_window_pid(struct vas_window *window)
{
- return pid_vnr(window->pid);
+ return pid_vnr(window->task_ref.pid);
}
-static inline void vas_log_write(struct vas_window *win, char *name,
+static inline void vas_log_write(struct pnv_vas_window *win, char *name,
void *regptr, u64 val)
{
if (val)
pr_debug("%swin #%d: %s reg %p, val 0x%016llx\n",
- win->tx_win ? "Tx" : "Rx", win->winid, name,
- regptr, val);
+ win->tx_win ? "Tx" : "Rx", win->vas_win.winid,
+ name, regptr, val);
}
-static inline void write_uwc_reg(struct vas_window *win, char *name,
+static inline void write_uwc_reg(struct pnv_vas_window *win, char *name,
s32 reg, u64 val)
{
void *regptr;
@@ -466,7 +458,7 @@ static inline void write_uwc_reg(struct vas_window *win, char *name,
out_be64(regptr, val);
}
-static inline void write_hvwc_reg(struct vas_window *win, char *name,
+static inline void write_hvwc_reg(struct pnv_vas_window *win, char *name,
s32 reg, u64 val)
{
void *regptr;
@@ -477,7 +469,7 @@ static inline void write_hvwc_reg(struct vas_window *win, char *name,
out_be64(regptr, val);
}
-static inline u64 read_hvwc_reg(struct vas_window *win,
+static inline u64 read_hvwc_reg(struct pnv_vas_window *win,
char *name __maybe_unused, s32 reg)
{
return in_be64(win->hvwc_map+reg);
diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig
index 4d0535cc7946..a4048b8c8c50 100644
--- a/arch/powerpc/platforms/ps3/Kconfig
+++ b/arch/powerpc/platforms/ps3/Kconfig
@@ -86,6 +86,15 @@ config PS3_SYS_MANAGER
This support is required for PS3 system control. In
general, all users will say Y or M.
+config PS3_VERBOSE_RESULT
+ bool "PS3 Verbose LV1 hypercall results" if PS3_ADVANCED
+ depends on PPC_PS3
+ help
+ Enables more verbose log mesages for LV1 hypercall results.
+
+ If in doubt, say N here and reduce the size of the kernel by a
+ small amount.
+
config PS3_REPOSITORY_WRITE
bool "PS3 Repository write support" if PS3_ADVANCED
depends on PPC_PS3
diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c
index d094321964fb..a81eac35d900 100644
--- a/arch/powerpc/platforms/ps3/mm.c
+++ b/arch/powerpc/platforms/ps3/mm.c
@@ -6,6 +6,7 @@
* Copyright 2006 Sony Corp.
*/
+#include <linux/dma-mapping.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/memblock.h>
@@ -1118,6 +1119,7 @@ int ps3_dma_region_init(struct ps3_system_bus_device *dev,
enum ps3_dma_region_type region_type, void *addr, unsigned long len)
{
unsigned long lpar_addr;
+ int result;
lpar_addr = addr ? ps3_mm_phys_to_lpar(__pa(addr)) : 0;
@@ -1129,6 +1131,16 @@ int ps3_dma_region_init(struct ps3_system_bus_device *dev,
r->offset -= map.r1.offset;
r->len = len ? len : ALIGN(map.total, 1 << r->page_size);
+ dev->core.dma_mask = &r->dma_mask;
+
+ result = dma_set_mask_and_coherent(&dev->core, DMA_BIT_MASK(32));
+
+ if (result < 0) {
+ dev_err(&dev->core, "%s:%d: dma_set_mask_and_coherent failed: %d\n",
+ __func__, __LINE__, result);
+ return result;
+ }
+
switch (dev->dev_type) {
case PS3_DEVICE_TYPE_SB:
r->region_ops = (USE_DYNAMIC_DMA)
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index e9ae5dd03593..3de9145c20bc 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -36,6 +36,7 @@ DEFINE_MUTEX(ps3_gpu_mutex);
EXPORT_SYMBOL_GPL(ps3_gpu_mutex);
static union ps3_firmware_version ps3_firmware_version;
+static char ps3_firmware_version_str[16];
void ps3_get_firmware_version(union ps3_firmware_version *v)
{
@@ -182,6 +183,40 @@ static int ps3_set_dabr(unsigned long dabr, unsigned long dabrx)
return lv1_set_dabr(dabr, dabrx) ? -1 : 0;
}
+static ssize_t ps3_fw_version_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%s", ps3_firmware_version_str);
+}
+
+static int __init ps3_setup_sysfs(void)
+{
+ static struct kobj_attribute attr = __ATTR(fw-version, S_IRUGO,
+ ps3_fw_version_show, NULL);
+ static struct kobject *kobj;
+ int result;
+
+ kobj = kobject_create_and_add("ps3", firmware_kobj);
+
+ if (!kobj) {
+ pr_warn("%s:%d: kobject_create_and_add failed.\n", __func__,
+ __LINE__);
+ return -ENOMEM;
+ }
+
+ result = sysfs_create_file(kobj, &attr.attr);
+
+ if (result) {
+ pr_warn("%s:%d: sysfs_create_file failed.\n", __func__,
+ __LINE__);
+ kobject_put(kobj);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+core_initcall(ps3_setup_sysfs);
+
static void __init ps3_setup_arch(void)
{
u64 tmp;
@@ -190,9 +225,11 @@ static void __init ps3_setup_arch(void)
lv1_get_version_info(&ps3_firmware_version.raw, &tmp);
- printk(KERN_INFO "PS3 firmware version %u.%u.%u\n",
- ps3_firmware_version.major, ps3_firmware_version.minor,
- ps3_firmware_version.rev);
+ snprintf(ps3_firmware_version_str, sizeof(ps3_firmware_version_str),
+ "%u.%u.%u", ps3_firmware_version.major,
+ ps3_firmware_version.minor, ps3_firmware_version.rev);
+
+ printk(KERN_INFO "PS3 firmware version %s\n", ps3_firmware_version_str);
ps3_spu_set_platform();
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index b431f41c6cb5..1a5665875165 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -64,9 +64,10 @@ static int ps3_open_hv_device_sb(struct ps3_system_bus_device *dev)
result = lv1_open_device(dev->bus_id, dev->dev_id, 0);
if (result) {
- pr_debug("%s:%d: lv1_open_device failed: %s\n", __func__,
- __LINE__, ps3_result(result));
- result = -EPERM;
+ pr_warn("%s:%d: lv1_open_device dev=%u.%u(%s) failed: %s\n",
+ __func__, __LINE__, dev->match_id, dev->match_sub_id,
+ dev_name(&dev->core), ps3_result(result));
+ result = -EPERM;
}
done:
@@ -120,7 +121,7 @@ static int ps3_open_hv_device_gpu(struct ps3_system_bus_device *dev)
result = lv1_gpu_open(0);
if (result) {
- pr_debug("%s:%d: lv1_gpu_open failed: %s\n", __func__,
+ pr_warn("%s:%d: lv1_gpu_open failed: %s\n", __func__,
