+ devicetree mail list
On 10/11/18 06:22, Akshay Adiga wrote:
> From: Abhishek Goel <hunt...@linux.vnet.ibm.com>
>
> This patch moves the saving and restoring of sprs for P9 cpuidle
> from kernel to opal.
> In an attempt to make the powernv idle code backward compatible,
> and to some extent forward compatible, add support for pre-stop entry
> and post-stop exit actions in OPAL. If a kernel knows about this
> opal call, then just a firmware supporting newer hardware is required,
> instead of waiting for kernel updates.
>
> Signed-off-by: Abhishek Goel <hunt...@linux.vnet.ibm.com>
> Signed-off-by: Akshay Adiga <akshay.ad...@linux.vnet.ibm.com>
> ---
> Changes from v1 :
> - Code is rebased on Nick Piggin's v4 patch "powerpc/64s: reimplement book3s
> idle code in C"
> - Set a global variable "request_opal_call" to indicate that deep
> states should make opal_call.
> - All the states that loses hypervisor states will be handled by OPAL
> - All the decision making such as identifying first thread in
> the core and taking locks before restoring in such cases have also been
> moved to OPAL
> arch/powerpc/include/asm/opal-api.h | 4 +-
> arch/powerpc/include/asm/opal.h | 3 +
> arch/powerpc/include/asm/processor.h | 3 +-
> arch/powerpc/kernel/idle_book3s.S | 6 +-
> arch/powerpc/platforms/powernv/idle.c | 88 +++++++++++++------
> .../powerpc/platforms/powernv/opal-wrappers.S | 2 +
> 6 files changed, 77 insertions(+), 29 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/opal-api.h
> b/arch/powerpc/include/asm/opal-api.h
> index 8365353330b4..93ea1f79e295 100644
> --- a/arch/powerpc/include/asm/opal-api.h
> +++ b/arch/powerpc/include/asm/opal-api.h
> @@ -210,7 +210,9 @@
> #define OPAL_PCI_GET_PBCQ_TUNNEL_BAR 164
> #define OPAL_PCI_SET_PBCQ_TUNNEL_BAR 165
> #define OPAL_NX_COPROC_INIT 167
> -#define OPAL_LAST 167
> +#define OPAL_IDLE_SAVE 170
> +#define OPAL_IDLE_RESTORE 171
> +#define OPAL_LAST 171
>
> #define QUIESCE_HOLD 1 /* Spin all calls at entry */
> #define QUIESCE_REJECT 2 /* Fail all calls with
> OPAL_BUSY */
> diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
> index ff3866473afe..26995e16171e 100644
> --- a/arch/powerpc/include/asm/opal.h
> +++ b/arch/powerpc/include/asm/opal.h
> @@ -356,6 +356,9 @@ extern int opal_handle_hmi_exception(struct pt_regs
> *regs);
> extern void opal_shutdown(void);
> extern int opal_resync_timebase(void);
>
> +extern int opal_cpuidle_save(u64 psscr);
> +extern int opal_cpuidle_restore(u64 psscr, u64 srr1);
> +
> extern void opal_lpc_init(void);
>
> extern void opal_kmsg_init(void);
> diff --git a/arch/powerpc/include/asm/processor.h
> b/arch/powerpc/include/asm/processor.h
> index 822d3236ad7f..26fa6c1836f4 100644
> --- a/arch/powerpc/include/asm/processor.h
> +++ b/arch/powerpc/include/asm/processor.h
> @@ -510,7 +510,8 @@ static inline unsigned long get_clean_sp(unsigned long
> sp, int is_32)
>
> /* asm stubs */
> extern unsigned long isa300_idle_stop_noloss(unsigned long psscr_val);
> -extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val);
> +extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val,
> + bool request_opal_call);
> extern unsigned long isa206_idle_insn_mayloss(unsigned long type);
