Message ID | 1539050912-25749-2-git-send-email-rplsssn@codeaurora.org (mailing list archive) |
---|---|
State | New, archived |
Delegated to: | Andy Gross |
Headers | show |
Series | drivers/qcom: add additional functionality to RPMH | expand |
On Tue, Oct 09 2018 at 20:08 -0600, Raju P.L.S.S.S.N wrote: >tcs->lock was introduced to serialize access with in TCS group. But >even without tcs->lock, drv->lock is serving the same purpose. So >use single drv->lock. > >Other optimizations include - > - Remove locking around clear_bit() in IRQ handler. clear_bit() is > atomic. > - Remove redundant read of TCS registers. > - Use spin_lock instead of _irq variants as the locks are not held > in interrupt context > >Suggested-by: Lina Iyer <ilina@codeaurora.org> >Signed-off-by: Raju P.L.S.S.S.N <rplsssn@codeaurora.org> Reviewed-by: Lina Iyer <ilina@codeaurora.org> >--- >This patch is based on https://lkml.org/lkml/2018/10/3/422 >--- > drivers/soc/qcom/rpmh-internal.h | 2 -- > drivers/soc/qcom/rpmh-rsc.c | 37 +++++++++++++------------------------ > drivers/soc/qcom/rpmh.c | 20 ++++++++------------ > 3 files changed, 21 insertions(+), 38 deletions(-) > >diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h >index 8c316b4..2e3ffcd 100644 >--- a/drivers/soc/qcom/rpmh-internal.h >+++ b/drivers/soc/qcom/rpmh-internal.h >@@ -28,7 +28,6 @@ > * @offset: start of the TCS group relative to the TCSes in the RSC > * @num_tcs: number of TCSes in this type > * @ncpt: number of commands in each TCS >- * @lock: lock for synchronizing this TCS writes > * @req: requests that are sent from the TCS > * @cmd_cache: flattened cache of cmds in sleep/wake TCS > * @slots: indicates which of @cmd_addr are occupied >@@ -40,7 +39,6 @@ struct tcs_group { > u32 offset; > int num_tcs; > int ncpt; >- spinlock_t lock; > const struct tcs_request *req[MAX_TCS_PER_TYPE]; > u32 *cmd_cache; > DECLARE_BITMAP(slots, MAX_TCS_SLOTS); >diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c >index 73d5b98..d6b834e 100644 >--- a/drivers/soc/qcom/rpmh-rsc.c >+++ b/drivers/soc/qcom/rpmh-rsc.c >@@ -98,8 +98,7 @@ static void write_tcs_reg_sync(struct rsc_drv *drv, int reg, int tcs_id, > > static bool tcs_is_free(struct rsc_drv *drv, int tcs_id) > { >- return !test_bit(tcs_id, drv->tcs_in_use) && >- read_tcs_reg(drv, RSC_DRV_STATUS, tcs_id, 0); >+ return !test_bit(tcs_id, drv->tcs_in_use); > } > > static struct tcs_group *get_tcs_of_type(struct rsc_drv *drv, int type) >@@ -109,29 +108,28 @@ static struct tcs_group *get_tcs_of_type(struct rsc_drv *drv, int type) > > static int tcs_invalidate(struct rsc_drv *drv, int type) > { >- int m; >+ int m, ret = 0; > struct tcs_group *tcs; > > tcs = get_tcs_of_type(drv, type); > >- spin_lock(&tcs->lock); >- if (bitmap_empty(tcs->slots, MAX_TCS_SLOTS)) { >- spin_unlock(&tcs->lock); >- return 0; >- } >+ spin_lock(&drv->lock); >+ if (bitmap_empty(tcs->slots, MAX_TCS_SLOTS)) >+ goto done; > > for (m = tcs->offset; m < tcs->offset + tcs->num_tcs; m++) { > if (!tcs_is_free(drv, m)) { >- spin_unlock(&tcs->lock); >- return -EAGAIN; >+ ret = -EAGAIN; >+ goto done; > } > write_tcs_reg_sync(drv, RSC_DRV_CMD_ENABLE, m, 0); > write_tcs_reg_sync(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, m, 