__LINE__, ps3_result(result));
result = -EPERM;
}
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index c8a2b0b05ac0..4cda0ef87be0 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -30,3 +30,4 @@ obj-$(CONFIG_PPC_SVM) += svm.o
obj-$(CONFIG_FA_DUMP) += rtas-fadump.o
obj-$(CONFIG_SUSPEND) += suspend.o
+obj-$(CONFIG_PPC_VAS) += vas.o
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 3ac70790ec7a..b1f01ac0c29e 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -289,8 +289,7 @@ int dlpar_acquire_drc(u32 drc_index)
{
int dr_status, rc;
- rc = rtas_call(rtas_token("get-sensor-state"), 2, 2, &dr_status,
- DR_ENTITY_SENSE, drc_index);
+ rc = rtas_get_sensor(DR_ENTITY_SENSE, drc_index, &dr_status);
if (rc || dr_status != DR_ENTITY_UNUSABLE)
return -1;
@@ -311,8 +310,7 @@ int dlpar_release_drc(u32 drc_index)
{
int dr_status, rc;
- rc = rtas_call(rtas_token("get-sensor-state"), 2, 2, &dr_status,
- DR_ENTITY_SENSE, drc_index);
+ rc = rtas_get_sensor(DR_ENTITY_SENSE, drc_index, &dr_status);
if (rc || dr_status != DR_ENTITY_PRESENT)
return -1;
@@ -333,8 +331,7 @@ int dlpar_unisolate_drc(u32 drc_index)
{
int dr_status, rc;
- rc = rtas_call(rtas_token("get-sensor-state"), 2, 2, &dr_status,
- DR_ENTITY_SENSE, drc_index);
+ rc = rtas_get_sensor(DR_ENTITY_SENSE, drc_index, &dr_status);
if (rc || dr_status != DR_ENTITY_PRESENT)
return -1;
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 8377f1f7c78e..377d852f5a9a 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -348,7 +348,8 @@ static int pseries_remove_mem_node(struct device_node *np)
static bool lmb_is_removable(struct drmem_lmb *lmb)
{
- if (!(lmb->flags & DRCONF_MEM_ASSIGNED))
+ if ((lmb->flags & DRCONF_MEM_RESERVED) ||
+ !(lmb->flags & DRCONF_MEM_ASSIGNED))
return false;
#ifdef CONFIG_FA_DUMP
@@ -401,7 +402,7 @@ static int dlpar_remove_lmb(struct drmem_lmb *lmb)
static int dlpar_memory_remove_by_count(u32 lmbs_to_remove)
{
struct drmem_lmb *lmb;
- int lmbs_removed = 0;
+ int lmbs_reserved = 0;
int lmbs_available = 0;
int rc;
@@ -435,12 +436,12 @@ static int dlpar_memory_remove_by_count(u32 lmbs_to_remove)
*/
drmem_mark_lmb_reserved(lmb);
- lmbs_removed++;
- if (lmbs_removed == lmbs_to_remove)
+ lmbs_reserved++;
+ if (lmbs_reserved == lmbs_to_remove)
break;
}
- if (lmbs_removed != lmbs_to_remove) {
+ if (lmbs_reserved != lmbs_to_remove) {
pr_err("Memory hot-remove failed, adding LMB's back\n");
for_each_drmem_lmb(lmb) {
@@ -453,6 +454,10 @@ static int dlpar_memory_remove_by_count(u32 lmbs_to_remove)
lmb->drc_index);
drmem_remove_lmb_reservation(lmb);
+
+ lmbs_reserved--;
+ if (lmbs_reserved == 0)
+ break;
}
rc = -EINVAL;
@@ -466,6 +471,10 @@ static int dlpar_memory_remove_by_count(u32 lmbs_to_remove)
lmb->base_addr);
drmem_remove_lmb_reservation(lmb);
+
+ lmbs_reserved--;
+ if (lmbs_reserved == 0)
+ break;
}
rc = 0;
}
@@ -508,7 +517,6 @@ static int dlpar_memory_remove_by_index(u32 drc_index)
static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index)
{
struct drmem_lmb *lmb, *start_lmb, *end_lmb;
- int lmbs_available = 0;
int rc;
pr_info("Attempting to hot-remove %u LMB(s) at %x\n",
@@ -521,18 +529,29 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index)
if (rc)
return -EINVAL;
- /* Validate that there are enough LMBs to satisfy the request */
+ /*
+ * Validate that all LMBs in range are not reserved. Note that it
+ * is ok if they are !ASSIGNED since our goal here is to remove the
+ * LMB range, regardless of whether some LMBs were already removed
+ * by any other reason.
+ *
+ * This is a contrast to what is done in remove_by_count() where we
+ * check for both RESERVED and !ASSIGNED (via lmb_is_removable()),
+ * because we want to remove a fixed amount of LMBs in that function.
+ */
for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
- if (lmb->flags & DRCONF_MEM_RESERVED)
- break;
-
- lmbs_available++;
+ if (lmb->flags & DRCONF_MEM_RESERVED) {
+ pr_err("Memory at %llx (drc index %x) is reserved\n",
+ lmb->base_addr, lmb->drc_index);
+ return -EINVAL;
+ }
}
- if (lmbs_available < lmbs_to_remove)
- return -EINVAL;
-
for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
+ /*
+ * dlpar_remove_lmb() will error out if the LMB is already
+ * !ASSIGNED, but this case is a no-op for us.
+ */
if (!(lmb->flags & DRCONF_MEM_ASSIGNED))
continue;
@@ -551,6 +570,13 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index)
if (!drmem_lmb_reserved(lmb))
continue;
+ /*
+ * Setting the isolation state of an UNISOLATED/CONFIGURED
+ * device to UNISOLATE is a no-op, but the hypervisor can
+ * use it as a hint that the LMB removal failed.
+ */
+ dlpar_unisolate_drc(lmb->drc_index);
+
rc = dlpar_add_lmb(lmb);
if (rc)
pr_err("Failed to add LMB, drc index %x\n",
@@ -585,10 +611,6 @@ static inline int pseries_remove_mem_node(struct device_node *np)
{
return 0;
}
-static inline int dlpar_memory_remove(struct pseries_hp_errorlog *hp_elog)
-{
- return -EOPNOTSUPP;
-}
static int dlpar_remove_lmb(struct drmem_lmb *lmb)
{
return -EOPNOTSUPP;
@@ -651,7 +673,7 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add)
{
struct drmem_lmb *lmb;
int lmbs_available = 0;
- int lmbs_added = 0;
+ int lmbs_reserved = 0;
int rc;
pr_info("Attempting to hot-add %d LMB(s)\n", lmbs_to_add);
@@ -661,6 +683,9 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add)
/* Validate that there are enough LMBs to satisfy the request */
for_each_drmem_lmb(lmb) {
+ if (lmb->flags & DRCONF_MEM_RESERVED)
+ continue;
+
if (!(lmb->flags & DRCONF_MEM_ASSIGNED))
lmbs_available++;
@@ -689,13 +714,12 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add)
* requested LMBs cannot be added.