>
> extern unsigned long cpuidle_disable;
> diff --git a/arch/powerpc/kernel/idle_book3s.S
> b/arch/powerpc/kernel/idle_book3s.S
> index ffdee1ab4388..a2014d152035 100644
> --- a/arch/powerpc/kernel/idle_book3s.S
> +++ b/arch/powerpc/kernel/idle_book3s.S
> @@ -52,14 +52,16 @@ _GLOBAL(isa300_idle_stop_noloss)
> _GLOBAL(isa300_idle_stop_mayloss)
> mtspr SPRN_PSSCR,r3
> std r1,PACAR1(r13)
> - mflr r4
> + mflr r7
> mfcr r5
> /* use stack red zone rather than a new frame */
> addi r6,r1,-INT_FRAME_SIZE
> SAVE_GPR(2, r6)
> SAVE_NVGPRS(r6)
> - std r4,_LINK(r6)
> + std r7,_LINK(r6)
> std r5,_CCR(r6)
> + cmpwi r4,0
> + bne opal_cpuidle_save
> PPC_STOP
> b . /* catch bugs */
>
> diff --git a/arch/powerpc/platforms/powernv/idle.c
> b/arch/powerpc/platforms/powernv/idle.c
> index 681a23a066bb..bcfe08022e65 100644
> --- a/arch/powerpc/platforms/powernv/idle.c
> +++ b/arch/powerpc/platforms/powernv/idle.c
> @@ -171,6 +171,7 @@ static void pnv_fastsleep_workaround_apply(void *info)
>
> static bool power7_fastsleep_workaround_entry = true;
> static bool power7_fastsleep_workaround_exit = true;
> +static bool request_opal_call = false;
>
> /*
> * Used to store fastsleep workaround state
> @@ -604,6 +605,7 @@ static unsigned long power9_idle_stop(unsigned long
> psscr, bool mmu_on)
> unsigned long mmcr0 = 0;
> struct p9_sprs sprs;
> bool sprs_saved = false;
> + bool is_hv_loss = false;
>
> memset(&sprs, 0, sizeof(sprs));
>
> @@ -648,7 +650,9 @@ static unsigned long power9_idle_stop(unsigned long
> psscr, bool mmu_on)
> */
> mmcr0 = mfspr(SPRN_MMCR0);
> }
> - if ((psscr & PSSCR_RL_MASK) >= pnv_first_hv_loss_level) {
> +
> + is_hv_loss = (psscr & PSSCR_RL_MASK) >= pnv_first_hv_loss_level;
> + if (is_hv_loss && (!request_opal_call)) {
> sprs.lpcr = mfspr(SPRN_LPCR);
> sprs.hfscr = mfspr(SPRN_HFSCR);
> sprs.fscr = mfspr(SPRN_FSCR);
> @@ -674,7 +678,8 @@ static unsigned long power9_idle_stop(unsigned long
> psscr, bool mmu_on)
> atomic_start_thread_idle();
> }
>
> - srr1 = isa300_idle_stop_mayloss(psscr);
> + srr1 = isa300_idle_stop_mayloss(psscr,
> + is_hv_loss && request_opal_call);
>
> #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
> local_paca->requested_psscr = 0;
> @@ -685,6 +690,25 @@ static unsigned long power9_idle_stop(unsigned long
> psscr, bool mmu_on)
> WARN_ON_ONCE(!srr1);
> WARN_ON_ONCE(mfmsr() & (MSR_IR|MSR_DR));
>
> + /*
> + * On POWER9, SRR1 bits do not match exactly as expected.
> + * SRR1_WS_GPRLOSS (10b) can also result in SPR loss, so
> + * always test PSSCR if there is any state loss.
> + */
> + if (likely(((psscr & PSSCR_PLS) >> 60) < pnv_first_hv_loss_level)) {
> + if (sprs_saved)
> + atomic_stop_thread_idle();
> + goto out;
> + }
> +
> + if (request_opal_call) {
> + opal_cpuidle_restore(psscr, srr1);
> + goto opal_return;
> + }
> +
> + /* HV state loss */
> + BUG_ON(!sprs_saved);
> +
> if ((srr1 & SRR1_WAKESTATE) != SRR1_WS_NOLOSS) {
> unsigned long mmcra;
>
> @@ -712,19 +736,6 @@ static unsigned long power9_idle_stop(unsigned long
> psscr, bool mmu_on)
> if (unlikely((srr1 & SRR1_WAKEMASK_P8) == SRR1_WAKEHMI))
> hmi_exception_realmode(NULL);
>
> - /*
> - * On POWER9, SRR1 bits do not match exactly as expected.
