x86, uaccess: introduce copy_from_iter_flushcache for pmem / cache-bypass operations

The pmem driver has a need to transfer data with a persistent memory
destination and be able to rely on the fact that the destination writes are not
cached. It is sufficient for the writes to be flushed to a cpu-store-buffer
(non-temporal / "movnt" in x86 terms), as we expect userspace to call fsync()
to ensure data-writes have reached a power-fail-safe zone in the platform. The
fsync() triggers a REQ_FUA or REQ_FLUSH to the pmem driver which will turn
around and fence previous writes with an "sfence".

Implement a __copy_from_user_inatomic_flushcache, memcpy_page_flushcache, and
memcpy_flushcache, that guarantee that the destination buffer is not dirty in
the cpu cache on completion. The new copy_from_iter_flushcache and sub-routines
will be used to replace the "pmem api" (include/linux/pmem.h +
arch/x86/include/asm/pmem.h). The availability of copy_from_iter_flushcache()
and memcpy_flushcache() are gated by the CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
config symbol, and fallback to copy_from_iter_nocache() and plain memcpy()
otherwise.

This is meant to satisfy the concern from Linus that if a driver wants to do
something beyond the normal nocache semantics it should be something private to
that driver [1], and Al's concern that anything uaccess related belongs with
the rest of the uaccess code [2].

The first consumer of this interface is a new 'copy_from_iter' dax operation so
that pmem can inject cache maintenance operations without imposing this
overhead on other dax-capable drivers.

[1]: https://lists.01.org/pipermail/linux-nvdimm/2017-January/008364.html
[2]: https://lists.01.org/pipermail/linux-nvdimm/2017-April/009942.html

Cc: <x86@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Toshi Kani <toshi.kani@hpe.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

1 files changed, 128 insertions, 0 deletions

diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 3b7c40a2e3e1..f42d2fd86ca3 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -7,6 +7,7 @@
  */
 #include <linux/export.h>
 #include <linux/uaccess.h>
+#include <linux/highmem.h>
 
 /*
  * Zero Userspace
@@ -73,3 +74,130 @@ copy_user_handle_tail(char *to, char *from, unsigned len)
 	clac();
 	return len;
 }
+
+#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+/**
+ * clean_cache_range - write back a cache range with CLWB
+ * @vaddr:	virtual start address
+ * @size:	number of bytes to write back
+ *
+ * Write back a cache range using the CLWB (cache line write back)
+ * instruction. Note that @size is internally rounded up to be cache
+ * line size aligned.
+ */
+static void clean_cache_range(void *addr, size_t size)
+{
+	u16 x86_clflush_size = boot_cpu_data.x86_clflush_size;
+	unsigned long clflush_mask = x86_clflush_size - 1;
+	void *vend = addr + size;
+	void *p;
+
+	for (p = (void *)((unsigned long)addr & ~clflush_mask);
+	     p < vend; p += x86_clflush_size)
+		clwb(p);
+}
+
+long __copy_user_flushcache(void *dst, const void __user *src, unsigned size)
+{
+	unsigned long flushed, dest = (unsigned long) dst;
+	long rc = __copy_user_nocache(dst, src, size, 0);
+
+	/*
+	 * __copy_user_nocache() uses non-temporal stores for the bulk
+	 * of the transfer, but we need to manually flush if the
+	 * transfer is unaligned. A cached memory copy is used when
+	 * destination or size is not naturally aligned. That is:
+	 *   - Require 8-byte alignment when size is 8 bytes or larger.
+	 *   - Require 4-byte alignment when size is 4 bytes.
+	 */
+	if (size < 8) {
+		if (!IS_ALIGNED(dest, 4) || size != 4)
+			clean_cache_range(dst, 1);
+	} else {
+		if (!IS_ALIGNED(dest, 8)) {
+			dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+			clean_cache_range(dst, 1);
+		}
+
+		flushed = dest - (unsigned long) dst;
+		if (size > flushed && !IS_ALIGNED(size - flushed, 8))
+			clean_cache_range(dst + size - 1, 1);
+	}
+
+	return rc;
+}
+
+void memcpy_flushcache(void *_dst, const void *_src, size_t size)
+{
+	unsigned long dest = (unsigned long) _dst;
+	unsigned long source = (unsigned long) _src;
+
+	/* cache copy and flush to align dest */
+	if (!IS_ALIGNED(dest, 8)) {
+		unsigned len = min_t(unsigned, size, ALIGN(dest, 8) - dest);
+
+		memcpy((void *) dest, (void *) source, len);
+		clean_cache_range((void *) dest, len);
+		dest += len;
+		source += len;
+		size -= len;
+		if (!size)
+			return;
+	}
+
+	/* 4x8 movnti loop */
+	while (size >= 32) {
+		asm("movq    (%0), %%r8\n"
+		    "movq   8(%0), %%r9\n"
+		    "movq  16(%0), %%r10\n"
+		    "movq  24(%0), %%r11\n"
+		    "movnti  %%r8,   (%1)\n"
+		    "movnti  %%r9,  8(%1)\n"
+		    "movnti %%r10, 16(%1)\n"
+		    "movnti %%r11, 24(%1)\n"
+		    :: "r" (source), "r" (dest)
+		    : "memory", "r8", "r9", "r10", "r11");
+		dest += 32;
+		source += 32;
+		size -= 32;
+	}
+
+	/* 1x8 movnti loop */
+	while (size >= 8) {
+		asm("movq    (%0), %%r8\n"
+		    "movnti  %%r8,   (%1)\n"
+		    :: "r" (source), "r" (dest)
+		    : "memory", "r8");
+		dest += 8;
+		source += 8;
+		size -= 8;
+	}
+
+	/* 1x4 movnti loop */
+	while (size >= 4) {
+		asm("movl    (%0), %%r8d\n"
+		    "movnti  %%r8d,   (%1)\n"
+		    :: "r" (source), "r" (dest)
+		    : "memory", "r8");
+		dest += 4;
+		source += 4;
+		size -= 4;
+	}
+
+	/* cache copy for remaining bytes */
+	if (size) {
+		memcpy((void *) dest, (void *) source, size);
+		clean_cache_range((void *) dest, size);
+	}
+}
+EXPORT_SYMBOL_GPL(memcpy_flushcache);
+
+void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
+		size_t len)
+{
+	char *from = kmap_atomic(page);
+
+	memcpy_flushcache(to, from + offset, len);
+	kunmap_atomic(from);
+}
+#endif