summaryrefslogtreecommitdiff
path: root/arch/x86/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/elf.h2
-rw-r--r--arch/x86/include/asm/pmem.h45
2 files changed, 33 insertions, 14 deletions
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1514753fd435..d262f985bbc8 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -278,7 +278,7 @@ struct task_struct;
#define ARCH_DLINFO_IA32 \
do { \
- if (vdso32_enabled) { \
+ if (VDSO_CURRENT_BASE) { \
NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \
NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \
} \
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index d8ce3ec816ab..6503526d7b24 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -72,8 +72,8 @@ static inline void arch_wmb_pmem(void)
* @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.
+ * instruction. Note that @size is internally rounded up to be cache
+ * line size aligned.
*/
static inline void __arch_wb_cache_pmem(void *vaddr, size_t size)
{
@@ -87,15 +87,6 @@ static inline void __arch_wb_cache_pmem(void *vaddr, size_t size)
clwb(p);
}
-/*
- * 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.
- */
-static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
-{
- return iter_is_iovec(i) == false;
-}
-
/**
* arch_copy_from_iter_pmem - copy data from an iterator to PMEM
* @addr: PMEM destination address
@@ -114,8 +105,36 @@ static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
/* TODO: skip the write-back by always using non-temporal stores */
len = copy_from_iter_nocache(vaddr, bytes, i);
- if (__iter_needs_pmem_wb(i))
- __arch_wb_cache_pmem(vaddr, bytes);
+ /*
+ * In the iovec case on x86_64 copy_from_iter_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.
+ *
+ * In the non-iovec case the entire destination needs to be
+ * flushed.
+ */
+ if (iter_is_iovec(i)) {
+ unsigned long flushed, dest = (unsigned long) addr;
+
+ if (bytes < 8) {
+ if (!IS_ALIGNED(dest, 4) || (bytes != 4))
+ __arch_wb_cache_pmem(addr, bytes);
+ } else {
+ if (!IS_ALIGNED(dest, 8)) {
+ dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+ __arch_wb_cache_pmem(addr, 1);
+ }
+
+ flushed = dest - (unsigned long) addr;
+ if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8))
+ __arch_wb_cache_pmem(addr + bytes - 1, 1);
+ }
+ } else
+ __arch_wb_cache_pmem(addr, bytes);
return len;
}