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
  ...

1 files changed, 167 insertions, 4 deletions

diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index 500b0f6a0b64..c9de03e0c1f1 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -12,23 +12,186 @@
 #include <linux/vmalloc.h>
 #include <linux/init.h>
 #include <linux/mm.h>
-#include <asm/page.h>
-#include <asm/code-patching.h>
+#include <linux/cpuhotplug.h>
+#include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/kprobes.h>
 
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/page.h>
+#include <asm/code-patching.h>
 
-int patch_instruction(unsigned int *addr, unsigned int instr)
+static int __patch_instruction(unsigned int *addr, unsigned int instr)
 {
 	int err;
 
 	__put_user_size(instr, addr, 4, err);
 	if (err)
 		return err;
-	asm ("dcbst 0, %0; sync; icbi 0,%0; sync; isync" : : "r" (addr));
+
+	asm ("dcbst 0, %0; sync; icbi 0,%0; sync; isync" :: "r" (addr));
+
+	return 0;
+}
+
+#ifdef CONFIG_STRICT_KERNEL_RWX
+static DEFINE_PER_CPU(struct vm_struct *, text_poke_area);
+
+static int text_area_cpu_up(unsigned int cpu)
+{
+	struct vm_struct *area;
+
+	area = get_vm_area(PAGE_SIZE, VM_ALLOC);
+	if (!area) {
+		WARN_ONCE(1, "Failed to create text area for cpu %d\n",
+			cpu);
+		return -1;
+	}
+	this_cpu_write(text_poke_area, area);
+
+	return 0;
+}
+
+static int text_area_cpu_down(unsigned int cpu)
+{
+	free_vm_area(this_cpu_read(text_poke_area));
+	return 0;
+}
+
+/*
+ * Run as a late init call. This allows all the boot time patching to be done
+ * simply by patching the code, and then we're called here prior to
+ * mark_rodata_ro(), which happens after all init calls are run. Although
+ * BUG_ON() is rude, in this case it should only happen if ENOMEM, and we judge
+ * it as being preferable to a kernel that will crash later when someone tries
+ * to use patch_instruction().
+ */
+static int __init setup_text_poke_area(void)
+{
+	BUG_ON(!cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+		"powerpc/text_poke:online", text_area_cpu_up,
+		text_area_cpu_down));
+
+	return 0;
+}
+late_initcall(setup_text_poke_area);
+
+/*
+ * This can be called for kernel text or a module.
+ */
+static int map_patch_area(void *addr, unsigned long text_poke_addr)
+{
+	unsigned long pfn;
+	int err;
+
+	if (is_vmalloc_addr(addr))
+		pfn = vmalloc_to_pfn(addr);
+	else
+		pfn = __pa_symbol(addr) >> PAGE_SHIFT;
+
+	err = map_kernel_page(text_poke_addr, (pfn << PAGE_SHIFT),
+				pgprot_val(PAGE_KERNEL));
+
+	pr_devel("Mapped addr %lx with pfn %lx:%d\n", text_poke_addr, pfn, err);
+	if (err)
+		return -1;
+
 	return 0;
 }
 
+static inline int unmap_patch_area(unsigned long addr)
+{
+	pte_t *ptep;
+	pmd_t *pmdp;
+	pud_t *pudp;
+	pgd_t *pgdp;
+
+	pgdp = pgd_offset_k(addr);
+	if (unlikely(!pgdp))
+		return -EINVAL;
+
+	pudp = pud_offset(pgdp, addr);
+	if (unlikely(!pudp))
+		return -EINVAL;
+
+	pmdp = pmd_offset(pudp, addr);
+	if (unlikely(!pmdp))
+		return -EINVAL;
+
+	ptep = pte_offset_kernel(pmdp, addr);
+	if (unlikely(!ptep))
+		return -EINVAL;
+
+	pr_devel("clearing mm %p, pte %p, addr %lx\n", &init_mm, ptep, addr);
+
+	/*
+	 * In hash, pte_clear flushes the tlb, in radix, we have to
+	 */
+	pte_clear(&init_mm, addr, ptep);
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
+	return 0;
+}
+
+int patch_instruction(unsigned int *addr, unsigned int instr)
+{
+	int err;
+	unsigned int *dest = NULL;
+	unsigned long flags;
+	unsigned long text_poke_addr;
+	unsigned long kaddr = (unsigned long)addr;
+
+	/*
+	 * During early early boot patch_instruction is called
+	 * when text_poke_area is not ready, but we still need
+	 * to allow patching. We just do the plain old patching
+	 * We use slab_is_available and per cpu read * via this_cpu_read
+	 * of text_poke_area. Per-CPU areas might not be up early
+	 * this can create problems with just using this_cpu_read()
+	 */
+	if (!slab_is_available() || !this_cpu_read(text_poke_area))
+		return __patch_instruction(addr, instr);
+
+	local_irq_save(flags);
+
+	text_poke_addr = (unsigned long)__this_cpu_read(text_poke_area)->addr;
+	if (map_patch_area(addr, text_poke_addr)) {
+		err = -1;
+		goto out;
+	}
+
+	dest = (unsigned int *)(text_poke_addr) +
+			((kaddr & ~PAGE_MASK) / sizeof(unsigned int));
+
+	/*
+	 * We use __put_user_size so that we can handle faults while
+	 * writing to dest and return err to handle faults gracefully
+	 */
+	__put_user_size(instr, dest, 4, err);
+	if (!err)
+		asm ("dcbst 0, %0; sync; icbi 0,%0; icbi 0,%1; sync; isync"
+			::"r" (dest), "r"(addr));
+
+	err = unmap_patch_area(text_poke_addr);
+	if (err)
+		pr_warn("failed to unmap %lx\n", text_poke_addr);
+
+out:
+	local_irq_restore(flags);
+
+	return err;
+}
+#else /* !CONFIG_STRICT_KERNEL_RWX */
+
+int patch_instruction(unsigned int *addr, unsigned int instr)
+{
+	return __patch_instruction(addr, instr);
+}
+
+#endif /* CONFIG_STRICT_KERNEL_RWX */
+NOKPROBE_SYMBOL(patch_instruction);
+
 int patch_branch(unsigned int *addr, unsigned long target, int flags)
 {
 	return patch_instruction(addr, create_branch(addr, target, flags));