linux-kernel - [PATCH 3/6] x86: add clwb_cache

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1438883000-9011-4-git-send-email-ross.zwisler@linux.intel.com>
Date:	Thu,  6 Aug 2015 11:43:17 -0600
From:	Ross Zwisler <ross.zwisler@...ux.intel.com>
To:	linux-kernel@...r.kernel.org, linux-nvdimm@...ts.01.org,
	dan.j.williams@...el.com
Cc:	Ross Zwisler <ross.zwisler@...ux.intel.com>,
	Thomas Gleixner <tglx@...utronix.de>,
	Ingo Molnar <mingo@...hat.com>,
	"H. Peter Anvin" <hpa@...or.com>, x86@...nel.org,
	Juergen Gross <jgross@...e.com>, Borislav Petkov <bp@...e.de>,
	Toshi Kani <toshi.kani@...com>,
	"Luis R. Rodriguez" <mcgrof@...e.com>
Subject: [PATCH 3/6] x86: add clwb_cache_range()

Add support for writing back a cache range using CLWB instead of just
flushing it using CLFLUSH or CLFLUSHOPT.  This allows you to ensure that
your data has become durable on your DIMM, but potentially leaves a
clean version in the processor cache hierarchy for future loads.

This will be used in DAX to write back stores to persistent memory.

Details on CLWB can be found here:

https://software.intel.com/sites/default/files/managed/0d/53/319433-022.pdf

Signed-off-by: Ross Zwisler <ross.zwisler@...ux.intel.com>
---
 arch/x86/include/asm/cacheflush.h |  1 +
 arch/x86/mm/pageattr.c            | 23 +++++++++++++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index ae00766..490b3d6 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -88,6 +88,7 @@ int set_pages_rw(struct page *page, int numpages);
 
 
 void clflush_cache_range(void *addr, unsigned int size);
+void clwb_cache_range(void *addr, size_t size);
 
 #ifdef CONFIG_DEBUG_RODATA
 void mark_rodata_ro(void);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 727158c..ce84d05 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -144,6 +144,29 @@ void clflush_cache_range(void *vaddr, unsigned int size)
 }
 EXPORT_SYMBOL_GPL(clflush_cache_range);
 
+/**
+ * clwb_cache_range - write back a cache range with clwb
+ * @vaddr:	virtual start address
+ * @size:	number of bytes to write back
+ *
+ * clwb is an unordered instruction which needs fencing with mfence or sfence
+ * to avoid ordering issues.
+ */
+void clwb_cache_range(void *vaddr, size_t size)
+{
+	u16 x86_clflush_size = boot_cpu_data.x86_clflush_size;
+	unsigned long clflush_mask = x86_clflush_size - 1;
+	char *vend = (char *)vaddr + size;
+	char *p;
+
+	for (p = (char *)((unsigned long)vaddr & ~clflush_mask);
+	     p < vend; p += x86_clflush_size)
+		clwb(p);
+
+	wmb();
+}
+EXPORT_SYMBOL_GPL(clwb_cache_range);
+
 static void __cpa_flush_all(void *arg)
 {
 	unsigned long cache = (unsigned long)arg;
-- 
2.1.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/