Merge tag 'powerpc-4.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights include:

   - Support for STRICT_KERNEL_RWX on 64-bit server CPUs.

   - Platform support for FSP2 (476fpe) board

   - Enable ZONE_DEVICE on 64-bit server CPUs.

   - Generic & powerpc spin loop primitives to optimise busy waiting

   - Convert VDSO update function to use new update_vsyscall() interface

   - Optimisations to hypercall/syscall/context-switch paths

   - Improvements to the CPU idle code on Power8 and Power9.

  As well as many other fixes and improvements.

  Thanks to: Akshay Adiga, Andrew Donnellan, Andrew Jeffery, Anshuman
  Khandual, Anton Blanchard, Balbir Singh, Benjamin Herrenschmidt,
  Christophe Leroy, Christophe Lombard, Colin Ian King, Dan Carpenter,
  Gautham R. Shenoy, Hari Bathini, Ian Munsie, Ivan Mikhaylov, Javier
  Martinez Canillas, Madhavan Srinivasan, Masahiro Yamada, Matt Brown,
  Michael Neuling, Michal Suchanek, Murilo Opsfelder Araujo, Naveen N.
  Rao, Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pavel Machek,
  Russell Currey, Santosh Sivaraj, Stephen Rothwell, Thiago Jung
  Bauermann, Yang Li"

* tag 'powerpc-4.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (158 commits)
  powerpc/Kconfig: Enable STRICT_KERNEL_RWX for some configs
  powerpc/mm/radix: Implement STRICT_RWX/mark_rodata_ro() for Radix
  powerpc/mm/hash: Implement mark_rodata_ro() for hash
  powerpc/vmlinux.lds: Align __init_begin to 16M
  powerpc/lib/code-patching: Use alternate map for patch_instruction()
  powerpc/xmon: Add patch_instruction() support for xmon
  powerpc/kprobes/optprobes: Use patch_instruction()
  powerpc/kprobes: Move kprobes over to patch_instruction()
  powerpc/mm/radix: Fix execute permissions for interrupt_vectors
  powerpc/pseries: Fix passing of pp0 in updatepp() and updateboltedpp()
  powerpc/64s: Blacklist rtas entry/exit from kprobes
  powerpc/64s: Blacklist functions invoked on a trap
  powerpc/64s: Un-blacklist system_call() from kprobes
  powerpc/64s: Move system_call() symbol to just after setting MSR_EE
  powerpc/64s: Blacklist system_call() and system_call_common() from kprobes
  powerpc/64s: Convert .L__replay_interrupt_return to a local label
  powerpc64/elfv1: Only dereference function descriptor for non-text symbols
  cxl: Export library to support IBM XSL
  powerpc/dts: Use #include "..." to include local DT
  powerpc/perf/hv-24x7: Aggregate result elements on POWER9 SMT8
  ...

3 files changed, 215 insertions, 0 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index f9f56f231ae6..da0be9a8d1de 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -594,6 +594,7 @@
 #define SBSS(sbss_align)						\
 	. = ALIGN(sbss_align);						\
 	.sbss : AT(ADDR(.sbss) - LOAD_OFFSET) {				\
+		*(.dynsbss)						\
 		*(.sbss)						\
 		*(.scommon)						\
 	}
@@ -640,11 +641,22 @@
 		.debug_str      0 : { *(.debug_str) }			\
 		.debug_loc      0 : { *(.debug_loc) }			\
 		.debug_macinfo  0 : { *(.debug_macinfo) }		\
+		.debug_pubtypes 0 : { *(.debug_pubtypes) }		\
+		/* DWARF 3 */						\
+		.debug_ranges	0 : { *(.debug_ranges) }		\
 		/* SGI/MIPS DWARF 2 extensions */			\
 		.debug_weaknames 0 : { *(.debug_weaknames) }		\
 		.debug_funcnames 0 : { *(.debug_funcnames) }		\
 		.debug_typenames 0 : { *(.debug_typenames) }		\
 		.debug_varnames  0 : { *(.debug_varnames) }		\
+		/* GNU DWARF 2 extensions */				\
+		.debug_gnu_pubnames 0 : { *(.debug_gnu_pubnames) }	\
+		.debug_gnu_pubtypes 0 : { *(.debug_gnu_pubtypes) }	\
+		/* DWARF 4 */						\
+		.debug_types	0 : { *(.debug_types) }			\
+		/* DWARF 5 */						\
+		.debug_macro	0 : { *(.debug_macro) }			\
+		.debug_addr	0 : { *(.debug_addr) }
 