*/
drmem_mark_lmb_reserved(lmb);
-
- lmbs_added++;
- if (lmbs_added == lmbs_to_add)
+ lmbs_reserved++;
+ if (lmbs_reserved == lmbs_to_add)
break;
}
- if (lmbs_added != lmbs_to_add) {
+ if (lmbs_reserved != lmbs_to_add) {
pr_err("Memory hot-add failed, removing any added LMBs\n");
for_each_drmem_lmb(lmb) {
@@ -710,6 +734,10 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add)
dlpar_release_drc(lmb->drc_index);
drmem_remove_lmb_reservation(lmb);
+ lmbs_reserved--;
+
+ if (lmbs_reserved == 0)
+ break;
}
rc = -EINVAL;
} else {
@@ -720,6 +748,10 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add)
pr_debug("Memory at %llx (drc index %x) was hot-added\n",
lmb->base_addr, lmb->drc_index);
drmem_remove_lmb_reservation(lmb);
+ lmbs_reserved--;
+
+ if (lmbs_reserved == 0)
+ break;
}
rc = 0;
}
@@ -764,7 +796,6 @@ static int dlpar_memory_add_by_index(u32 drc_index)
static int dlpar_memory_add_by_ic(u32 lmbs_to_add, u32 drc_index)
{
struct drmem_lmb *lmb, *start_lmb, *end_lmb;
- int lmbs_available = 0;
int rc;
pr_info("Attempting to hot-add %u LMB(s) at index %x\n",
@@ -779,15 +810,14 @@ static int dlpar_memory_add_by_ic(u32 lmbs_to_add, u32 drc_index)
/* Validate that the LMBs in this range are not reserved */
for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
- if (lmb->flags & DRCONF_MEM_RESERVED)
- break;
-
- lmbs_available++;
+ /* Fail immediately if the whole range can't be hot-added */
+ if (lmb->flags & DRCONF_MEM_RESERVED) {
+ pr_err("Memory at %llx (drc index %x) is reserved\n",
+ lmb->base_addr, lmb->drc_index);
+ return -EINVAL;
+ }
}
- if (lmbs_available < lmbs_to_add)
- return -EINVAL;
-
for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
if (lmb->flags & DRCONF_MEM_ASSIGNED)
continue;
diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S
index 8a2b8d64265b..ab9fc6506861 100644
--- a/arch/powerpc/platforms/pseries/hvCall.S
+++ b/arch/powerpc/platforms/pseries/hvCall.S
@@ -108,6 +108,10 @@ _GLOBAL_TOC(plpar_hcall_norets_notrace)
mfcr r0
stw r0,8(r1)
HVSC /* invoke the hypervisor */
+
+ li r4,0
+ stb r4,PACASRR_VALID(r13)
+
lwz r0,8(r1)
mtcrf 0xff,r0
blr /* return r3 = status */
@@ -120,6 +124,9 @@ _GLOBAL_TOC(plpar_hcall_norets)
HCALL_BRANCH(plpar_hcall_norets_trace)
HVSC /* invoke the hypervisor */
+ li r4,0
+ stb r4,PACASRR_VALID(r13)
+
lwz r0,8(r1)
mtcrf 0xff,r0
blr /* return r3 = status */
@@ -129,6 +136,10 @@ plpar_hcall_norets_trace:
HCALL_INST_PRECALL(R4)
HVSC
HCALL_INST_POSTCALL_NORETS
+
+ li r4,0
+ stb r4,PACASRR_VALID(r13)
+
lwz r0,8(r1)
mtcrf 0xff,r0
blr
@@ -159,6 +170,9 @@ _GLOBAL_TOC(plpar_hcall)
std r6, 16(r12)
std r7, 24(r12)
+ li r4,0
+ stb r4,PACASRR_VALID(r13)
+
lwz r0,8(r1)
mtcrf 0xff,r0
@@ -188,6 +202,9 @@ plpar_hcall_trace:
HCALL_INST_POSTCALL(r12)
+ li r4,0
+ stb r4,PACASRR_VALID(r13)
+
lwz r0,8(r1)
mtcrf 0xff,r0
@@ -223,6 +240,9 @@ _GLOBAL(plpar_hcall_raw)
std r6, 16(r12)
std r7, 24(r12)
+ li r4,0
+ stb r4,PACASRR_VALID(r13)
+
lwz r0,8(r1)
mtcrf 0xff,r0
@@ -262,6 +282,9 @@ _GLOBAL_TOC(plpar_hcall9)
std r11,56(r12)
std r0, 64(r12)
+ li r4,0
+ stb r4,PACASRR_VALID(r13)
+
lwz r0,8(r1)
mtcrf 0xff,r0
@@ -300,6 +323,9 @@ plpar_hcall9_trace:
HCALL_INST_POSTCALL(r12)
+ li r4,0
+ stb r4,PACASRR_VALID(r13)
+
lwz r0,8(r1)
mtcrf 0xff,r0
@@ -339,6 +365,9 @@ _GLOBAL(plpar_hcall9_raw)
std r11,56(r12)
std r0, 64(r12)
+ li r4,0
+ stb r4,PACASRR_VALID(r13)
+
lwz r0,8(r1)
mtcrf 0xff,r0
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index ef26fe40efb0..f48e87ac89c9 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -18,6 +18,7 @@
#include <asm/plpar_wrappers.h>
#include <asm/papr_pdsm.h>
#include <asm/mce.h>
+#include <asm/unaligned.h>
#define BIND_ANY_ADDR (~0ul)
@@ -114,6 +115,9 @@ struct papr_scm_priv {
/* Health information for the dimm */
u64 health_bitmap;
+ /* Holds the last known dirty shutdown counter value */
+ u64 dirty_shutdown_counter;
+
/* length of the stat buffer as expected by phyp */
size_t stat_buffer_len;
};
@@ -260,7 +264,7 @@ err_out:
* Query the Dimm performance stats from PHYP and copy them (if returned) to
* provided struct papr_scm_perf_stats instance 'stats' that can hold atleast
* (num_stats + header) bytes.
- * - If buff_stats == NULL the return value is the size in byes of the buffer
+ * - If buff_stats == NULL the return value is the size in bytes of the buffer
* needed to hold all supported performance-statistics.
