Merge tag 'powerpc-4.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights include:

   - Support for the kexec_file_load() syscall, which is a prereq for
     secure and trusted boot.

   - Prevent kernel execution of userspace on P9 Radix (similar to
     SMEP/PXN).

   - Sort the exception tables at build time, to save time at boot, and
     store them as relative offsets to save space in the kernel image &
     memory.

   - Allow building the kernel with thin archives, which should allow us
     to build an allyesconfig once some other fixes land.

   - Build fixes to allow us to correctly rebuild when changing the
     kernel endian from big to little or vice versa.

   - Plumbing so that we can avoid doing a full mm TLB flush on P9
     Radix.

   - Initial stack protector support (-fstack-protector).

   - Support for dumping the radix (aka. Linux) and hash page tables via
     debugfs.

   - Fix an oops in cxl coredump generation when cxl_get_fd() is used.

   - Freescale updates from Scott: "Highlights include 8xx hugepage
     support, qbman fixes/cleanup, device tree updates, and some misc
     cleanup."

   - Many and varied fixes and minor enhancements as always.

  Thanks to:
    Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V, Anshuman
    Khandual, Anton Blanchard, Balbir Singh, Bartlomiej Zolnierkiewicz,
    Christophe Jaillet, Christophe Leroy, Denis Kirjanov, Elimar
    Riesebieter, Frederic Barrat, Gautham R. Shenoy, Geliang Tang, Geoff
    Levand, Jack Miller, Johan Hovold, Lars-Peter Clausen, Libin,
    Madhavan Srinivasan, Michael Neuling, Nathan Fontenot, Naveen N.
    Rao, Nicholas Piggin, Pan Xinhui, Peter Senna Tschudin, Rashmica
    Gupta, Rui Teng, Russell Currey, Scott Wood, Simon Guo, Suraj
    Jitindar Singh, Thiago Jung Bauermann, Tobias Klauser, Vaibhav Jain"

[ And thanks to Michael, who took time off from a new baby to get this
  pull request done.   - Linus ]

* tag 'powerpc-4.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (174 commits)
  powerpc/fsl/dts: add FMan node for t1042d4rdb
  powerpc/fsl/dts: add sg_2500_aqr105_phy4 alias on t1024rdb
  powerpc/fsl/dts: add QMan and BMan nodes on t1024
  powerpc/fsl/dts: add QMan and BMan nodes on t1023
  soc/fsl/qman: test: use DEFINE_SPINLOCK()
  powerpc/fsl-lbc: use DEFINE_SPINLOCK()
  powerpc/8xx: Implement support of hugepages
  powerpc: get hugetlbpage handling more generic
  powerpc: port 64 bits pgtable_cache to 32 bits
  powerpc/boot: Request no dynamic linker for boot wrapper
  soc/fsl/bman: Use resource_size instead of computation
  soc/fsl/qe: use builtin_platform_driver
  powerpc/fsl_pmc: use builtin_platform_driver
  powerpc/83xx/suspend: use builtin_platform_driver
  powerpc/ftrace: Fix the comments for ftrace_modify_code
  powerpc/perf: macros for power9 format encoding
  powerpc/perf: power9 raw event format encoding
  powerpc/perf: update attribute_group data structure
  powerpc/perf: factor out the event format field
  powerpc/mm/iommu, vfio/spapr: Put pages on VFIO container shutdown
  ...

