@@ -334,7 +334,7 @@ void check_tlb_flush(CPUPPCState *env, bool global)
if (global && (env->tlb_need_flush & TLB_NEED_GLOBAL_FLUSH)) {
env->tlb_need_flush &= ~TLB_NEED_GLOBAL_FLUSH;
env->tlb_need_flush &= ~TLB_NEED_LOCAL_FLUSH;
- tlb_flush_all_cpus(cs);
+ tlb_flush_all_cpus_synced(cs);
return;
}
@@ -534,7 +534,7 @@ void helper_tlbie_isa300(CPUPPCState *env, target_ulong rb, target_ulong rs,
if (local) {
tlb_flush_page(env_cpu(env), addr);
} else {
- tlb_flush_page_all_cpus(env_cpu(env), addr);
+ tlb_flush_page_all_cpus_synced(env_cpu(env), addr);
}
return;
@@ -3494,6 +3494,13 @@ static inline void gen_check_tlb_flush(DisasContext *ctx, bool global)
gen_helper_check_tlb_flush_local(tcg_env);
}
gen_set_label(l);
+ if (global) {
+ /*
+ * Global TLB flush uses async-work which must run before the
+ * next instruction, so this must be the last in the TB.
+ */
+ ctx->base.is_jmp = DISAS_EXIT_UPDATE;
+ }
}
#else
static inline void gen_check_tlb_flush(DisasContext *ctx, bool global) { }
@@ -224,6 +224,13 @@ static bool do_tlbie(DisasContext *ctx, arg_X_tlbie *a, bool local)
a->prs << TLBIE_F_PRS_SHIFT |
a->r << TLBIE_F_R_SHIFT |
local << TLBIE_F_LOCAL_SHIFT));
+ if (!local) {
+ /*
+ * Global TLB flush uses async-work which must run before the
+ * next instruction, so this must be the last in the TB.
+ */
+ ctx->base.is_jmp = DISAS_EXIT_UPDATE;
+ }
return true;
#endif
With mttcg, broadcast tlbie instructions do not wait until other vCPUs have been kicked out of TCG execution before they complete (including necessary subsequent tlbsync, etc., instructions). This is contrary to the ISA, and it permits other vCPUs to use translations after the TLB flush. For example: CPU0 // *memP is initially 0, memV maps to memP with *pte *pte = 0; ptesync ; tlbie ; eieio ; tlbsync ; ptesync *memP = 1; CPU1 assert(*memV == 0); It is possible for the assertion to fail because CPU1 translates memV using the TLB after CPU0 has stored 1 to the underlying memory. This race was observed with a careful test case where CPU1 checks run in a very large expensive TB so it can run for the entire CPU0 period between clearing the pte and storing the memory, but host vCPU thread preemption could cause the race to hit anywhere. As explained in commit 4ddc104689b ("target/ppc: Fix tlbie"), it is not enough to just use tlb_flush_all_cpus_synced(), because that does not execute until the calling CPU has finished its TB. It is also required that the TB is ended at the point where the TLB flush must subsequently take effect. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> --- target/ppc/helper_regs.c | 2 +- target/ppc/mmu_helper.c | 2 +- target/ppc/translate.c | 7 +++++++ target/ppc/translate/storage-ctrl-impl.c.inc | 7 +++++++ 4 files changed, 16 insertions(+), 2 deletions(-)