if ( flags & FLUSH_CACHE )
{
const struct cpuinfo_x86 *c = ¤t_cpu_data;
- unsigned long i, sz = 0;
+ unsigned long sz = 0;
if ( order < (BITS_PER_LONG - PAGE_SHIFT) )
sz = 1UL << (order + PAGE_SHIFT);
c->x86_clflush_size && c->x86_cache_size && sz &&
((sz >> 10) < c->x86_cache_size) )
{
- alternative("", "sfence", X86_FEATURE_CLFLUSHOPT);
- for ( i = 0; i < sz; i += c->x86_clflush_size )
- alternative_input(".byte " __stringify(NOP_DS_PREFIX) ";"
- " clflush %0",
- "data16 clflush %0", /* clflushopt */
- X86_FEATURE_CLFLUSHOPT,
- "m" (((const char *)va)[i]));
+ cache_flush(va, sz);
flags &= ~FLUSH_CACHE;
}
else
return flags;
}
+void cache_flush(const void *addr, unsigned int size)
+{
+ /*
+ * This function may be called before current_cpu_data is established.
+ * Hence a fallback is needed to prevent the loop below becoming infinite.
+ */
+ unsigned int clflush_size = current_cpu_data.x86_clflush_size ?: 16;
+ const void *end = addr + size;
+
+ addr -= (unsigned long)addr & (clflush_size - 1);
+ for ( ; addr < end; addr += clflush_size )
+ {
+ /*
+ * Note regarding the "ds" prefix use: it's faster to do a clflush
+ * + prefix than a clflush + nop, and hence the prefix is added instead
+ * of letting the alternative framework fill the gap by appending nops.
+ */
+ alternative_io("ds; clflush %[p]",
+ "data16 clflush %[p]", /* clflushopt */
+ X86_FEATURE_CLFLUSHOPT,
+ /* no outputs */,
+ [p] "m" (*(const char *)(addr)));
+ }
+
+ alternative("", "sfence", X86_FEATURE_CLFLUSHOPT);
+}
+
+void cache_writeback(const void *addr, unsigned int size)
+{
+ unsigned int clflush_size;
+ const void *end = addr + size;
+
+ /* Fall back to CLFLUSH{,OPT} when CLWB isn't available. */
+ if ( !boot_cpu_has(X86_FEATURE_CLWB) )
+ return cache_flush(addr, size);
+
+ /*
+ * This function may be called before current_cpu_data is established.
+ * Hence a fallback is needed to prevent the loop below becoming infinite.
+ */
+ clflush_size = current_cpu_data.x86_clflush_size ?: 16;
+ addr -= (unsigned long)addr & (clflush_size - 1);
+ for ( ; addr < end; addr += clflush_size )
+ {
+/*
+ * The arguments to a macro must not include preprocessor directives. Doing so
+ * results in undefined behavior, so we have to create some defines here in
+ * order to avoid it.
+ */
+#if defined(HAVE_AS_CLWB)
+# define CLWB_ENCODING "clwb %[p]"
+#elif defined(HAVE_AS_XSAVEOPT)
+# define CLWB_ENCODING "data16 xsaveopt %[p]" /* clwb */
+#else
+# define CLWB_ENCODING ".byte 0x66, 0x0f, 0xae, 0x30" /* clwb (%%rax) */
+#endif
+
+#define BASE_INPUT(addr) [p] "m" (*(const char *)(addr))
+#if defined(HAVE_AS_CLWB) || defined(HAVE_AS_XSAVEOPT)
+# define INPUT BASE_INPUT
+#else
+# define INPUT(addr) "a" (addr), BASE_INPUT(addr)
+#endif
+
+ asm volatile (CLWB_ENCODING :: INPUT(addr));
+
+#undef INPUT
+#undef BASE_INPUT
+#undef CLWB_ENCODING
+ }
+
+ asm volatile ("sfence" ::: "memory");
+}
+
unsigned int guest_flush_tlb_flags(const struct domain *d)
{
bool shadow = paging_mode_shadow(d);
#include <xen/pci.h>
#include <xen/pci_regs.h>
#include <xen/keyhandler.h>
+#include <asm/cache.h>
#include <asm/msi.h>
#include <asm/nops.h>
#include <asm/irq.h>
}
}
-static void sync_cache(const void *addr, unsigned int size)
-{
- static unsigned long clflush_size = 0;
- const void *end = addr + size;
-
- if ( clflush_size == 0 )
- clflush_size = get_cache_line_size();
-
- addr -= (unsigned long)addr & (clflush_size - 1);
- for ( ; addr < end; addr += clflush_size )
-/*
- * The arguments to a macro must not include preprocessor directives. Doing so
- * results in undefined behavior, so we have to create some defines here in
- * order to avoid it.
- */
-#if defined(HAVE_AS_CLWB)
-# define CLWB_ENCODING "clwb %[p]"
-#elif defined(HAVE_AS_XSAVEOPT)
-# define CLWB_ENCODING "data16 xsaveopt %[p]" /* clwb */
-#else
-# define CLWB_ENCODING ".byte 0x66, 0x0f, 0xae, 0x30" /* clwb (%%rax) */
-#endif
-
-#define BASE_INPUT(addr) [p] "m" (*(const char *)(addr))
-#if defined(HAVE_AS_CLWB) || defined(HAVE_AS_XSAVEOPT)
-# define INPUT BASE_INPUT
-#else
-# define INPUT(addr) "a" (addr), BASE_INPUT(addr)
-#endif
- /*
- * Note regarding the use of NOP_DS_PREFIX: it's faster to do a clflush
- * + prefix than a clflush + nop, and hence the prefix is added instead
- * of letting the alternative framework fill the gap by appending nops.
- */
- alternative_io_2(".byte " __stringify(NOP_DS_PREFIX) "; clflush %[p]",
- "data16 clflush %[p]", /* clflushopt */
- X86_FEATURE_CLFLUSHOPT,
- CLWB_ENCODING,
- X86_FEATURE_CLWB, /* no outputs */,
- INPUT(addr));
-#undef INPUT
-#undef BASE_INPUT
-#undef CLWB_ENCODING
-
- alternative_2("", "sfence", X86_FEATURE_CLFLUSHOPT,
- "sfence", X86_FEATURE_CLWB);
-}
-
/* Allocate page table, return its machine address */
uint64_t alloc_pgtable_maddr(unsigned long npages, nodeid_t node)
{
clear_page(vaddr);
if ( (iommu_ops.init ? &iommu_ops : &vtd_ops)->sync_cache )
- sync_cache(vaddr, PAGE_SIZE);
+ cache_writeback(vaddr, PAGE_SIZE);
unmap_domain_page(vaddr);
cur_pg++;
}
iommu->nr_pt_levels = agaw_to_level(agaw);
if ( !ecap_coherent(iommu->ecap) )
- vtd_ops.sync_cache = sync_cache;
+ vtd_ops.sync_cache = cache_writeback;
/* allocate domain id bitmap */
iommu->domid_bitmap = xzalloc_array(unsigned long, BITS_TO_LONGS(nr_dom));
projects / xen.git / commitdiff