* - If buff_stats != NULL and num_stats == 0 then we copy all known
* performance-statistics to 'buff_stat' and expect to be large enough to
@@ -310,6 +314,13 @@ static ssize_t drc_pmem_query_stats(struct papr_scm_priv *p,
dev_err(&p->pdev->dev,
"Unknown performance stats, Err:0x%016lX\n", ret[0]);
return -ENOENT;
+ } else if (rc == H_AUTHORITY) {
+ dev_info(&p->pdev->dev,
+ "Permission denied while accessing performance stats");
+ return -EPERM;
+ } else if (rc == H_UNSUPPORTED) {
+ dev_dbg(&p->pdev->dev, "Performance stats unsupported\n");
+ return -EOPNOTSUPP;
} else if (rc != H_SUCCESS) {
dev_err(&p->pdev->dev,
"Failed to query performance stats, Err:%lld\n", rc);
@@ -596,6 +607,16 @@ free_stats:
return rc;
}
+/* Add the dirty-shutdown-counter value to the pdsm */
+static int papr_pdsm_dsc(struct papr_scm_priv *p,
+ union nd_pdsm_payload *payload)
+{
+ payload->health.extension_flags |= PDSM_DIMM_DSC_VALID;
+ payload->health.dimm_dsc = p->dirty_shutdown_counter;
+
+ return sizeof(struct nd_papr_pdsm_health);
+}
+
/* Fetch the DIMM health info and populate it in provided package. */
static int papr_pdsm_health(struct papr_scm_priv *p,
union nd_pdsm_payload *payload)
@@ -639,6 +660,8 @@ static int papr_pdsm_health(struct papr_scm_priv *p,
/* Populate the fuel gauge meter in the payload */
papr_pdsm_fuel_gauge(p, payload);
+ /* Populate the dirty-shutdown-counter field */
+ papr_pdsm_dsc(p, payload);
rc = sizeof(struct nd_papr_pdsm_health);
@@ -900,15 +923,41 @@ static ssize_t flags_show(struct device *dev,
}
DEVICE_ATTR_RO(flags);
+static ssize_t dirty_shutdown_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nvdimm *dimm = to_nvdimm(dev);
+ struct papr_scm_priv *p = nvdimm_provider_data(dimm);
+
+ return sysfs_emit(buf, "%llu\n", p->dirty_shutdown_counter);
+}
+DEVICE_ATTR_RO(dirty_shutdown);
+
+static umode_t papr_nd_attribute_visible(struct kobject *kobj,
+ struct attribute *attr, int n)
+{
+ struct device *dev = kobj_to_dev(kobj);
+ struct nvdimm *nvdimm = to_nvdimm(dev);
+ struct papr_scm_priv *p = nvdimm_provider_data(nvdimm);
+
+ /* For if perf-stats not available remove perf_stats sysfs */
+ if (attr == &dev_attr_perf_stats.attr && p->stat_buffer_len == 0)
+ return 0;
+
+ return attr->mode;
+}
+
/* papr_scm specific dimm attributes */
static struct attribute *papr_nd_attributes[] = {
&dev_attr_flags.attr,
&dev_attr_perf_stats.attr,
+ &dev_attr_dirty_shutdown.attr,
NULL,
};
static struct attribute_group papr_nd_attribute_group = {
.name = "papr",
+ .is_visible = papr_nd_attribute_visible,
.attrs = papr_nd_attributes,
};
@@ -924,7 +973,6 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
struct nd_region_desc ndr_desc;
unsigned long dimm_flags;
int target_nid, online_nid;
- ssize_t stat_size;
p->bus_desc.ndctl = papr_scm_ndctl;
p->bus_desc.module = THIS_MODULE;
@@ -1009,16 +1057,6 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
list_add_tail(&p->region_list, &papr_nd_regions);
mutex_unlock(&papr_ndr_lock);
- /* Try retriving the stat buffer and see if its supported */
- stat_size = drc_pmem_query_stats(p, NULL, 0);
- if (stat_size > 0) {
- p->stat_buffer_len = stat_size;
- dev_dbg(&p->pdev->dev, "Max perf-stat size %lu-bytes\n",
- p->stat_buffer_len);
- } else {
- dev_info(&p->pdev->dev, "Dimm performance stats unavailable\n");
- }
-
return 0;
err: nvdimm_bus_unregister(p->bus);
@@ -1094,8 +1132,10 @@ static int papr_scm_probe(struct platform_device *pdev)
u32 drc_index, metadata_size;
u64 blocks, block_size;
struct papr_scm_priv *p;
+ u8 uuid_raw[UUID_SIZE];
const char *uuid_str;
- u64 uuid[2];
+ ssize_t stat_size;
+ uuid_t uuid;
int rc;
/* check we have all the required DT properties */
@@ -1137,17 +1177,28 @@ static int papr_scm_probe(struct platform_device *pdev)
p->is_volatile = !of_property_read_bool(dn, "ibm,cache-flush-required");
p->hcall_flush_required = of_property_read_bool(dn, "ibm,hcall-flush-required");
+ if (of_property_read_u64(dn, "ibm,persistence-failed-count",
+ &p->dirty_shutdown_counter))
+ p->dirty_shutdown_counter = 0;
+
/* We just need to ensure that set cookies are unique across */
- uuid_parse(uuid_str, (uuid_t *) uuid);
+ uuid_parse(uuid_str, &uuid);
+
/*
- * cookie1 and cookie2 are not really little endian
- * we store a little endian representation of the
- * uuid str so that we can compare this with the label
- * area cookie irrespective of the endian config with which
- * the kernel is built.
+ * The cookie1 and cookie2 are not really little endian.
+ * We store a raw buffer representation of the
+ * uuid string so that we can compare this with the label
+ * area cookie irrespective of the endian configuration
+ * with which the kernel is built.
+ *
+ * Historically we stored the cookie in the below format.
