diff mbox

[v3,5/7] pmem: add copy_from_iter_pmem() and clear_pmem()

Message ID 1439836211-4719-6-git-send-email-ross.zwisler@linux.intel.com (mailing list archive)
State Superseded
Delegated to: Ross Zwisler
Headers show

Commit Message

Ross Zwisler Aug. 17, 2015, 6:30 p.m. UTC
Add support for two new PMEM APIs, copy_from_iter_pmem() and
clear_pmem().  copy_from_iter_pmem() is used to copy data from an
iterator into a PMEM buffer.  clear_pmem() zeros a PMEM memory range.

Both of these new APIs must be explicitly ordered using a wmb_pmem()
function call and are implemented in such a way that the wmb_pmem()
will make the stores to PMEM durable.  Because both APIs are unordered
they can be called as needed without introducing any unwanted memory
barriers.

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
---
 arch/x86/include/asm/pmem.h | 69 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pmem.h        | 65 ++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 131 insertions(+), 3 deletions(-)

Comments

Christoph Hellwig Aug. 17, 2015, 7:10 p.m. UTC | #1
>  #include <linux/uaccess.h>
> +#include <linux/uio.h>
> +

Can we keep this in linux/pmem.h?  I'm pretty sure the stubs would need
it as well, and even if they don't it'll keep the includes consistent.

> +{
> +	size_t len;
> +
> +	len = copy_from_iter_nocache((void __force *)addr, bytes, i);
> +
> +	/*
> +	 * copy_from_iter_nocache() on x86 only uses non-temporal stores for
> +	 * iovec iterators, so for other types (bvec & kvec) we must do a
> +	 * cache write-back.

Shouldn't we fi that?

> +	 */
> +	if (iter_is_iovec(i) == false)
> +		__arch_wb_cache_pmem(addr, bytes);

And if not and iter_needs_pmem_wb helper to encode this knowledge would
be useful.

> +static inline void arch_clear_pmem(void __pmem *addr, size_t size)
> +{
> +	/* TODO: implement the zeroing via non-temporal writes */
> +	if (size == PAGE_SIZE && ((unsigned long)addr & ~PAGE_MASK) == 0)
> +		clear_page((void __force *)addr);
> +	else
> +		memset((void __force *)addr, 0, size);
> +
> +	__arch_wb_cache_pmem(addr, size);

Please add a local vaiable so that the __force casting is only needed
once.  Same for other functions with this pattern.
Ross Zwisler Aug. 17, 2015, 10:23 p.m. UTC | #2
On Mon, 2015-08-17 at 21:10 +0200, Christoph Hellwig wrote:
> >  #include <linux/uaccess.h>
> > +#include <linux/uio.h>
> > +
> 
> Can we keep this in linux/pmem.h?  I'm pretty sure the stubs would need
> it as well, and even if they don't it'll keep the includes consistent.

Sure.

> > +{
> > +	size_t len;
> > +
> > +	len = copy_from_iter_nocache((void __force *)addr, bytes, i);
> > +
> > +	/*
> > +	 * copy_from_iter_nocache() on x86 only uses non-temporal stores for
> > +	 * iovec iterators, so for other types (bvec & kvec) we must do a
> > +	 * cache write-back.
> 
> Shouldn't we fi that?

I'm not sure - When Al make copy_from_iter_nocache() it was just a copy of
copy_from_iter(), with the iovec case changed to use
__copy_from_user_nocache().  The other cases use memcpy_from_page() and
memcpy().  To have everything do non-temporal stores we'd probably need to
make non-temporal versions of each of those (alluded to by Al's comment in the
copy_from_iter_nocache() commit: "BTW, do we want memcpy_nocache()?").

> > +	 */
> > +	if (iter_is_iovec(i) == false)
> > +		__arch_wb_cache_pmem(addr, bytes);
> 
> And if not and iter_needs_pmem_wb helper to encode this knowledge would
> be useful.

Maybe this should be the short-term solution, and I'll add a TODO to fix the
copy_from_iter_nocache() implementation as described above so we can always
have non-temporal stores?

> > +static inline void arch_clear_pmem(void __pmem *addr, size_t size)
> > +{
> > +	/* TODO: implement the zeroing via non-temporal writes */
> > +	if (size == PAGE_SIZE && ((unsigned long)addr & ~PAGE_MASK) == 0)
> > +		clear_page((void __force *)addr);
> > +	else
> > +		memset((void __force *)addr, 0, size);
> > +
> > +	__arch_wb_cache_pmem(addr, size);
> 
> Please add a local vaiable so that the __force casting is only needed
> once.  Same for other functions with this pattern.

Sure.
diff mbox

Patch

diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index 7f3413f..fba0121 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -14,6 +14,8 @@ 
 #define __ASM_X86_PMEM_H__
 
 #include <linux/uaccess.h>
+#include <linux/uio.h>
+
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
 #include <asm/special_insns.h>
@@ -66,6 +68,73 @@  static inline void arch_wmb_pmem(void)
 	pcommit_sfence();
 }
 
