On POWER9, under some circumstances, a broadcast TLB invalidation
might complete before all previous stores have drained, potentially
allowing stale stores from becoming visible after the invalidation.
This works around it by doubling up those TLB invalidations which was
verified by HW to be sufficient to close the risk window.
This will be documented in a yet-to-be-published errata.
Fixes:
1a472c9dba6b ("powerpc/mm/radix: Add tlbflush routines")
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[mpe: Enable the feature in the DT CPU features code for all Power9,
rename the feature to CPU_FTR_P9_TLBIE_BUG per benh.]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
#define CPU_FTR_DAWR LONG_ASM_CONST(0x0400000000000000)
#define CPU_FTR_DABRX LONG_ASM_CONST(0x0800000000000000)
#define CPU_FTR_PMAO_BUG LONG_ASM_CONST(0x1000000000000000)
+#define CPU_FTR_P9_TLBIE_BUG LONG_ASM_CONST(0x2000000000000000)
#define CPU_FTR_POWER9_DD1 LONG_ASM_CONST(0x4000000000000000)
#define CPU_FTR_POWER9_DD2_1 LONG_ASM_CONST(0x8000000000000000)
CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | \
- CPU_FTR_PKEY)
+ CPU_FTR_PKEY | CPU_FTR_P9_TLBIE_BUG)
#define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \
(~CPU_FTR_SAO))
#define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9
cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1;
else if ((version & 0xffffefff) == 0x004e0201)
cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
+
+ if ((version & 0xffff0000) == 0x004e0000)
+ cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_BUG;
}
static void __init cpufeatures_setup_finished(void)
asm volatile("ptesync": : :"memory");
asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
: : "r" (addr), "r" (kvm->arch.lpid) : "memory");
+ if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG))
+ asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1)
+ : : "r" (addr), "r" (kvm->arch.lpid) : "memory");
asm volatile("ptesync": : :"memory");
}
trace_tlbie(kvm->arch.lpid, 0, rbvalues[i],
kvm->arch.lpid, 0, 0, 0);
}
+
+ if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+ /*
+ * Need the extra ptesync to make sure we don't
+ * re-order the tlbie
+ */
+ asm volatile("ptesync": : :"memory");
+ asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : :
+ "r" (rbvalues[0]), "r" (kvm->arch.lpid));
+ }
+
asm volatile("eieio; tlbsync; ptesync" : : : "memory");
kvm->arch.tlbie_lock = 0;
} else {
return va;
}
+static inline void fixup_tlbie(unsigned long vpn, int psize, int apsize, int ssize)
+{
+ if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+ /* Need the extra ptesync to ensure we don't reorder tlbie*/
+ asm volatile("ptesync": : :"memory");
+ ___tlbie(vpn, psize, apsize, ssize);
+ }
+}
+
static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
{
unsigned long rb;
asm volatile("ptesync": : :"memory");
} else {
__tlbie(vpn, psize, apsize, ssize);
+ fixup_tlbie(vpn, psize, apsize, ssize);
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
if (lock_tlbie && !use_local)
*/
static void native_flush_hash_range(unsigned long number, int local)
{
- unsigned long vpn;
+ unsigned long vpn = 0;
unsigned long hash, index, hidx, shift, slot;
struct hash_pte *hptep;
unsigned long hpte_v;
__tlbie(vpn, psize, psize, ssize);
} pte_iterate_hashed_end();
}
+ /*
+ * Just do one more with the last used values.
+ */
+ fixup_tlbie(vpn, psize, psize, ssize);
asm volatile("eieio; tlbsync; ptesync":::"memory");
if (lock_tlbie)
"r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0);
}
+ /* do we need fixup here ?*/
asm volatile("eieio; tlbsync; ptesync" : : : "memory");
}
EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);
trace_tlbie(0, 0, rb, rs, ric, prs, r);
}
+static inline void fixup_tlbie(void)
+{
+ unsigned long pid = 0;
+ unsigned long va = ((1UL << 52) - 1);
+
+ if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
+ asm volatile("ptesync": : :"memory");
+ __tlbie_va(va, pid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB);
+ }
+}
+
/*
* We use 128 set in radix mode and 256 set in hpt mode.
*/
default:
__tlbie_pid(pid, RIC_FLUSH_ALL);
}
+ fixup_tlbie();
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
asm volatile("ptesync": : :"memory");
__tlbie_va(va, pid, ap, ric);
+ fixup_tlbie();
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
if (also_pwc)
__tlbie_pid(pid, RIC_FLUSH_PWC);
__tlbie_va_range(start, end, pid, page_size, psize);
+ fixup_tlbie();
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
if (hflush)
__tlbie_va_range(hstart, hend, pid,
HPAGE_PMD_SIZE, MMU_PAGE_2M);
+ fixup_tlbie();
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
}