+ * for a uuid string 72511b67-0b3b-42fd-8d1d-5be3cae8bcaa
+ * cookie1 was 0xfd423b0b671b5172
+ * cookie2 was 0xaabce8cae35b1d8d
*/
- p->nd_set.cookie1 = cpu_to_le64(uuid[0]);
- p->nd_set.cookie2 = cpu_to_le64(uuid[1]);
+ export_uuid(uuid_raw, &uuid);
+ p->nd_set.cookie1 = get_unaligned_le64(&uuid_raw[0]);
+ p->nd_set.cookie2 = get_unaligned_le64(&uuid_raw[8]);
/* might be zero */
p->metadata_size = metadata_size;
@@ -1172,6 +1223,14 @@ static int papr_scm_probe(struct platform_device *pdev)
p->res.name = pdev->name;
p->res.flags = IORESOURCE_MEM;
+ /* Try retrieving the stat buffer and see if its supported */
+ stat_size = drc_pmem_query_stats(p, NULL, 0);
+ if (stat_size > 0) {
+ p->stat_buffer_len = stat_size;
+ dev_dbg(&p->pdev->dev, "Max perf-stat size %lu-bytes\n",
+ p->stat_buffer_len);
+ }
+
rc = papr_scm_nvdimm_init(p);
if (rc)
goto err2;
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 9d4ef65da7f3..167f2e1b8d39 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -487,8 +487,8 @@ int pSeries_system_reset_exception(struct pt_regs *regs)
if ((be64_to_cpu(regs->msr) &
(MSR_LE|MSR_RI|MSR_DR|MSR_IR|MSR_ME|MSR_PR|
MSR_ILE|MSR_HV|MSR_SF)) == (MSR_DR|MSR_SF)) {
- regs->nip = be64_to_cpu((__be64)regs->nip);
- regs->msr = 0;
+ regs_set_return_ip(regs, be64_to_cpu((__be64)regs->nip));
+ regs_set_return_msr(regs, 0);
}
#endif
@@ -593,8 +593,6 @@ static int mce_handle_err_virtmode(struct pt_regs *regs,
mce_err.severity = MCE_SEV_SEVERE;
else if (severity == RTAS_SEVERITY_ERROR)
mce_err.severity = MCE_SEV_SEVERE;
- else if (severity == RTAS_SEVERITY_FATAL)
- mce_err.severity = MCE_SEV_FATAL;
else
mce_err.severity = MCE_SEV_FATAL;
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 754e493b7c05..631a0d57b6cd 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -549,6 +549,15 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result)
if (!(result->behaviour & H_CPU_BEHAV_L1D_FLUSH_PR))
security_ftr_clear(SEC_FTR_L1D_FLUSH_PR);
+ if (result->behaviour & H_CPU_BEHAV_NO_L1D_FLUSH_ENTRY)
+ security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY);
+
+ if (result->behaviour & H_CPU_BEHAV_NO_L1D_FLUSH_UACCESS)
+ security_ftr_clear(SEC_FTR_L1D_FLUSH_UACCESS);
+
+ if (result->behaviour & H_CPU_BEHAV_NO_STF_BARRIER)
+ security_ftr_clear(SEC_FTR_STF_BARRIER);
+
if (!(result->behaviour & H_CPU_BEHAV_BNDS_CHK_SPEC_BAR))
security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR);
}
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index c70b4be9f0a5..096629f54576 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -211,7 +211,9 @@ static __init void pSeries_smp_probe(void)
if (!cpu_has_feature(CPU_FTR_SMT))
return;
- if (check_kvm_guest()) {
+ check_kvm_guest();
+
+ if (is_kvm_guest()) {
/*
* KVM emulates doorbells by disabling FSCR[MSGP] so msgsndp
* faults to the hypervisor which then reads the instruction
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
new file mode 100644
index 000000000000..b5c1cf1bc64d
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -0,0 +1,595 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2020-21 IBM Corp.
+ */
+
+#define pr_fmt(fmt) "vas: " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <asm/machdep.h>
+#include <asm/hvcall.h>
+#include <asm/plpar_wrappers.h>
+#include <asm/vas.h>
+#include "vas.h"
+
+#define VAS_INVALID_WIN_ADDRESS 0xFFFFFFFFFFFFFFFFul
+#define VAS_DEFAULT_DOMAIN_ID 0xFFFFFFFFFFFFFFFFul
+/* The hypervisor allows one credit per window right now */
+#define DEF_WIN_CREDS 1
+
+static struct vas_all_caps caps_all;
+static bool copypaste_feat;
+
+static struct vas_caps vascaps[VAS_MAX_FEAT_TYPE];
+static DEFINE_MUTEX(vas_pseries_mutex);
+
+static long hcall_return_busy_check(long rc)
+{
+ /* Check if we are stalled for some time */
+ if (H_IS_LONG_BUSY(rc)) {
+ msleep(get_longbusy_msecs(rc));
+ rc = H_BUSY;
+ } else if (rc == H_BUSY) {
+ cond_resched();
+ }
+
+ return rc;
+}
+
+/*
+ * Allocate VAS window hcall
+ */
+static int h_allocate_vas_window(struct pseries_vas_window *win, u64 *domain,
+ u8 wintype, u16 credits)
+{
+ long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
+ long rc;
+
+ do {
+ rc = plpar_hcall9(H_ALLOCATE_VAS_WINDOW, retbuf, wintype,
+ credits, domain[0], domain[1], domain[2],
+ domain[3], domain[4], domain[5]);
+
+ rc = hcall_return_busy_check(rc);
+ } while (rc == H_BUSY);
+
+ if (rc == H_SUCCESS) {
+ if (win->win_addr == VAS_INVALID_WIN_ADDRESS) {
+ pr_err("H_ALLOCATE_VAS_WINDOW: COPY/PASTE is not supported\n");
+ return -ENOTSUPP;
+ }
+ win->vas_win.winid = retbuf[0];
+ win->win_addr = retbuf[1];
+ win->complete_irq = retbuf[2];
+ win->fault_irq = retbuf[3];
+ return 0;
+ }
+
+ pr_err("H_ALLOCATE_VAS_WINDOW error: %ld, wintype: %u, credits: %u\n",
+ rc, wintype, credits);
+
+ return -EIO;
+}
+
+/*
+ * Deallocate VAS window hcall.
+ */
+static int h_deallocate_vas_window(u64 winid)
+{
+ long rc;
+
+ do {
+ rc = plpar_hcall_norets(H_DEALLOCATE_VAS_WINDOW, winid);
+
+ rc = hcall_return_busy_check(rc);
+ } while (rc == H_BUSY);
+
+ if (rc == H_SUCCESS)
+ return 0;
+
+ pr_err("H_DEALLOCATE_VAS_WINDOW error: %ld, winid: %llu\n",
+ rc, winid);
+ return -EIO;
+}
+
+/*
+ * Modify VAS window.
+ * After the window is opened with allocate window hcall, configure it
+ * with flags and LPAR PID before using.
+ */
+static int h_modify_vas_window(struct pseries_vas_window *win)
+{
+ long rc;
+ u32 lpid = mfspr(SPRN_PID);
+
+ /*
+ * AMR value is not supported in Linux VAS implementation.
+ * The hypervisor ignores it if 0 is passed.
+ */
+ do {
+ rc = plpar_hcall_norets(H_MODIFY_VAS_WINDOW,
+ win->vas_win.winid, lpid, 0,
+ VAS_MOD_WIN_FLAGS, 0);
+
+ rc = hcall_return_busy_check(rc);
+ } while (rc == H_BUSY);
+
+ if (rc == H_SUCCESS)
+ return 0;
+
+ pr_err("H_MODIFY_VAS_WINDOW error: %ld, winid %u lpid %u\n",
+ rc, win->vas_win.winid, lpid);
+ return -EIO;
+}
+
+/*
+ * This hcall is used to determine the capabilities from the hypervisor.
+ * @hcall: H_QUERY_VAS_CAPABILITIES or H_QUERY_NX_CAPABILITIES
+ * @query_type: If 0 is passed, the hypervisor returns the overall
+ * capabilities which provides all feature(s) that are
+ * available. Then query the hypervisor to get the
+ * corresponding capabilities for the specific feature.
+ * Example: H_QUERY_VAS_CAPABILITIES provides VAS GZIP QoS
+ * and VAS GZIP Default capabilities.
+ * H_QUERY_NX_CAPABILITIES provides NX GZIP
+ * capabilities.
+ * @result: Return buffer to save capabilities.