10 files changed, 160 insertions, 49 deletions

diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 2e5233b60971..1b35e33d2434 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -9,18 +9,119 @@
 
 #include <linux/pci.h>
 #include <linux/slab.h>
-#include <linux/anon_inodes.h>
 #include <linux/file.h>
 #include <misc/cxl.h>
-#include <linux/fs.h>
 #include <asm/pnv-pci.h>
 #include <linux/msi.h>
+#include <linux/module.h>
+#include <linux/mount.h>
 
 #include "cxl.h"
 
+/*
+ * Since we want to track memory mappings to be able to force-unmap
+ * when the AFU is no longer reachable, we need an inode. For devices
+ * opened through the cxl user API, this is not a problem, but a
+ * userland process can also get a cxl fd through the cxl_get_fd()
+ * API, which is used by the cxlflash driver.
+ *
+ * Therefore we implement our own simple pseudo-filesystem and inode
+ * allocator. We don't use the anonymous inode, as we need the
+ * meta-data associated with it (address_space) and it is shared by
+ * other drivers/processes, so it could lead to cxl unmapping VMAs
+ * from random processes.
+ */
+
+#define CXL_PSEUDO_FS_MAGIC	0x1697697f
+
+static int cxl_fs_cnt;
+static struct vfsmount *cxl_vfs_mount;
+
+static const struct dentry_operations cxl_fs_dops = {
+	.d_dname	= simple_dname,
+};
+
+static struct dentry *cxl_fs_mount(struct file_system_type *fs_type, int flags,
+				const char *dev_name, void *data)
+{
+	return mount_pseudo(fs_type, "cxl:", NULL, &cxl_fs_dops,
+			CXL_PSEUDO_FS_MAGIC);
+}
+
+static struct file_system_type cxl_fs_type = {
+	.name		= "cxl",
+	.owner		= THIS_MODULE,
+	.mount		= cxl_fs_mount,
+	.kill_sb	= kill_anon_super,
+};
+
+
+void cxl_release_mapping(struct cxl_context *ctx)
+{
+	if (ctx->kernelapi && ctx->mapping)
+		simple_release_fs(&cxl_vfs_mount, &cxl_fs_cnt);
+}
+
+static struct file *cxl_getfile(const char *name,
+				const struct file_operations *fops,
+				void *priv, int flags)
+{
+	struct qstr this;
+	struct path path;
+	struct file *file;
+	struct inode *inode = NULL;
+	int rc;
+
+	/* strongly inspired by anon_inode_getfile() */
+
+	if (fops->owner && !try_module_get(fops->owner))
+		return ERR_PTR(-ENOENT);
+
+	rc = simple_pin_fs(&cxl_fs_type, &cxl_vfs_mount, &cxl_fs_cnt);
+	if (rc < 0) {
+		pr_err("Cannot mount cxl pseudo filesystem: %d\n", rc);
+		file = ERR_PTR(rc);
+		goto err_module;
+	}
+
+	inode = alloc_anon_inode(cxl_vfs_mount->mnt_sb);
+	if (IS_ERR(inode)) {
+		file = ERR_CAST(inode);
+		goto err_fs;
+	}
+
+	file = ERR_PTR(-ENOMEM);
+	this.name = name;
+	this.len = strlen(name);
+	this.hash = 0;
+	path.dentry = d_alloc_pseudo(cxl_vfs_mount->mnt_sb, &this);
+	if (!path.dentry)
+		goto err_inode;
+
+	path.mnt = mntget(cxl_vfs_mount);
+	d_instantiate(path.dentry, inode);
+
+	file = alloc_file(&path, OPEN_FMODE(flags), fops);
+	if (IS_ERR(file))
+		goto err_dput;
+	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
+	file->private_data = priv;
+
+	return file;
+
+err_dput:
+	path_put(&path);
+err_inode:
+	iput(inode);
+err_fs:
+	simple_release_fs(&cxl_vfs_mount, &cxl_fs_cnt);
+err_module:
+	module_put(fops->owner);
+	return file;
+}
+
 struct cxl_context *cxl_dev_context_init(struct pci_dev *dev)
 {
-	struct address_space *mapping;
 	struct cxl_afu *afu;
 	struct cxl_context  *ctx;
 	int rc;
@@ -30,38 +131,20 @@ struct cxl_context *cxl_dev_context_init(struct pci_dev *dev)
 		return ERR_CAST(afu);
 
 	ctx = cxl_context_alloc();
-	if (IS_ERR(ctx)) {
-		rc = PTR_ERR(ctx);
-		goto err_dev;
-	}
+	if (!ctx)
+		return ERR_PTR(-ENOMEM);
 
 	ctx->kernelapi = true;
 
