diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c
index 9dd1352..bb041a2 100644
--- a/arch/mips/mm/c-r3k.c
+++ b/arch/mips/mm/c-r3k.c
@@ -260,6 +260,10 @@
 {
 }
 
+static void local_r3k_flush_data_cache_page(unsigned long addr)
+{
+}
+
 static void r3k_flush_data_cache_page(unsigned long addr)
 {
 }
@@ -335,6 +339,7 @@
 	flush_icache_range = r3k_flush_icache_range;
 
 	flush_cache_sigtramp = r3k_flush_cache_sigtramp;
+	local_flush_data_cache_page = local_r3k_flush_data_cache_page;
 	flush_data_cache_page = r3k_flush_data_cache_page;
 
 	_dma_cache_wback_inv = r3k_dma_cache_wback_inv;
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index c4c2084..d88c668 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1199,6 +1199,7 @@
 
 	flush_cache_sigtramp	= r4k_flush_cache_sigtramp;
 	flush_icache_all	= r4k_flush_icache_all;
+	local_flush_data_cache_page	= local_r4k_flush_data_cache_page;
 	flush_data_cache_page	= r4k_flush_data_cache_page;
 	flush_icache_range	= r4k_flush_icache_range;
 
diff --git a/arch/mips/mm/c-sb1.c b/arch/mips/mm/c-sb1.c
index 2f08b53..f9b1294 100644
--- a/arch/mips/mm/c-sb1.c
+++ b/arch/mips/mm/c-sb1.c
@@ -528,6 +528,7 @@
 	flush_cache_page = sb1_flush_cache_page;
 
 	flush_cache_sigtramp = sb1_flush_cache_sigtramp;
+	local_flush_data_cache_page = (void *) sb1_nop;
 	flush_data_cache_page = (void *) sb1_nop;
 
 	/* Full flush */
diff --git a/arch/mips/mm/c-tx39.c b/arch/mips/mm/c-tx39.c
index fe232e3..5dfc9b1 100644
--- a/arch/mips/mm/c-tx39.c
+++ b/arch/mips/mm/c-tx39.c
@@ -216,6 +216,11 @@
 		tx39_blast_icache_page_indexed(page);
 }
 
+static void local_tx39_flush_data_cache_page(void * addr)
+{
+	tx39_blast_dcache_page(addr);
+}
+
 static void tx39_flush_data_cache_page(unsigned long addr)
 {
 	tx39_blast_dcache_page(addr);
@@ -381,6 +386,7 @@
 		flush_icache_range	= (void *) tx39h_flush_icache_all;
 
 		flush_cache_sigtramp	= (void *) tx39h_flush_icache_all;
+		local_flush_data_cache_page	= (void *) tx39h_flush_icache_all;
 		flush_data_cache_page	= (void *) tx39h_flush_icache_all;
 
 		_dma_cache_wback_inv	= tx39h_dma_cache_wback_inv;
@@ -406,6 +412,7 @@
 		flush_icache_range = tx39_flush_icache_range;
 
 		flush_cache_sigtramp = tx39_flush_cache_sigtramp;
+		local_flush_data_cache_page = local_tx39_flush_data_cache_page;
 		flush_data_cache_page = tx39_flush_data_cache_page;
 
 		_dma_cache_wback_inv = tx39_dma_cache_wback_inv;
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index 591c22b..83a5629 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -30,6 +30,7 @@
 
 /* MIPS specific cache operations */
 void (*flush_cache_sigtramp)(unsigned long addr);
+void (*local_flush_data_cache_page)(void * addr);
 void (*flush_data_cache_page)(unsigned long addr);
 void (*flush_icache_all)(void);
 
diff --git a/include/asm-mips/cacheflush.h b/include/asm-mips/cacheflush.h
index aeae9fa..47bc8f6 100644
--- a/include/asm-mips/cacheflush.h
+++ b/include/asm-mips/cacheflush.h
@@ -74,6 +74,7 @@
 
 extern void (*flush_cache_sigtramp)(unsigned long addr);
 extern void (*flush_icache_all)(void);
+extern void (*local_flush_data_cache_page)(void * addr);
 extern void (*flush_data_cache_page)(unsigned long addr);
 