 		/* Stabs debugging sections.  */
 #define STABS_DEBUG							\
diff --git a/include/linux/processor.h b/include/linux/processor.h
new file mode 100644
index 000000000000..da0c5e56ca02
--- /dev/null
+++ b/include/linux/processor.h
@@ -0,0 +1,70 @@
+/* Misc low level processor primitives */
+#ifndef _LINUX_PROCESSOR_H
+#define _LINUX_PROCESSOR_H
+
+#include <asm/processor.h>
+
+/*
+ * spin_begin is used before beginning a busy-wait loop, and must be paired
+ * with spin_end when the loop is exited. spin_cpu_relax must be called
+ * within the loop.
+ *
+ * The loop body should be as small and fast as possible, on the order of
+ * tens of instructions/cycles as a guide. It should and avoid calling
+ * cpu_relax, or any "spin" or sleep type of primitive including nested uses
+ * of these primitives. It should not lock or take any other resource.
+ * Violations of these guidelies will not cause a bug, but may cause sub
+ * optimal performance.
+ *
+ * These loops are optimized to be used where wait times are expected to be
+ * less than the cost of a context switch (and associated overhead).
+ *
+ * Detection of resource owner and decision to spin or sleep or guest-yield
+ * (e.g., spin lock holder vcpu preempted, or mutex owner not on CPU) can be
+ * tested within the loop body.
+ */
+#ifndef spin_begin
+#define spin_begin()
+#endif
+
+#ifndef spin_cpu_relax
+#define spin_cpu_relax() cpu_relax()
+#endif
+
+/*
+ * spin_cpu_yield may be called to yield (undirected) to the hypervisor if
+ * necessary. This should be used if the wait is expected to take longer
+ * than context switch overhead, but we can't sleep or do a directed yield.
+ */
+#ifndef spin_cpu_yield
+#define spin_cpu_yield() cpu_relax_yield()
+#endif
+
+#ifndef spin_end
+#define spin_end()
+#endif
+
+/*
+ * spin_until_cond can be used to wait for a condition to become true. It
+ * may be expected that the first iteration will true in the common case
+ * (no spinning), so that callers should not require a first "likely" test
+ * for the uncontended case before using this primitive.
+ *
+ * Usage and implementation guidelines are the same as for the spin_begin
+ * primitives, above.
+ */
+#ifndef spin_until_cond
+#define spin_until_cond(cond)					\
+do {								\
+	if (unlikely(!(cond))) {				\
+		spin_begin();					\
+		do {						\
+			spin_cpu_relax();			\
+		} while (!(cond));				\
+		spin_end();					\
+	}							\
+} while (0)
+
+#endif
+
+#endif /* _LINUX_PROCESSOR_H */
diff --git a/include/misc/cxllib.h b/include/misc/cxllib.h
new file mode 100644
index 000000000000..e5aa29f019a6
--- /dev/null
+++ b/include/misc/cxllib.h
@@ -0,0 +1,133 @@
+/*
+ * Copyright 2017 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _MISC_CXLLIB_H
+#define _MISC_CXLLIB_H
+
+#include <linux/pci.h>
+#include <asm/reg.h>
+
+/*
+ * cxl driver exports a in-kernel 'library' API which can be called by
+ * other drivers to help interacting with an IBM XSL.
+ */
+
+/*
+ * tells whether capi is supported on the PCIe slot where the
+ * device is seated
+ *
+ * Input:
+ *	dev: device whose slot needs to be checked
+ *	flags: 0 for the time being
+ */
+bool cxllib_slot_is_supported(struct pci_dev *dev, unsigned long flags);
+
+
+/*
+ * Returns the configuration parameters to be used by the XSL or device
+ *
+ * Input:
+ *	dev: device, used to find PHB
+ * Output:
+ *	struct cxllib_xsl_config:
+ *		version
+ *		capi BAR address, i.e. 0x2000000000000-0x2FFFFFFFFFFFF
+ *		capi BAR size
+ *		data send control (XSL_DSNCTL)
+ *		dummy read address (XSL_DRA)
+ */
+#define CXL_XSL_CONFIG_VERSION1		1
+struct cxllib_xsl_config {
+	u32	version;     /* format version for register encoding */
+	u32	log_bar_size;/* log size of the capi_window */
+	u64	bar_addr;    /* address of the start of capi window */
+	u64	dsnctl;      /* matches definition of XSL_DSNCTL */
+	u64	dra;         /* real address that can be used for dummy read */
+};
+
+int cxllib_get_xsl_config(struct pci_dev *dev, struct cxllib_xsl_config *cfg);
+
+
+/*
+ * Activate capi for the pci host bridge associated with the device.
+ * Can be extended to deactivate once we know how to do it.
+ * Device must be ready to accept messages from the CAPP unit and
+ * respond accordingly (TLB invalidates, ...)
+ *
+ * PHB is switched to capi mode through calls to skiboot.
+ * CAPP snooping is activated
+ *
+ * Input:
+ *	dev: device whose PHB should switch mode
+ *	mode: mode to switch to i.e. CAPI or PCI
+ *	flags: options related to the mode
+ */
+enum cxllib_mode {
+	CXL_MODE_CXL,
+	CXL_MODE_PCI,
+};
+
+#define CXL_MODE_NO_DMA       0
+#define CXL_MODE_DMA_TVT0     1
+#define CXL_MODE_DMA_TVT1     2
+
+int cxllib_switch_phb_mode(struct pci_dev *dev, enum cxllib_mode mode,
+			unsigned long flags);
+
+
+/*
+ * Set the device for capi DMA.
+ * Define its dma_ops and dma offset so that allocations will be using TVT#1
+ *
+ * Input:
+ *	dev: device to set
+ *	flags: options. CXL_MODE_DMA_TVT1 should be used
+ */
+int cxllib_set_device_dma(struct pci_dev *dev, unsigned long flags);
+
+
+/*
+ * Get the Process Element structure for the given thread
+ *
+ * Input:
+ *    task: task_struct for the context of the translation
+ *    translation_mode: whether addresses should be translated
+ * Output:
+ *    attr: attributes to fill up the Process Element structure from CAIA
+ */
+struct cxllib_pe_attributes {
+	u64 sr;
+	u32 lpid;
+	u32 tid;
+	u32 pid;
+};
+#define CXL_TRANSLATED_MODE 0
+#define CXL_REAL_MODE 1
+
+int cxllib_get_PE_attributes(struct task_struct *task,
+	     unsigned long translation_mode, struct cxllib_pe_attributes *attr);
+
+
+/*
+ * Handle memory fault.
+ * Fault in all the pages of the specified buffer for the permissions
+ * provided in ‘flags’
+ *
+ * Shouldn't be called from interrupt context
+ *
+ * Input:
+ *	mm: struct mm for the thread faulting the pages
+ *	addr: base address of the buffer to page in
+ *	size: size of the buffer to page in
+ *	flags: permission requested (DSISR_ISSTORE...)
+ */
+int cxllib_handle_fault(struct mm_struct *mm, u64 addr, u64 size, u64 flags);
+
+
+#endif /* _MISC_CXLLIB_H */