-	/*
-	 * Make our own address space since we won't have one from the
-	 * filesystem like the user api has, and even if we do associate a file
-	 * with this context we don't want to use the global anonymous inode's
-	 * address space as that can invalidate unrelated users:
-	 */
-	mapping = kmalloc(sizeof(struct address_space), GFP_KERNEL);
-	if (!mapping) {
-		rc = -ENOMEM;
-		goto err_ctx;
-	}
-	address_space_init_once(mapping);
-
 	/* Make it a slave context.  We can promote it later? */
-	rc = cxl_context_init(ctx, afu, false, mapping);
+	rc = cxl_context_init(ctx, afu, false);
 	if (rc)
-		goto err_mapping;
+		goto err_ctx;
 
 	return ctx;
 
-err_mapping:
-	kfree(mapping);
 err_ctx:
 	kfree(ctx);
-err_dev:
 	return ERR_PTR(rc);
 }
 EXPORT_SYMBOL_GPL(cxl_dev_context_init);
@@ -340,6 +423,11 @@ struct file *cxl_get_fd(struct cxl_context *ctx, struct file_operations *fops,
 {
 	struct file *file;
 	int rc, flags, fdtmp;
+	char *name = NULL;
+
+	/* only allow one per context */
+	if (ctx->mapping)
+		return ERR_PTR(-EEXIST);
 
 	flags = O_RDWR | O_CLOEXEC;
 
@@ -363,12 +451,13 @@ struct file *cxl_get_fd(struct cxl_context *ctx, struct file_operations *fops,
 	} else /* use default ops */
 		fops = (struct file_operations *)&afu_fops;
 
-	file = anon_inode_getfile("cxl", fops, ctx, flags);
+	name = kasprintf(GFP_KERNEL, "cxl:%d", ctx->pe);
+	file = cxl_getfile(name, fops, ctx, flags);
+	kfree(name);
 	if (IS_ERR(file))
 		goto err_fd;
 
-	file->f_mapping = ctx->mapping;
-
+	cxl_context_set_mapping(ctx, file->f_mapping);
 	*fd = fdtmp;
 	return file;
 
@@ -541,7 +630,7 @@ int _cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 
 		if (remaining > 0) {
 			new_ctx = cxl_dev_context_init(pdev);
-			if (!new_ctx) {
+			if (IS_ERR(new_ctx)) {
 				pr_warn("%s: Failed to allocate enough contexts for MSIs\n", pci_name(pdev));
 				return -ENOSPC;
 			}
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index 5d36dcc7f47e..3907387b6d15 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -34,8 +34,7 @@ struct cxl_context *cxl_context_alloc(void)
 /*
  * Initialises a CXL context.
  */
-int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
-		     struct address_space *mapping)
+int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master)
 {
 	int i;
 
@@ -44,7 +43,7 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
 	ctx->master = master;
 	ctx->pid = ctx->glpid = NULL; /* Set in start work ioctl */
 	mutex_init(&ctx->mapping_lock);
-	ctx->mapping = mapping;
+	ctx->mapping = NULL;
 
 	/*
 	 * Allocate the segment table before we put it in the IDR so that we
@@ -114,6 +113,14 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
 	return 0;
 }
 
+void cxl_context_set_mapping(struct cxl_context *ctx,
+			struct address_space *mapping)
+{
+	mutex_lock(&ctx->mapping_lock);
+	ctx->mapping = mapping;
+	mutex_unlock(&ctx->mapping_lock);
+}
+
 static int cxl_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct cxl_context *ctx = vma->vm_file->private_data;
@@ -299,8 +306,6 @@ static void reclaim_ctx(struct rcu_head *rcu)
 	if (ctx->ff_page)
 		__free_page(ctx->ff_page);
 	ctx->sstp = NULL;
-	if (ctx->kernelapi)
-		kfree(ctx->mapping);
 
 	kfree(ctx->irq_bitmap);
 