+ */
+int h_query_vas_capabilities(const u64 hcall, u8 query_type, u64 result)
+{
+ long rc;
+
+ rc = plpar_hcall_norets(hcall, query_type, result);
+
+ if (rc == H_SUCCESS)
+ return 0;
+
+ pr_err("HCALL(%llx) error %ld, query_type %u, result buffer 0x%llx\n",
+ hcall, rc, query_type, result);
+ return -EIO;
+}
+EXPORT_SYMBOL_GPL(h_query_vas_capabilities);
+
+/*
+ * hcall to get fault CRB from the hypervisor.
+ */
+static int h_get_nx_fault(u32 winid, u64 buffer)
+{
+ long rc;
+
+ rc = plpar_hcall_norets(H_GET_NX_FAULT, winid, buffer);
+
+ if (rc == H_SUCCESS)
+ return 0;
+
+ pr_err("H_GET_NX_FAULT error: %ld, winid %u, buffer 0x%llx\n",
+ rc, winid, buffer);
+ return -EIO;
+
+}
+
+/*
+ * Handle the fault interrupt.
+ * When the fault interrupt is received for each window, query the
+ * hypervisor to get the fault CRB on the specific fault. Then
+ * process the CRB by updating CSB or send signal if the user space
+ * CSB is invalid.
+ * Note: The hypervisor forwards an interrupt for each fault request.
+ * So one fault CRB to process for each H_GET_NX_FAULT hcall.
+ */
+irqreturn_t pseries_vas_fault_thread_fn(int irq, void *data)
+{
+ struct pseries_vas_window *txwin = data;
+ struct coprocessor_request_block crb;
+ struct vas_user_win_ref *tsk_ref;
+ int rc;
+
+ rc = h_get_nx_fault(txwin->vas_win.winid, (u64)virt_to_phys(&crb));
+ if (!rc) {
+ tsk_ref = &txwin->vas_win.task_ref;
+ vas_dump_crb(&crb);
+ vas_update_csb(&crb, tsk_ref);
+ }
+
+ return IRQ_HANDLED;
+}
+
+/*
+ * Allocate window and setup IRQ mapping.
+ */
+static int allocate_setup_window(struct pseries_vas_window *txwin,
+ u64 *domain, u8 wintype)
+{
+ int rc;
+
+ rc = h_allocate_vas_window(txwin, domain, wintype, DEF_WIN_CREDS);
+ if (rc)
+ return rc;
+ /*
+ * On PowerVM, the hypervisor setup and forwards the fault
+ * interrupt per window. So the IRQ setup and fault handling
+ * will be done for each open window separately.
+ */
+ txwin->fault_virq = irq_create_mapping(NULL, txwin->fault_irq);
+ if (!txwin->fault_virq) {
+ pr_err("Failed irq mapping %d\n", txwin->fault_irq);
+ rc = -EINVAL;
+ goto out_win;
+ }
+
+ txwin->name = kasprintf(GFP_KERNEL, "vas-win-%d",
+ txwin->vas_win.winid);
+ if (!txwin->name) {
+ rc = -ENOMEM;
+ goto out_irq;
+ }
+
+ rc = request_threaded_irq(txwin->fault_virq, NULL,
+ pseries_vas_fault_thread_fn, IRQF_ONESHOT,
+ txwin->name, txwin);
+ if (rc) {
+ pr_err("VAS-Window[%d]: Request IRQ(%u) failed with %d\n",
+ txwin->vas_win.winid, txwin->fault_virq, rc);
+ goto out_free;
+ }
+
+ txwin->vas_win.wcreds_max = DEF_WIN_CREDS;
+
+ return 0;
+out_free:
+ kfree(txwin->name);
+out_irq:
+ irq_dispose_mapping(txwin->fault_virq);
+out_win:
+ h_deallocate_vas_window(txwin->vas_win.winid);
+ return rc;
+}
+
+static inline void free_irq_setup(struct pseries_vas_window *txwin)
+{
+ free_irq(txwin->fault_virq, txwin);
+ kfree(txwin->name);
+ irq_dispose_mapping(txwin->fault_virq);
+}
+
+static struct vas_window *vas_allocate_window(int vas_id, u64 flags,
+ enum vas_cop_type cop_type)
+{
+ long domain[PLPAR_HCALL9_BUFSIZE] = {VAS_DEFAULT_DOMAIN_ID};
+ struct vas_cop_feat_caps *cop_feat_caps;
+ struct vas_caps *caps;
+ struct pseries_vas_window *txwin;
+ int rc;
+
+ txwin = kzalloc(sizeof(*txwin), GFP_KERNEL);
+ if (!txwin)
+ return ERR_PTR(-ENOMEM);
+
+ /*
+ * A VAS window can have many credits which means that many
+ * requests can be issued simultaneously. But the hypervisor
+ * restricts one credit per window.
+ * The hypervisor introduces 2 different types of credits:
+ * Default credit type (Uses normal priority FIFO):
+ * A limited number of credits are assigned to partitions
+ * based on processor entitlement. But these credits may be
+ * over-committed on a system depends on whether the CPUs
+ * are in shared or dedicated modes - that is, more requests
+ * may be issued across the system than NX can service at
+ * once which can result in paste command failure (RMA_busy).
+ * Then the process has to resend requests or fall-back to
+ * SW compression.
+ * Quality of Service (QoS) credit type (Uses high priority FIFO):
+ * To avoid NX HW contention, the system admins can assign
+ * QoS credits for each LPAR so that this partition is
+ * guaranteed access to NX resources. These credits are
+ * assigned to partitions via the HMC.
+ * Refer PAPR for more information.
+ *
+ * Allocate window with QoS credits if user requested. Otherwise
+ * default credits are used.
+ */
+ if (flags & VAS_TX_WIN_FLAG_QOS_CREDIT)
+ caps = &vascaps[VAS_GZIP_QOS_FEAT_TYPE];
+ else
+ caps = &vascaps[VAS_GZIP_DEF_FEAT_TYPE];
+
+ cop_feat_caps = &caps->caps;
+
+ if (atomic_inc_return(&cop_feat_caps->used_lpar_creds) >
+ atomic_read(&cop_feat_caps->target_lpar_creds)) {
+ pr_err("Credits are not available to allocate window\n");
+ rc = -EINVAL;
+ goto out;
+ }
+
+ if (vas_id == -1) {
+ /*
+ * The user space is requesting to allocate a window on
+ * a VAS instance where the process is executing.
+ * On PowerVM, domain values are passed to the hypervisor
+ * to select VAS instance. Useful if the process is
+ * affinity to NUMA node.
+ * The hypervisor selects VAS instance if
+ * VAS_DEFAULT_DOMAIN_ID (-1) is passed for domain values.
+ * The h_allocate_vas_window hcall is defined to take a
+ * domain values as specified by h_home_node_associativity,
+ * So no unpacking needs to be done.
+ */
+ rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, domain,
+ VPHN_FLAG_VCPU, smp_processor_id());
+ if (rc != H_SUCCESS) {
+ pr_err("H_HOME_NODE_ASSOCIATIVITY error: %d\n", rc);
+ goto out;
+ }
+ }
+
+ /*
+ * Allocate / Deallocate window hcalls and setup / free IRQs
+ * have to be protected with mutex.
