ldr r4, =boot_httbr /* VA of HTTBR value stashed by CPU 0 */
add r4, r4, r10 /* PA of it */
ldrd r4, r5, [r4] /* Actual value */
+ dsb
mcrr CP64(r4, r5, HTTBR)
+ dsb
+ isb
mcr CP32(r0, TLBIALLH) /* Flush hypervisor TLB */
+ mcr CP32(r0, ICIALLU) /* Flush I-cache */
mcr CP32(r0, BPIALL) /* Flush branch predictor */
dsb /* Ensure completion of TLB+BP flush */
isb
teq r2, #0
bne 1b
dsb
+ mcr CP32(r0, DCCMVAC) /* flush D-Cache */
+ dsb
/* Here, the non-boot CPUs must wait again -- they're now running on
* the boot CPU's pagetables so it's safe for the boot CPU to
/* Change pagetables to the copy in the relocated Xen */
boot_httbr = (unsigned long) xen_pgtable + phys_offset;
- asm volatile (
- STORE_CP64(0, HTTBR) /* Change translation base */
- "dsb;" /* Ensure visibility of HTTBR update */
- STORE_CP32(0, TLBIALLH) /* Flush hypervisor TLB */
- STORE_CP32(0, BPIALL) /* Flush branch predictor */
- "dsb;" /* Ensure completion of TLB+BP flush */
- "isb;"
- : : "r" (boot_httbr) : "memory");
+ flush_xen_dcache_va(&boot_httbr);
+ flush_xen_dcache_va_range((void*)dest_va, _end - _start);
+ flush_xen_text_tlb();
+
+ WRITE_CP64(boot_httbr, HTTBR); /* Change translation base */
+ dsb(); /* Ensure visibility of HTTBR update */
+ flush_xen_text_tlb();
/* Undo the temporary map */
pte.bits = 0;
>> PAGE_SHIFT);
pte.pt.table = 1;
write_pte(xen_second + second_linear_offset(XEN_VIRT_START), pte);
- /* Have changed a mapping used for .text. Flush everything for safety. */
- flush_xen_text_tlb();
+ /* TLBFLUSH and ISB would be needed here, but wait until we set WXN */
/* From now on, no mapping may be both writable and executable. */
WRITE_CP32(READ_CP32(HSCTLR) | SCTLR_WXN, HSCTLR);
+ /* Flush everything after setting WXN bit. */
+ flush_xen_text_tlb();
}
/* MMU setup for secondary CPUS (which already have paging enabled) */
{
/* From now on, no mapping may be both writable and executable. */
WRITE_CP32(READ_CP32(HSCTLR) | SCTLR_WXN, HSCTLR);
+ flush_xen_text_tlb();
}
/* Create Xen's mappings of memory.
/* Tell the next CPU to get ready */
/* TODO: handle boards where CPUIDs are not contiguous */
*gate = i;
+ flush_xen_dcache_va(gate);
asm volatile("dsb; isb; sev");
/* And wait for it to respond */
while ( ready_cpus < i )
/* Unblock the CPU. It should be waiting in the loop in head.S
* for an event to arrive when smp_up_cpu matches its cpuid. */
smp_up_cpu = cpu;
+ /* we need to make sure that the change to smp_up_cpu is visible to
+ * secondary cpus with D-cache off */
+ flush_xen_dcache_va(&smp_up_cpu);
asm volatile("dsb; isb; sev");
while ( !cpu_online(cpu) )
return e;
}
-/* Write a pagetable entry */
+/* Write a pagetable entry.
+ *
+ * If the table entry is changing a text mapping, it is responsibility
+ * of the caller to issue an ISB after write_pte.
+ */
static inline void write_pte(lpae_t *p, lpae_t pte)
{
asm volatile (
+ /* Ensure any writes have completed with the old mappings. */
+ "dsb;"
/* Safely write the entry (STRD is atomic on CPUs that support LPAE) */
"strd %0, %H0, [%1];"
+ "dsb;"
/* Push this cacheline to the PoC so the rest of the system sees it. */
STORE_CP32(1, DCCMVAC)
+ /* Ensure that the data flush is completed before proceeding */
+ "dsb;"
: : "r" (pte.bits), "r" (p) : "memory");
}
+
+/* Function for flushing medium-sized areas.
+ * if 'range' is large enough we might want to use model-specific
+ * full-cache flushes. */
+static inline void flush_xen_dcache_va_range(void *p, unsigned long size)
+{
+ int cacheline_bytes = READ_CP32(CCSIDR);
+ void *end;
+ dsb(); /* So the CPU issues all writes to the range */
+ for ( end = p + size; p < end; p += cacheline_bytes )
+ WRITE_CP32((uint32_t) p, DCCMVAC);
+ dsb(); /* So we know the flushes happen before continuing */
+}
+
+
+/* Macro for flushing a single small item. The predicate is always
+ * compile-time constant so this will compile down to 3 instructions in
+ * the common case. Make sure to call it with the correct type of
+ * pointer! */
+#define flush_xen_dcache_va(p) do { \
+ int cacheline_bytes = READ_CP32(CCSIDR); \
+ typeof(p) _p = (p); \
+ if ( ((unsigned long)_p & ~(cacheline_bytes - 1)) != \
+ (((unsigned long)_p + (sizeof *_p)) & ~(cacheline_bytes - 1)) ) \
+ flush_xen_dcache_va_range(_p, sizeof *_p); \
+ else \
+ asm volatile ( \
+ "dsb;" /* Finish all earlier writes */ \
+ STORE_CP32(0, DCCMVAC) \
+ "dsb;" /* Finish flush before continuing */ \
+ : : "r" (_p), "m" (*_p)); \
+} while (0)
+
+
/*
* Flush all hypervisor mappings from the TLB and branch predictor.
- * This is needed after changing Xen code mappings.
+ * This is needed after changing Xen code mappings.
+ *
+ * The caller needs to issue the necessary DSB and D-cache flushes
+ * before calling flush_xen_text_tlb.
*/
static inline void flush_xen_text_tlb(void)
{
register unsigned long r0 asm ("r0");
asm volatile (
- "dsb;" /* Ensure visibility of PTE writes */
+ "isb;" /* Ensure synchronization with previous changes to text */
STORE_CP32(0, TLBIALLH) /* Flush hypervisor TLB */
+ STORE_CP32(0, ICIALLU) /* Flush I-cache */
STORE_CP32(0, BPIALL) /* Flush branch predictor */
"dsb;" /* Ensure completion of TLB+BP flush */
"isb;"