> - * SRR1_WS_GPRLOSS (10b) can also result in SPR loss, so
> - * always test PSSCR if there is any state loss.
> - */
> - if (likely((psscr & PSSCR_RL_MASK) < pnv_first_hv_loss_level)) {
> - if (sprs_saved)
> - atomic_stop_thread_idle();
> - goto out;
> - }
> -
> - /* HV state loss */
> - BUG_ON(!sprs_saved);
>
> atomic_lock_thread_idle();
>
> @@ -771,6 +782,7 @@ static unsigned long power9_idle_stop(unsigned long
> psscr, bool mmu_on)
>
> mtspr(SPRN_SPRG3, local_paca->sprg_vdso);
>
> +opal_return:
> if (!radix_enabled())
> __slb_restore_bolted_realmode();
>
> @@ -1284,6 +1296,7 @@ static int pnv_parse_cpuidle_dt(void)
> u32 *temp_u32;
> u64 *temp_u64;
> const char **temp_string;
> + bool fall_back_to_opal = false;
>
> np = of_find_node_by_path("/ibm,opal/power-mgt");
> if (!np) {
> @@ -1396,23 +1409,48 @@ static int pnv_parse_cpuidle_dt(void)
> /* Parse each child node with appropriate parser_fn */
> for_each_child_of_node(np1, dt_node) {
> bool found_known_version = false;
> - /* we don't have state falling back to opal*/
> - for (i = 0; i < nr_known_versions ; i++) {
> - if (of_device_is_compatible(dt_node,
> known_versions[i].name)) {
> - rc = known_versions[i].parser_fn(dt_node);
> + if (!fall_back_to_opal) {
> + /* we don't have state falling back to opal*/
> + for (i = 0; i < nr_known_versions ; i++) {
> + if (of_device_is_compatible(dt_node,
> known_versions[i].name)) {
> + rc =
> known_versions[i].parser_fn(dt_node);
> + if (rc) {
> + pr_err("%s could not parse\n",
> known_versions[i].name);
> + continue;
> + }
> + found_known_version = true;
> + }
> + }
> + }
> +
> + /*
> + * If any previous state falls back to opal_call
> + * Then all futher states will either call opal_call
> + * or not be included for cpuidle/cpuoffline.
> + *
> + * Moreover, having any intermediate state with no
> + * kernel support or opal support can be potentially
> + * dangerous, as hardware can potentially wakeup from
> + * that state. Hence, no futher states are added to
> + * to cpuidle/cpuoffline
> + */
> + if (!found_known_version || fall_back_to_opal) {
> + if (of_device_is_compatible(dt_node, "opal-support")) {
> + rc = known_versions[0].parser_fn(dt_node);
> if (rc) {
> - pr_err("%s could not parse\n",
> known_versions[i].name);
> + pr_err("%s could not parse\n",
> "opal-support");
> continue;
> }
> - found_known_version = true;
> + fall_back_to_opal = true;
> + } else {
> + pr_info("Unsupported state, skipping all
> further state\n");
> + goto out;
> }
> }
> - if (!found_known_version) {
> - pr_info("Unsupported state, skipping all further
> state\n");
> - goto out;
> - }
> nr_pnv_idle_states++;
> }
> + if (fall_back_to_opal)
> + request_opal_call = true;
> out:
> kfree(temp_u32);
> kfree(temp_u64);
> diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S
> b/arch/powerpc/platforms/powernv/opal-wrappers.S
> index 251528231a9e..7a039a81a67e 100644
> --- a/arch/powerpc/platforms/powernv/opal-wrappers.S
> +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
> @@ -331,3 +331,5 @@ OPAL_CALL(opal_pci_set_pbcq_tunnel_bar,
> OPAL_PCI_SET_PBCQ_TUNNEL_BAR);
> OPAL_CALL(opal_sensor_read_u64, OPAL_SENSOR_READ_U64);
> OPAL_CALL(opal_sensor_group_enable, OPAL_SENSOR_GROUP_ENABLE);
> OPAL_CALL(opal_nx_coproc_init, OPAL_NX_COPROC_INIT);
> +OPAL_CALL(opal_cpuidle_save, OPAL_IDLE_SAVE);
> +OPAL_CALL(opal_cpuidle_restore, OPAL_IDLE_RESTORE);
>