+ * Open VAS window: Allocate window hcall and setup IRQ
+ * Close VAS window: Deallocate window hcall and free IRQ
+ * The hypervisor waits until all NX requests are
+ * completed before closing the window. So expects OS
+ * to handle NX faults, means IRQ can be freed only
+ * after the deallocate window hcall is returned.
+ * So once the window is closed with deallocate hcall before
+ * the IRQ is freed, it can be assigned to new allocate
+ * hcall with the same fault IRQ by the hypervisor. It can
+ * result in setup IRQ fail for the new window since the
+ * same fault IRQ is not freed by the OS before.
+ */
+ mutex_lock(&vas_pseries_mutex);
+ rc = allocate_setup_window(txwin, (u64 *)&domain[0],
+ cop_feat_caps->win_type);
+ mutex_unlock(&vas_pseries_mutex);
+ if (rc)
+ goto out;
+
+ /*
+ * Modify window and it is ready to use.
+ */
+ rc = h_modify_vas_window(txwin);
+ if (!rc)
+ rc = get_vas_user_win_ref(&txwin->vas_win.task_ref);
+ if (rc)
+ goto out_free;
+
+ vas_user_win_add_mm_context(&txwin->vas_win.task_ref);
+ txwin->win_type = cop_feat_caps->win_type;
+ mutex_lock(&vas_pseries_mutex);
+ list_add(&txwin->win_list, &caps->list);
+ mutex_unlock(&vas_pseries_mutex);
+
+ return &txwin->vas_win;
+
+out_free:
+ /*
+ * Window is not operational. Free IRQ before closing
+ * window so that do not have to hold mutex.
+ */
+ free_irq_setup(txwin);
+ h_deallocate_vas_window(txwin->vas_win.winid);
+out:
+ atomic_dec(&cop_feat_caps->used_lpar_creds);
+ kfree(txwin);
+ return ERR_PTR(rc);
+}
+
+static u64 vas_paste_address(struct vas_window *vwin)
+{
+ struct pseries_vas_window *win;
+
+ win = container_of(vwin, struct pseries_vas_window, vas_win);
+ return win->win_addr;
+}
+
+static int deallocate_free_window(struct pseries_vas_window *win)
+{
+ int rc = 0;
+
+ /*
+ * The hypervisor waits for all requests including faults
+ * are processed before closing the window - Means all
+ * credits have to be returned. In the case of fault
+ * request, a credit is returned after OS issues
+ * H_GET_NX_FAULT hcall.
+ * So free IRQ after executing H_DEALLOCATE_VAS_WINDOW
+ * hcall.
+ */
+ rc = h_deallocate_vas_window(win->vas_win.winid);
+ if (!rc)
+ free_irq_setup(win);
+
+ return rc;
+}
+
+static int vas_deallocate_window(struct vas_window *vwin)
+{
+ struct pseries_vas_window *win;
+ struct vas_cop_feat_caps *caps;
+ int rc = 0;
+
+ if (!vwin)
+ return -EINVAL;
+
+ win = container_of(vwin, struct pseries_vas_window, vas_win);
+
+ /* Should not happen */
+ if (win->win_type >= VAS_MAX_FEAT_TYPE) {
+ pr_err("Window (%u): Invalid window type %u\n",
+ vwin->winid, win->win_type);
+ return -EINVAL;
+ }
+
+ caps = &vascaps[win->win_type].caps;
+ mutex_lock(&vas_pseries_mutex);
+ rc = deallocate_free_window(win);
+ if (rc) {
+ mutex_unlock(&vas_pseries_mutex);
+ return rc;
+ }
+
+ list_del(&win->win_list);
+ atomic_dec(&caps->used_lpar_creds);
+ mutex_unlock(&vas_pseries_mutex);
+
+ put_vas_user_win_ref(&vwin->task_ref);
+ mm_context_remove_vas_window(vwin->task_ref.mm);
+
+ kfree(win);
+ return 0;
+}
+
+static const struct vas_user_win_ops vops_pseries = {
+ .open_win = vas_allocate_window, /* Open and configure window */
+ .paste_addr = vas_paste_address, /* To do copy/paste */
+ .close_win = vas_deallocate_window, /* Close window */
+};
+
+/*
+ * Supporting only nx-gzip coprocessor type now, but this API code
+ * extended to other coprocessor types later.
+ */
+int vas_register_api_pseries(struct module *mod, enum vas_cop_type cop_type,
+ const char *name)
+{
+ int rc;
+
+ if (!copypaste_feat)
+ return -ENOTSUPP;
+
+ rc = vas_register_coproc_api(mod, cop_type, name, &vops_pseries);
+
+ return rc;
+}
+EXPORT_SYMBOL_GPL(vas_register_api_pseries);
+
+void vas_unregister_api_pseries(void)
+{
+ vas_unregister_coproc_api();
+}
+EXPORT_SYMBOL_GPL(vas_unregister_api_pseries);
+
+/*
+ * Get the specific capabilities based on the feature type.
+ * Right now supports GZIP default and GZIP QoS capabilities.
+ */
+static int get_vas_capabilities(u8 feat, enum vas_cop_feat_type type,
+ struct hv_vas_cop_feat_caps *hv_caps)
+{
+ struct vas_cop_feat_caps *caps;
+ struct vas_caps *vcaps;
+ int rc = 0;
+
+ vcaps = &vascaps[type];
+ memset(vcaps, 0, sizeof(*vcaps));
+ INIT_LIST_HEAD(&vcaps->list);
+
+ caps = &vcaps->caps;
+
+ rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, feat,
+ (u64)virt_to_phys(hv_caps));
+ if (rc)
+ return rc;
+
+ caps->user_mode = hv_caps->user_mode;
+ if (!(caps->user_mode & VAS_COPY_PASTE_USER_MODE)) {
+ pr_err("User space COPY/PASTE is not supported\n");
+ return -ENOTSUPP;
+ }
+
+ caps->descriptor = be64_to_cpu(hv_caps->descriptor);
+ caps->win_type = hv_caps->win_type;
+ if (caps->win_type >= VAS_MAX_FEAT_TYPE) {
+ pr_err("Unsupported window type %u\n", caps->win_type);
+ return -EINVAL;
+ }
+ caps->max_lpar_creds = be16_to_cpu(hv_caps->max_lpar_creds);
+ caps->max_win_creds = be16_to_cpu(hv_caps->max_win_creds);
+ atomic_set(&caps->target_lpar_creds,
+ be16_to_cpu(hv_caps->target_lpar_creds));
+ if (feat == VAS_GZIP_DEF_FEAT) {
+ caps->def_lpar_creds = be16_to_cpu(hv_caps->def_lpar_creds);
+
+ if (caps->max_win_creds < DEF_WIN_CREDS) {
+ pr_err("Window creds(%u) > max allowed window creds(%u)\n",
+ DEF_WIN_CREDS, caps->max_win_creds);
+ return -EINVAL;
+ }
+ }
+
+ copypaste_feat = true;
+
+ return 0;
+}
+
+static int __init pseries_vas_init(void)
+{
+ struct hv_vas_cop_feat_caps *hv_cop_caps;
+ struct hv_vas_all_caps *hv_caps;
+ int rc;
+
+ /*
+ * Linux supports user space COPY/PASTE only with Radix
+ */
+ if (!radix_enabled()) {
+ pr_err("API is supported only with radix page tables\n");
+ return -ENOTSUPP;
+ }
+
+ hv_caps = kmalloc(sizeof(*hv_caps), GFP_KERNEL);
+ if (!hv_caps)
+ return -ENOMEM;
+ /*
+ * Get VAS overall capabilities by passing 0 to feature type.