@@ -312,6 +317,8 @@ static void reclaim_ctx(struct rcu_head *rcu)
 
 void cxl_context_free(struct cxl_context *ctx)
 {
+	if (ctx->kernelapi && ctx->mapping)
+		cxl_release_mapping(ctx);
 	mutex_lock(&ctx->afu->contexts_lock);
 	idr_remove(&ctx->afu->contexts_idr, ctx->pe);
 	mutex_unlock(&ctx->afu->contexts_lock);
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index a144073593fa..b24d76723fb0 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -817,8 +817,9 @@ void cxl_dump_debug_buffer(void *addr, size_t size);
 void init_cxl_native(void);
 
 struct cxl_context *cxl_context_alloc(void);
-int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
-		     struct address_space *mapping);
+int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master);
+void cxl_context_set_mapping(struct cxl_context *ctx,
+			struct address_space *mapping);
 void cxl_context_free(struct cxl_context *ctx);
 int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma);
 unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq,
@@ -877,6 +878,7 @@ void cxl_native_err_irq_dump_regs(struct cxl *adapter);
 void cxl_stop_trace(struct cxl *cxl);
 int cxl_pci_vphb_add(struct cxl_afu *afu);
 void cxl_pci_vphb_remove(struct cxl_afu *afu);
+void cxl_release_mapping(struct cxl_context *ctx);
 
 extern struct pci_driver cxl_pci_driver;
 extern struct platform_driver cxl_of_driver;
diff --git a/drivers/misc/cxl/debugfs.c b/drivers/misc/cxl/debugfs.c
index ec7b8a017439..9c06ac8fa5ac 100644
--- a/drivers/misc/cxl/debugfs.c
+++ b/drivers/misc/cxl/debugfs.c
@@ -43,12 +43,14 @@ static int debugfs_io_u64_set(void *data, u64 val)
 	out_be64((u64 __iomem *)data, val);
 	return 0;
 }
-DEFINE_SIMPLE_ATTRIBUTE(fops_io_x64, debugfs_io_u64_get, debugfs_io_u64_set, "0x%016llx\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_io_x64, debugfs_io_u64_get, debugfs_io_u64_set,
+			 "0x%016llx\n");
 
 static struct dentry *debugfs_create_io_x64(const char *name, umode_t mode,
 					    struct dentry *parent, u64 __iomem *value)
 {
-	return debugfs_create_file(name, mode, parent, (void __force *)value, &fops_io_x64);
+	return debugfs_create_file_unsafe(name, mode, parent,
+					  (void __force *)value, &fops_io_x64);
 }
 
 void cxl_debugfs_add_adapter_psl_regs(struct cxl *adapter, struct dentry *dir)
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index 77080cc5fa0a..859959f19f10 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -86,9 +86,12 @@ static int __afu_open(struct inode *inode, struct file *file, bool master)
 		goto err_put_afu;
 	}
 
-	if ((rc = cxl_context_init(ctx, afu, master, inode->i_mapping)))
+	rc = cxl_context_init(ctx, afu, master);
+	if (rc)
 		goto err_put_afu;
 
+	cxl_context_set_mapping(ctx, inode->i_mapping);
+
 	pr_devel("afu_open pe: %i\n", ctx->pe);
 	file->private_data = ctx;
 	cxl_ctx_get();
diff --git a/drivers/misc/cxl/guest.c b/drivers/misc/cxl/guest.c
index 3e102cd6ed91..e04bc4ddfd74 100644
--- a/drivers/misc/cxl/guest.c
+++ b/drivers/misc/cxl/guest.c
@@ -887,7 +887,7 @@ static void afu_handle_errstate(struct work_struct *work)
 	    afu_guest->previous_state == H_STATE_PERM_UNAVAILABLE)
 		return;
 