+/**
+ * __arch_wb_cache_pmem - write back a cache range with CLWB
+ * @addr:	virtual start address
+ * @size:	number of bytes to write back
+ *
+ * Write back a cache range using the CLWB (cache line write back)
+ * instruction.  This function requires explicit ordering with an
+ * arch_wmb_pmem() call.  This API is internal to the x86 PMEM implementation.
+ */
+static inline void __arch_wb_cache_pmem(void __pmem *addr, size_t size)
+{
+	u16 x86_clflush_size = boot_cpu_data.x86_clflush_size;
+	unsigned long clflush_mask = x86_clflush_size - 1;
+	void *vend = (void __force *)addr + size;
+	void *p;
+
+	for (p = (void *)((unsigned long)addr & ~clflush_mask);
+	     p < vend; p += x86_clflush_size)
+		clwb(p);
+}
+
+/**
+ * arch_copy_from_iter_pmem - copy data from an iterator to PMEM
+ * @addr:	PMEM destination address
+ * @bytes:	number of bytes to copy
+ * @i:		iterator with source data
+ *
+ * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'.
+ * This function requires explicit ordering with an arch_wmb_pmem() call.
+ */
+static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
+		struct iov_iter *i)
+{
+	size_t len;
+
+	len = copy_from_iter_nocache((void __force *)addr, bytes, i);
+
+	/*
+	 * copy_from_iter_nocache() on x86 only uses non-temporal stores for
+	 * iovec iterators, so for other types (bvec & kvec) we must do a
+	 * cache write-back.
+	 */
+	if (iter_is_iovec(i) == false)
+		__arch_wb_cache_pmem(addr, bytes);
+
+	return len;
+}
+
+/**
+ * arch_clear_pmem - zero a PMEM memory range
+ * @addr:	virtual start address
+ * @size:	number of bytes to zero
+ *
+ * Write zeros into the memory range starting at 'addr' for 'size' bytes.
+ * This function requires explicit ordering with an arch_wmb_pmem() call.
+ */
+static inline void arch_clear_pmem(void __pmem *addr, size_t size)
+{
+	/* TODO: implement the zeroing via non-temporal writes */
+	if (size == PAGE_SIZE && ((unsigned long)addr & ~PAGE_MASK) == 0)
+		clear_page((void __force *)addr);
+	else
+		memset((void __force *)addr, 0, size);
+
+	__arch_wb_cache_pmem(addr, size);
+}
+
 static inline bool arch_has_wmb_pmem(void)
 {
 #ifdef CONFIG_X86_64
diff --git a/include/linux/pmem.h b/include/linux/pmem.h
index 9d619d2..de415b3 100644
--- a/include/linux/pmem.h
+++ b/include/linux/pmem.h
@@ -39,12 +39,24 @@  static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
 {
 	BUG();
 }
+
+static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
+		struct iov_iter *i)
+{
+	BUG();
+	return 0;
+}
+
+static inline void arch_clear_pmem(void __pmem *addr, size_t size)
+{
+	BUG();
+}
 #endif
 
 /*
- * Architectures that define ARCH_HAS_PMEM_API must provide
- * implementations for arch_memremap_pmem(), arch_memcpy_to_pmem(),
- * arch_wmb_pmem(), and arch_has_wmb_pmem().
+ * Architectures that define ARCH_HAS_PMEM_API must provide implementations
+ * for arch_memremap_pmem(), arch_memcpy_to_pmem(), arch_wmb_pmem(),
+ * arch_copy_from_iter_pmem(), arch_clear_pmem() and arch_has_wmb_pmem().
  */
 
 static inline void memcpy_from_pmem(void *dst, void __pmem const *src, size_t size)
@@ -90,6 +102,20 @@  static void __pmem *default_memremap_pmem(resource_size_t offset,
 	return (void __pmem __force *)ioremap_wt(offset, size);
 }
 
+static inline size_t default_copy_from_iter_pmem(void __pmem *addr,
+		size_t bytes, struct iov_iter *i)
+{
+	return copy_from_iter_nocache((void __force *)addr, bytes, i);
+}
+
+static inline void default_clear_pmem(void __pmem *addr, size_t size)
+{
+	if (size == PAGE_SIZE && ((unsigned long)addr & ~PAGE_MASK) == 0)
+		clear_page((void __force *)addr);
+	else
+		memset((void __force *)addr, 0, size);
+}
+
 /**
  * memremap_pmem - map physical persistent memory for pmem api
  * @offset: physical address of persistent memory
@@ -142,4 +168,37 @@  static inline void wmb_pmem(void)
 	if (arch_has_pmem_api())
 		arch_wmb_pmem();
 }
+
+/**
+ * copy_from_iter_pmem - copy data from an iterator to PMEM
+ * @addr:	PMEM destination address
+ * @bytes:	number of bytes to copy
+ * @i:		iterator with source data
+ *
+ * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'.
+ * This function requires explicit ordering with a wmb_pmem() call.
+ */
+static inline size_t copy_from_iter_pmem(void __pmem *addr, size_t bytes,
+		struct iov_iter *i)
+{
+	if (arch_has_pmem_api())
+		return arch_copy_from_iter_pmem(addr, bytes, i);
+	return default_copy_from_iter_pmem(addr, bytes, i);
+}
+
+/**
+ * clear_pmem - zero a PMEM memory range
+ * @addr:	virtual start address
+ * @size:	number of bytes to zero
+ *
+ * Write zeros into the memory range starting at 'addr' for 'size' bytes.
+ * This function requires explicit ordering with a wmb_pmem() call.
+ */
+static inline void clear_pmem(void __pmem *addr, size_t size)
+{
+	if (arch_has_pmem_api())
+		arch_clear_pmem(addr, size);
+	else
+		default_clear_pmem(addr, size);
+}
 #endif /* __PMEM_H__ */