+ */
+ rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, 0,
+ (u64)virt_to_phys(hv_caps));
+ if (rc)
+ goto out;
+
+ caps_all.descriptor = be64_to_cpu(hv_caps->descriptor);
+ caps_all.feat_type = be64_to_cpu(hv_caps->feat_type);
+
+ hv_cop_caps = kmalloc(sizeof(*hv_cop_caps), GFP_KERNEL);
+ if (!hv_cop_caps) {
+ rc = -ENOMEM;
+ goto out;
+ }
+ /*
+ * QOS capabilities available
+ */
+ if (caps_all.feat_type & VAS_GZIP_QOS_FEAT_BIT) {
+ rc = get_vas_capabilities(VAS_GZIP_QOS_FEAT,
+ VAS_GZIP_QOS_FEAT_TYPE, hv_cop_caps);
+
+ if (rc)
+ goto out_cop;
+ }
+ /*
+ * Default capabilities available
+ */
+ if (caps_all.feat_type & VAS_GZIP_DEF_FEAT_BIT) {
+ rc = get_vas_capabilities(VAS_GZIP_DEF_FEAT,
+ VAS_GZIP_DEF_FEAT_TYPE, hv_cop_caps);
+ if (rc)
+ goto out_cop;
+ }
+
+ pr_info("GZIP feature is available\n");
+
+out_cop:
+ kfree(hv_cop_caps);
+out:
+ kfree(hv_caps);
+ return rc;
+}
+machine_device_initcall(pseries, pseries_vas_init);
diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h
new file mode 100644
index 000000000000..4ecb3fcabd10
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/vas.h
@@ -0,0 +1,125 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright 2020-21 IBM Corp.
+ */
+
+#ifndef _VAS_H
+#define _VAS_H
+#include <asm/vas.h>
+#include <linux/mutex.h>
+#include <linux/stringify.h>
+
+/*
+ * VAS window modify flags
+ */
+#define VAS_MOD_WIN_CLOSE PPC_BIT(0)
+#define VAS_MOD_WIN_JOBS_KILL PPC_BIT(1)
+#define VAS_MOD_WIN_DR PPC_BIT(3)
+#define VAS_MOD_WIN_PR PPC_BIT(4)
+#define VAS_MOD_WIN_SF PPC_BIT(5)
+#define VAS_MOD_WIN_TA PPC_BIT(6)
+#define VAS_MOD_WIN_FLAGS (VAS_MOD_WIN_JOBS_KILL | VAS_MOD_WIN_DR | \
+ VAS_MOD_WIN_PR | VAS_MOD_WIN_SF)
+
+#define VAS_WIN_ACTIVE 0x0
+#define VAS_WIN_CLOSED 0x1
+#define VAS_WIN_INACTIVE 0x2 /* Inactive due to HW failure */
+/* Process of being modified, deallocated, or quiesced */
+#define VAS_WIN_MOD_IN_PROCESS 0x3
+
+#define VAS_COPY_PASTE_USER_MODE 0x00000001
+#define VAS_COP_OP_USER_MODE 0x00000010
+
+/*
+ * Co-processor feature - GZIP QoS windows or GZIP default windows
+ */
+enum vas_cop_feat_type {
+ VAS_GZIP_QOS_FEAT_TYPE,
+ VAS_GZIP_DEF_FEAT_TYPE,
+ VAS_MAX_FEAT_TYPE,
+};
+
+/*
+ * Use to get feature specific capabilities from the
+ * hypervisor.
+ */
+struct hv_vas_cop_feat_caps {
+ __be64 descriptor;
+ u8 win_type; /* Default or QoS type */
+ u8 user_mode;
+ __be16 max_lpar_creds;
+ __be16 max_win_creds;
+ union {
+ __be16 reserved;
+ __be16 def_lpar_creds; /* Used for default capabilities */
+ };
+ __be16 target_lpar_creds;
+} __packed __aligned(0x1000);
+
+/*
+ * Feature specific (QoS or default) capabilities.
+ */
+struct vas_cop_feat_caps {
+ u64 descriptor;
+ u8 win_type; /* Default or QoS type */
+ u8 user_mode; /* User mode copy/paste or COP HCALL */
+ u16 max_lpar_creds; /* Max credits available in LPAR */
+ /* Max credits can be assigned per window */
+ u16 max_win_creds;
+ union {
+ u16 reserved; /* Used for QoS credit type */
+ u16 def_lpar_creds; /* Used for default credit type */
+ };
+ /* Total LPAR available credits. Can be different from max LPAR */
+ /* credits due to DLPAR operation */
+ atomic_t target_lpar_creds;
+ atomic_t used_lpar_creds; /* Used credits so far */
+ u16 avail_lpar_creds; /* Remaining available credits */
+};
+
+/*
+ * Feature (QoS or Default) specific to store capabilities and
+ * the list of open windows.
+ */
+struct vas_caps {
+ struct vas_cop_feat_caps caps;
+ struct list_head list; /* List of open windows */
+};
+
+/*
+ * To get window information from the hypervisor.
+ */
+struct hv_vas_win_lpar {
+ __be16 version;
+ u8 win_type;
+ u8 status;
+ __be16 credits; /* No of credits assigned to this window */
+ __be16 reserved;
+ __be32 pid; /* LPAR Process ID */
+ __be32 tid; /* LPAR Thread ID */
+ __be64 win_addr; /* Paste address */
+ __be32 interrupt; /* Interrupt when NX request completes */
+ __be32 fault; /* Interrupt when NX sees fault */
+ /* Associativity Domain Identifiers as returned in */
+ /* H_HOME_NODE_ASSOCIATIVITY */
+ __be64 domain[6];
+ __be64 win_util; /* Number of bytes processed */
+} __packed __aligned(0x1000);
+
+struct pseries_vas_window {
+ struct vas_window vas_win;
+ u64 win_addr; /* Physical paste address */
+ u8 win_type; /* QoS or Default window */
+ u32 complete_irq; /* Completion interrupt */
+ u32 fault_irq; /* Fault interrupt */
+ u64 domain[6]; /* Associativity domain Ids */
+ /* this window is allocated */
+ u64 util;
+
+ /* List of windows opened which is used for LPM */
+ struct list_head win_list;
+ u64 flags;
+ char *name;
+ int fault_virq;
+};
+#endif /* _VAS_H */