From mboxrd@z Thu Jan 1 00:00:00 1970 From: nicolas.pitre@linaro.org (Nicolas Pitre) Date: Mon, 22 Jul 2013 13:58:12 -0400 (EDT) Subject: [PATCH 1/4] ARM: vexpress/dcscb: fix cache disabling sequences In-Reply-To: <20130719105907.GB27389@e102568-lin.cambridge.arm.com> References: <1374118116-16836-1-git-send-email-nicolas.pitre@linaro.org> <1374118116-16836-2-git-send-email-nicolas.pitre@linaro.org> <20130718150408.GB2655@localhost.localdomain> <20130718180323.GC2655@localhost.localdomain> <20130719102844.GA3746@localhost.localdomain> <20130719105907.GB27389@e102568-lin.cambridge.arm.com> Message-ID: To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Fri, 19 Jul 2013, Lorenzo Pieralisi wrote: > On Fri, Jul 19, 2013 at 11:28:49AM +0100, Dave Martin wrote: > > On Thu, Jul 18, 2013 at 02:59:06PM -0400, Nicolas Pitre wrote: > > > On Thu, 18 Jul 2013, Dave Martin wrote: > > > > > > > I had other names in mind, like "coherency_exit" or "cache_exit". > > > > Those are not very intelligible, but that might at least make people > > > > pause and think before blindly using it. > > > > > > Good point. It should still embody the architecture name for which it > > > is valid though. > > > > Sure, I was assuming something would be pasted on the start of the name. > > v7 :-) with a comment describing the assumptions (in particular related > as Dave mentioned to the SMP bit behaviour) ? OK... What about this then: ----- >8 From: Nicolas Pitre Date: Thu, 18 Jul 2013 13:12:48 -0400 Subject: [PATCH] ARM: cacheflush: consolidate single-CPU ARMv7 cache disabling code This code is becoming duplicated in many places. So let's consolidate it into a handy macro that is known to be right and available for reuse. Signed-off-by: Nicolas Pitre diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 17d0ae8672..8f4e2297e2 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -436,4 +436,44 @@ static inline void __sync_cache_range_r(volatile void *p, size_t size) #define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr)) #define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr)) +/* + * Disabling cache access for one CPU in an ARMv7 SMP system is tricky. + * To do so we must: + * + * - Clear the SCTLR.C bit to prevent further cache allocations + * - Flush the desired level of cache + * - Clear the ACTLR "SMP" bit to disable local coherency + * + * ... and so without any intervening memory access in between those steps, + * not even to the stack. + * + * WARNING -- After this has been called: + * + * - No ldr/str exclusive must be used. + * - The CPU is obviously no longer coherent with the other CPUs. + * + * Further considerations: + * + * - This relies on the presence and behavior of the AUXCR.SMP bit as + * documented in the ARMv7 TRM. Vendor implementations that deviate from + * that will need their own procedure. + * - This is unlikely to work if Linux is running non-secure. + */ +#define v7_exit_coherency_flush(level) \ + asm volatile( \ + "mrc p15, 0, r0, c1, c0, 0 @ get CR \n\t" \ + "bic r0, r0, #"__stringify(CR_C)" \n\t" \ + "mcr p15, 0, r0, c1, c0, 0 @ set CR \n\t" \ + "isb \n\t" \ + "bl v7_flush_dcache_"__stringify(level)" \n\t" \ + "clrex \n\t" \ + "mrc p15, 0, r0, c1, c0, 1 @ get AUXCR \n\t" \ + "bic r0, r0, #(1 << 6) @ disable local coherency \n\t" \ + "mcr p15, 0, r0, c1, c0, 1 @ set AUXCR \n\t" \ + "isb \n\t" \ + "dsb " \ + /* The clobber list is dictated by the call to v7_flush_dcache_* */ \ + : : : "r0","r1","r2","r3","r4","r5","r6","r7", \ + "r9","r10","r11","lr","memory" ) + #endif diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c index 85fffa702f..14d4996887 100644 --- a/arch/arm/mach-vexpress/dcscb.c +++ b/arch/arm/mach-vexpress/dcscb.c @@ -133,32 +133,8 @@ static void dcscb_power_down(void) if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) { arch_spin_unlock(&dcscb_lock); - /* - * Flush all cache levels for this cluster. - * - * To do so we do: - * - Clear the SCTLR.C bit to prevent further cache allocations - * - Flush the whole cache - * - Clear the ACTLR "SMP" bit to disable local coherency - * - * Let's do it in the safest possible way i.e. with - * no memory access within the following sequence - * including to the stack. - */ - asm volatile( - "mrc p15, 0, r0, c1, c0, 0 @ get CR \n\t" - "bic r0, r0, #"__stringify(CR_C)" \n\t" - "mcr p15, 0, r0, c1, c0, 0 @ set CR \n\t" - "isb \n\t" - "bl v7_flush_dcache_all \n\t" - "clrex \n\t" - "mrc p15, 0, r0, c1, c0, 1 @ get AUXCR \n\t" - "bic r0, r0, #(1 << 6) @ disable local coherency \n\t" - "mcr p15, 0, r0, c1, c0, 1 @ set AUXCR \n\t" - "isb \n\t" - "dsb " - : : : "r0","r1","r2","r3","r4","r5","r6","r7", - "r9","r10","r11","lr","memory"); + /* Flush all cache levels for this cluster. */ + v7_exit_coherency_flush(all); /* * This is a harmless no-op. On platforms with a real @@ -177,24 +153,8 @@ static void dcscb_power_down(void) } else { arch_spin_unlock(&dcscb_lock); - /* - * Flush the local CPU cache. - * Let's do it in the safest possible way as above. - */ - asm volatile( - "mrc p15, 0, r0, c1, c0, 0 @ get CR \n\t" - "bic r0, r0, #"__stringify(CR_C)" \n\t" - "mcr p15, 0, r0, c1, c0, 0 @ set CR \n\t" - "isb \n\t" - "bl v7_flush_dcache_louis \n\t" - "clrex \n\t" - "mrc p15, 0, r0, c1, c0, 1 @ get AUXCR \n\t" - "bic r0, r0, #(1 << 6) @ disable local coherency \n\t" - "mcr p15, 0, r0, c1, c0, 1 @ set AUXCR \n\t" - "isb \n\t" - "dsb " - : : : "r0","r1","r2","r3","r4","r5","r6","r7", - "r9","r10","r11","lr","memory"); + /* Disable and flush the local CPU cache. */ + v7_exit_coherency_flush(louis); } __mcpm_cpu_down(cpu, cluster); diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c index dfb55d45b6..5940f1e317 100644 --- a/arch/arm/mach-vexpress/tc2_pm.c +++ b/arch/arm/mach-vexpress/tc2_pm.c @@ -134,26 +134,7 @@ static void tc2_pm_down(u64 residency) : : "r" (0x400) ); } - /* - * We need to disable and flush the whole (L1 and L2) cache. - * Let's do it in the safest possible way i.e. with - * no memory access within the following sequence - * including the stack. - */ - asm volatile( - "mrc p15, 0, r0, c1, c0, 0 @ get CR \n\t" - "bic r0, r0, #"__stringify(CR_C)" \n\t" - "mcr p15, 0, r0, c1, c0, 0 @ set CR \n\t" - "isb \n\t" - "bl v7_flush_dcache_all \n\t" - "clrex \n\t" - "mrc p15, 0, r0, c1, c0, 1 @ get AUXCR \n\t" - "bic r0, r0, #(1 << 6) @ disable local coherency \n\t" - "mcr p15, 0, r0, c1, c0, 1 @ set AUXCR \n\t" - "isb \n\t" - "dsb " - : : : "r0","r1","r2","r3","r4","r5","r6","r7", - "r9","r10","r11","lr","memory"); + v7_exit_coherency_flush(all); cci_disable_port_by_cpu(mpidr); @@ -169,24 +150,7 @@ static void tc2_pm_down(u64 residency) arch_spin_unlock(&tc2_pm_lock); - /* - * We need to disable and flush only the L1 cache. - * Let's do it in the safest possible way as above. - */ - asm volatile( - "mrc p15, 0, r0, c1, c0, 0 @ get CR \n\t" - "bic r0, r0, #"__stringify(CR_C)" \n\t" - "mcr p15, 0, r0, c1, c0, 0 @ set CR \n\t" - "isb \n\t" - "bl v7_flush_dcache_louis \n\t" - "clrex \n\t" - "mrc p15, 0, r0, c1, c0, 1 @ get AUXCR \n\t" - "bic r0, r0, #(1 << 6) @ disable local coherency \n\t" - "mcr p15, 0, r0, c1, c0, 1 @ set AUXCR \n\t" - "isb \n\t" - "dsb " - : : : "r0","r1","r2","r3","r4","r5","r6","r7", - "r9","r10","r11","lr","memory"); + v7_exit_coherency_flush(louis); } __mcpm_cpu_down(cpu, cluster);