-	if (afu_guest->handle_err == true)
+	if (afu_guest->handle_err)
 		schedule_delayed_work(&afu_guest->work_err,
 				      msecs_to_jiffies(3000));
 }
diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c
index dec60f58a767..1a402bbed687 100644
--- a/drivers/misc/cxl/irq.c
+++ b/drivers/misc/cxl/irq.c
@@ -104,7 +104,7 @@ irqreturn_t cxl_irq(int irq, struct cxl_context *ctx, struct cxl_irq_info *irq_i
 		} else {
 			spin_lock(&ctx->lock);
 			ctx->afu_err = irq_info->afu_err;
-			ctx->pending_afu_err = 1;
+			ctx->pending_afu_err = true;
 			spin_unlock(&ctx->lock);
 
 			wake_up_all(&ctx->wq);
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index a217a74ccc98..09505f432eda 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -10,7 +10,6 @@
 #include <linux/spinlock.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
 #include <linux/mutex.h>
 #include <linux/mm.h>
 #include <linux/uaccess.h>
@@ -54,7 +53,7 @@ static int afu_control(struct cxl_afu *afu, u64 command, u64 clear,
 				     AFU_Cntl | command);
 		cpu_relax();
 		AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
-	};
+	}
 
 	if (AFU_Cntl & CXL_AFU_Cntl_An_RA) {
 		/*
@@ -167,7 +166,7 @@ int cxl_psl_purge(struct cxl_afu *afu)
 			cpu_relax();
 		}
 		PSL_CNTL = cxl_p1n_read(afu, CXL_PSL_SCNTL_An);
-	};
+	}
 	end = local_clock();
 	pr_devel("PSL purged in %lld ns\n", end - start);
 
@@ -931,9 +930,18 @@ static irqreturn_t native_irq_multiplexed(int irq, void *data)
 	struct cxl_afu *afu = data;
 	struct cxl_context *ctx;
 	struct cxl_irq_info irq_info;
-	int ph = cxl_p2n_read(afu, CXL_PSL_PEHandle_An) & 0xffff;
-	int ret;
-
+	u64 phreg = cxl_p2n_read(afu, CXL_PSL_PEHandle_An);
+	int ph, ret;
+
+	/* check if eeh kicked in while the interrupt was in flight */
+	if (unlikely(phreg == ~0ULL)) {
+		dev_warn(&afu->dev,
+			 "Ignoring slice interrupt(%d) due to fenced card",
+			 irq);
+		return IRQ_HANDLED;
+	}
+	/* Mask the pe-handle from register value */
+	ph = phreg & 0xffff;
 	if ((ret = native_get_irq_info(afu, &irq_info))) {
 		WARN(1, "Unable to get CXL IRQ Info: %i\n", ret);
 		return fail_psl_irq(afu, &irq_info);
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index e96be9ca4e60..80a87ab25b83 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -1921,7 +1921,7 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev)
 				goto err;
 
 			ctx = cxl_dev_context_init(afu_dev);
-			if (!ctx)
+			if (IS_ERR(ctx))
 				goto err;
 
 			afu_dev->dev.archdata.cxl_ctx = ctx;
diff --git a/drivers/misc/cxl/phb.c b/drivers/misc/cxl/phb.c
index 0935d44c1770..6ec69ada19f4 100644
--- a/drivers/misc/cxl/phb.c
+++ b/drivers/misc/cxl/phb.c
@@ -20,7 +20,7 @@ bool _cxl_pci_associate_default_context(struct pci_dev *dev, struct cxl_afu *afu
 	 * in the virtual phb, we'll need a default context to attach them to.
 	 */
 	ctx = cxl_dev_context_init(dev);
-	if (!ctx)
+	if (IS_ERR(ctx))
 		return false;
 	dev->dev.archdata.cxl_ctx = ctx;