 /*
diff --git a/include/asm-mips/mach-generic/ide.h b/include/asm-mips/mach-generic/ide.h
index 550979a..e331535 100644
--- a/include/asm-mips/mach-generic/ide.h
+++ b/include/asm-mips/mach-generic/ide.h
@@ -104,65 +104,107 @@
 #endif
 
 /* MIPS port and memory-mapped I/O string operations.  */
+static inline void __ide_flush_prologue(void)
+{
+#ifdef CONFIG_SMP
+	if (cpu_has_dc_aliases)
+		preempt_disable();
+#endif
+}
+
+static inline void __ide_flush_epilogue(void)
+{
+#ifdef CONFIG_SMP
+	if (cpu_has_dc_aliases)
+		preempt_enable();
+#endif
+}
 
 static inline void __ide_flush_dcache_range(unsigned long addr, unsigned long size)
 {
 	if (cpu_has_dc_aliases) {
 		unsigned long end = addr + size;
-		for (; addr < end; addr += PAGE_SIZE)
-			flush_dcache_page(virt_to_page(addr));
+
+		while (addr < end) {
+			local_flush_data_cache_page((void *)addr);
+			addr += PAGE_SIZE;
+		}
 	}
 }
 
+/*
+ * insw() and gang might be called with interrupts disabled, so we can't
+ * send IPIs for flushing due to the potencial of deadlocks, see the comment
+ * above smp_call_function() in arch/mips/kernel/smp.c.  We work around the
+ * problem by disabling preemption so we know we actually perform the flush
+ * on the processor that actually has the lines to be flushed which hopefully
+ * is even better for performance anyway.
+ */
 static inline void __ide_insw(unsigned long port, void *addr,
 	unsigned int count)
 {
+	__ide_flush_prologue();
 	insw(port, addr, count);
 	__ide_flush_dcache_range((unsigned long)addr, count * 2);
+	__ide_flush_epilogue();
 }
 
 static inline void __ide_insl(unsigned long port, void *addr, unsigned int count)
 {
+	__ide_flush_prologue();
 	insl(port, addr, count);
 	__ide_flush_dcache_range((unsigned long)addr, count * 4);
+	__ide_flush_epilogue();
 }
 
 static inline void __ide_outsw(unsigned long port, const void *addr,
 	unsigned long count)
 {
+	__ide_flush_prologue();
 	outsw(port, addr, count);
 	__ide_flush_dcache_range((unsigned long)addr, count * 2);
+	__ide_flush_epilogue();
 }
 
 static inline void __ide_outsl(unsigned long port, const void *addr,
 	unsigned long count)
 {
+	__ide_flush_prologue();
 	outsl(port, addr, count);
 	__ide_flush_dcache_range((unsigned long)addr, count * 4);
+	__ide_flush_epilogue();
 }
 
 static inline void __ide_mm_insw(void __iomem *port, void *addr, u32 count)
 {
+	__ide_flush_prologue();
 	readsw(port, addr, count);
 	__ide_flush_dcache_range((unsigned long)addr, count * 2);
+	__ide_flush_epilogue();
 }
 
 static inline void __ide_mm_insl(void __iomem *port, void *addr, u32 count)
 {
+	__ide_flush_prologue();
 	readsl(port, addr, count);
 	__ide_flush_dcache_range((unsigned long)addr, count * 4);
+	__ide_flush_epilogue();
 }
 
 static inline void __ide_mm_outsw(void __iomem *port, void *addr, u32 count)
 {
+	__ide_flush_prologue();
 	writesw(port, addr, count);
 	__ide_flush_dcache_range((unsigned long)addr, count * 2);
+	__ide_flush_epilogue();
 }
 
 static inline void __ide_mm_outsl(void __iomem * port, void *addr, u32 count)
 {
+	__ide_flush_prologue();
 	writesl(port, addr, count);
 	__ide_flush_dcache_range((unsigned long)addr, count * 4);
+	__ide_flush_epilogue();
 }
 
 /* ide_insw calls insw, not __ide_insw.  Why? */