arch, x86: pmem api for ensuring durability of persistent memory updates

Based on an original patch by Ross Zwisler [1].

Writes to persistent memory have the potential to be posted to cpu
cache, cpu write buffers, and platform write buffers (memory controller)
before being committed to persistent media.  Provide apis,
memcpy_to_pmem(), wmb_pmem(), and memremap_pmem(), to write data to
pmem and assert that it is durable in PMEM (a persistent linear address
range).  A '__pmem' attribute is added so sparse can track proper usage
of pointers to pmem.

This continues the status quo of pmem being x86 only for 4.2, but
reworks to ioremap, and wider implementation of memremap() will enable
other archs in 4.3.

[1]: https://lists.01.org/pipermail/linux-nvdimm/2015-May/000932.html

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
[djbw: various reworks]
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

3 files changed, 79 insertions, 0 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1a2cbf641667..62564ddf7f78 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -27,6 +27,7 @@ config X86
 	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_PMEM_API
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select HAVE_AOUT if X86_32
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 47c8e32f621a..ec23bb753a3e 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -4,6 +4,7 @@
 /* Caches aren't brain-dead on the intel. */
 #include <asm-generic/cacheflush.h>
 #include <asm/special_insns.h>
+#include <asm/uaccess.h>
 
 /*
  * The set_memory_* API can be used to change various attributes of a virtual
@@ -104,4 +105,75 @@ static inline int rodata_test(void)
 }
 #endif
 
+#ifdef ARCH_HAS_NOCACHE_UACCESS
+
+/**
+ * arch_memcpy_to_pmem - copy data to persistent memory
+ * @dst: destination buffer for the copy
+ * @src: source buffer for the copy
+ * @n: length of the copy in bytes
+ *
+ * Copy data to persistent memory media via non-temporal stores so that
+ * a subsequent arch_wmb_pmem() can flush cpu and memory controller
+ * write buffers to guarantee durability.
+ */
+static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
+		size_t n)
+{
+	int unwritten;
+
+	/*
+	 * We are copying between two kernel buffers, if
+	 * __copy_from_user_inatomic_nocache() returns an error (page
+	 * fault) we would have already reported a general protection fault
+	 * before the WARN+BUG.
+	 */
+	unwritten = __copy_from_user_inatomic_nocache((void __force *) dst,
+			(void __user *) src, n);
+	if (WARN(unwritten, "%s: fault copying %p <- %p unwritten: %d\n",
+				__func__, dst, src, unwritten))
+		BUG();
+}
+
+/**
+ * arch_wmb_pmem - synchronize writes to persistent memory
+ *
+ * After a series of arch_memcpy_to_pmem() operations this drains data
+ * from cpu write buffers and any platform (memory controller) buffers
+ * to ensure that written data is durable on persistent memory media.
+ */
+static inline void arch_wmb_pmem(void)
+{
+	/*
+	 * wmb() to 'sfence' all previous writes such that they are
+	 * architecturally visible to 'pcommit'.  Note, that we've
+	 * already arranged for pmem writes to avoid the cache via
+	 * arch_memcpy_to_pmem().
+	 */
+	wmb();
+	pcommit_sfence();
+}
+
+static inline bool __arch_has_wmb_pmem(void)
+{
+#ifdef CONFIG_X86_64
+	/*
+	 * We require that wmb() be an 'sfence', that is only guaranteed on
+	 * 64-bit builds
+	 */
+	return static_cpu_has(X86_FEATURE_PCOMMIT);
+#else
+	return false;
+#endif
+}
+#else /* ARCH_HAS_NOCACHE_UACCESS i.e. ARCH=um */
+extern void arch_memcpy_to_pmem(void __pmem *dst, const void *src, size_t n);
+extern void arch_wmb_pmem(void);
+
+static inline bool __arch_has_wmb_pmem(void)
+{
+	return false;
+}
+#endif
+
 #endif /* _ASM_X86_CACHEFLUSH_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 34a5b93704d3..c60c3f3b0183 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -247,6 +247,12 @@ static inline void flush_write_buffers(void)
 #endif
 }
 
+static inline void __pmem *arch_memremap_pmem(resource_size_t offset,
+	unsigned long size)
+{
+	return (void __force __pmem *) ioremap_cache(offset, size);
+}
+
 #endif /* __KERNEL__ */
 
 extern void native_io_delay(void);