0); > } > bitmap_zero(tcs->slots, MAX_TCS_SLOTS); >- spin_unlock(&tcs->lock); > >- return 0; >+done: >+ spin_unlock(&drv->lock); >+ return ret; > } > > /** >@@ -298,9 +296,7 @@ static irqreturn_t tcs_tx_done(int irq, void *p) > write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, i, 0); > write_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, i, 0); > write_tcs_reg(drv, RSC_DRV_IRQ_CLEAR, 0, BIT(i)); >- spin_lock(&drv->lock); > clear_bit(i, drv->tcs_in_use); >- spin_unlock(&drv->lock); > if (req) > rpmh_tx_done(req, err); > } >@@ -383,14 +379,12 @@ static int tcs_write(struct rsc_drv *drv, const struct tcs_request *msg) > { > struct tcs_group *tcs; > int tcs_id; >- unsigned long flags; > int ret; > > tcs = get_tcs_for_msg(drv, msg); > if (IS_ERR(tcs)) > return PTR_ERR(tcs); > >- spin_lock_irqsave(&tcs->lock, flags); > spin_lock(&drv->lock); > /* > * The h/w does not like if we send a request to the same address, >@@ -398,14 +392,12 @@ static int tcs_write(struct rsc_drv *drv, const struct tcs_request *msg) > */ > ret = check_for_req_inflight(drv, tcs, msg); > if (ret) { >- spin_unlock(&drv->lock); > goto done_write; > } > > tcs_id = find_free_tcs(tcs); > if (tcs_id < 0) { > ret = tcs_id; >- spin_unlock(&drv->lock); > goto done_write; > } > >@@ -413,13 +405,12 @@ static int tcs_write(struct rsc_drv *drv, const struct tcs_request *msg) > set_bit(tcs_id, drv->tcs_in_use); > if (msg->state == RPMH_ACTIVE_ONLY_STATE && tcs->type != ACTIVE_TCS) > enable_tcs_irq(drv, tcs_id, true); >- spin_unlock(&drv->lock); > > __tcs_buffer_write(drv, tcs_id, 0, msg); > __tcs_trigger(drv, tcs_id, true); > > done_write: >- spin_unlock_irqrestore(&tcs->lock, flags); >+ spin_unlock(&drv->lock); > return ret; > } > >@@ -517,19 +508,18 @@ static int tcs_ctrl_write(struct rsc_drv *drv, const struct tcs_request *msg) > { > struct tcs_group *tcs; > int tcs_id = 0, cmd_id = 0; >- unsigned long flags; > int ret; > > tcs = get_tcs_for_msg(drv, msg); > if (IS_ERR(tcs)) > return PTR_ERR(tcs); > >- spin_lock_irqsave(&tcs->lock, flags); >+ spin_lock(&drv->lock); > /* find the TCS id and the command in the TCS to write to */ > ret = find_slots(tcs, msg, &tcs_id, &cmd_id); > if (!ret) > __tcs_buffer_write(drv, tcs_id, cmd_id, msg); >- spin_unlock_irqrestore(&tcs->lock, flags); >+ spin_unlock(&drv->lock); > > return ret; > } >@@ -638,7 +628,6 @@ static int rpmh_probe_tcs_config(struct platform_device *pdev, > tcs->type = tcs_cfg[i].type; > tcs->num_tcs = tcs_cfg[i].n; > tcs->ncpt = ncpt; >- spin_lock_init(&tcs->lock); > > if (!tcs->num_tcs || tcs->type == CONTROL_TCS) > continue; >diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c >index 71a76ea..297d6cc 100644 >--- a/drivers/soc/qcom/rpmh.c >+++ b/drivers/soc/qcom/rpmh.c >@@ -117,9 +117,8 @@ static struct cache_req *cache_rpm_request(struct rpmh_ctrlr *ctrlr, > struct tcs_cmd *cmd) > { > struct cache_req *req; >- unsigned long flags; > >- spin_lock_irqsave(&ctrlr->cache_lock, flags); >+ spin_lock(&ctrlr->cache_lock); > req = __find_req(ctrlr, cmd->addr); > if (req) > goto existing; >@@ -153,7 +152,7 @@ static struct cache_req *cache_rpm_request(struct rpmh_ctrlr *ctrlr, > > ctrlr->dirty = true; > unlock: >- spin_unlock_irqrestore(&ctrlr->cache_lock, flags); >+ spin_unlock(&ctrlr->cache_lock); > > return req; > } >@@ -283,23 +282,21 @@ int rpmh_write(const struct device *dev, enum rpmh_state state, > > static void cache_batch(struct rpmh_ctrlr *ctrlr, struct batch_cache_req *req) > { >- unsigned long flags; > >- spin_lock_irqsave(&ctrlr->cache_lock, flags); >+ spin_lock(&ctrlr->cache_lock); > list_add_tail(&req->list, &ctrlr->batch_cache); >- spin_unlock_irqrestore(&ctrlr->cache_lock, flags); >+ spin_unlock(&ctrlr->cache_lock); > } > > static int flush_batch(struct rpmh_ctrlr *ctrlr) > { > struct batch_cache_req *req; > const struct rpmh_request *rpm_msg; >- unsigned long flags; > int ret = 0; > int i; > > /* Send Sleep/Wake requests to the controller, expect no response */ >- spin_lock_irqsave(&ctrlr->cache_lock, flags); >+ spin_lock(&ctrlr->cache_lock); > list_for_each_entry(req, &ctrlr->batch_cache, list) { > for (i = 0; i < req->count; i++) { > rpm_msg = req->rpm_msgs + i; >@@ -309,7 +306,7 @@ static int flush_batch(struct rpmh_ctrlr *ctrlr) > break; > } > } >- spin_unlock_irqrestore(&ctrlr->cache_lock, flags); >+ spin_unlock(&ctrlr->cache_lock); > > return ret; > } >@@ -317,13 +314,12 @@ static int flush_batch(struct rpmh_ctrlr *ctrlr) > static void invalidate_batch(struct rpmh_ctrlr *ctrlr) > { > struct batch_cache_req *req, *tmp; >- unsigned long flags; > >- spin_lock_irqsave(&ctrlr->cache_lock, flags); >+ spin_lock(&ctrlr->cache_lock); > list_for_each_entry_safe(req, tmp, &ctrlr->batch_cache, list) > kfree(req); > INIT_LIST_HEAD(&ctrlr->batch_cache); >- spin_unlock_irqrestore(&ctrlr->cache_lock, flags); >+ spin_unlock(&ctrlr->cache_lock); > } > > /** >-- >QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member >of the Code Aurora Forum, hosted by The Linux Foundation. >
diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h index 8c316b4..2e3ffcd 100644 --- a/drivers/soc/qcom/rpmh-internal.h +++ b/drivers/soc/qcom/rpmh-internal.h @@ -28,7 +28,6 @@ * @offset: start of the TCS group relative to the TCSes in the RSC * @num_tcs: number of TCSes in this type * @ncpt: number of commands in each TCS - * @lock: lock for synchronizing this TCS writes * @req: requests that are sent from the TCS * @cmd_cache: flattened cache of cmds in sleep/wake TCS * @slots: indicates which of @cmd_addr are occupied @@ -40,7 +39,6 @@ struct tcs_group { u32 offset; int num_tcs; int ncpt; - spinlock_t lock; const struct tcs_request *req[MAX_TCS_PER_TYPE]; u32 *cmd_cache; DECLARE_BITMAP(slots, MAX_TCS_SLOTS); diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c index 73d5b98..d6b834e 100644 --- a/drivers/soc/qcom/rpmh-rsc.c +++ b/drivers/soc/qcom/rpmh-rsc.c @@ -98,8 +98,7 @@ static void write_tcs_reg_sync(struct rsc_drv *drv, int reg, int tcs_id, static bool tcs_is_free(struct rsc_drv *drv, int tcs_id) { - return !test_bit(tcs_id, drv->tcs_in_use) && - read_tcs_reg(drv, RSC_DRV_STATUS, tcs_id, 0); + return !test_bit(tcs_id, drv->tcs_in_use); } static struct tcs_group *get_tcs_of_type(struct rsc_drv *drv, int type) @@ -109,29 +108,28 @@ static struct tcs_group *get_tcs_of_type(struct rsc_drv *drv, int type) static int tcs_invalidate(struct rsc_drv *drv, int type) { - int m; + int m, ret = 0; struct tcs_group *tcs; tcs = get_tcs_of_type(drv, type); - spin_lock(&tcs->lock); - if (bitmap_empty(tcs->slots, MAX_TCS_SLOTS)) { - spin_unlock(&tcs->lock); - return 0; - } + spin_lock(&drv->lock); + if (bitmap_empty(tcs->slots, MAX_TCS_SLOTS)) + goto done; for (m = tcs->offset; m < tcs->offset + tcs->num_tcs; m++) { if (!tcs_is_free(drv, m)) { - spin_unlock(&tcs->lock); - return -EAGAIN; + ret = -EAGAIN; + goto done; } write_tcs_reg_sync(drv, RSC_DRV_CMD_ENABLE, m, 0); write_tcs_reg_sync(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, m, 0); } bitmap_zero(tcs->slots, MAX_TCS_SLOTS); - spin_unlock(&tcs->lock); - return 0; +done: + spin_unlock(&drv->lock); + return ret; } /** @@ -298,9 +296,7 @@ static irqreturn_t tcs_tx_done(int irq, void *p) write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, i, 0); write_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, i, 0); write_tcs_reg(drv, RSC_DRV_IRQ_CLEAR, 0, BIT(i)); - spin_lock(&drv->lock); clear_bit(i, drv->tcs_in_use); - spin_unlock(&drv->lock); if (req) rpmh_tx_done(req, err); } @@ -383,14 +379,12 @@ static int tcs_write(struct rsc_drv *drv, const struct tcs_request *msg) { struct tcs_group *tcs; int tcs_id; - unsigned long flags; int ret; tcs = get_tcs_for_msg(drv, msg); if (IS_ERR(tcs)) return PTR_ERR(tcs); - spin_lock_irqsave(&tcs->lock, flags); spin_lock(&drv->lock); /* * The h/w does not like if we send a request to the same address, @@ -398,14 +392,12 @@ static int tcs_write(struct rsc_drv *drv, const struct tcs_request *msg) */ ret = check_for_req_inflight(drv, tcs, msg); if (ret) { - spin_unlock(&drv->lock); goto done_write; } tcs_id = find_free_tcs(tcs); if (tcs_id < 0) { ret = tcs_id; - spin_unlock(&drv->lock); goto done_write; } @@ -413,13 +405,12 @@ static int tcs_write(struct rsc_drv *drv, const struct tcs_request *msg) set_bit(tcs_id, drv->tcs_in_use); if (msg->state == RPMH_ACTIVE_ONLY_STATE && tcs->type != ACTIVE_TCS) enable_tcs_irq(drv, tcs_id, true); - spin_unlock(&drv->lock); __tcs_buffer_write(drv, tcs_id, 0, msg); __tcs_trigger(drv, tcs_id, true); done_write: - spin_unlock_irqrestore(&tcs->lock, flags); + spin_unlock(&drv->lock); return ret; } @@ -517,19 +508,18 @@ static int tcs_ctrl_write(struct rsc_drv *drv, const struct tcs_request *msg) { struct tcs_group *tcs; int tcs_id = 0, cmd_id = 0; - unsigned long flags; int ret; tcs = get_tcs_for_msg(drv, msg); if (IS_ERR(tcs)) return PTR_ERR(tcs); - spin_lock_irqsave(&tcs->lock, flags); + spin_lock(&drv->lock); /* find the TCS id and the command in the TCS to write to */ ret = find_slots(tcs, msg, &tcs_id, &cmd_id); if (!ret) __tcs_buffer_write(drv, tcs_id, cmd_id, msg); - spin_unlock_irqrestore(&tcs->lock, flags); + spin_unlock(&drv->lock); return ret; } @@ -638,7 +628,6 @@ static int rpmh_probe_tcs_config(struct platform_device *pdev, tcs->type = tcs_cfg[i].type; tcs->num_tcs = tcs_cfg[i].n; tcs->ncpt = ncpt; - spin_lock_init(&tcs->lock); if (!tcs->num_tcs || tcs->type == CONTROL_TCS) continue; diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c index 71a76ea..297d6cc 100644 --- a/drivers/soc/qcom/rpmh.c +++ b/drivers/soc/qcom/rpmh.c @@ -117,9 +117,8 @@ static struct cache_req *cache_rpm_request(struct rpmh_ctrlr *ctrlr, struct tcs_cmd *cmd) { struct cache_req *req; - unsigned long flags; - spin_lock_irqsave(&ctrlr->cache_lock, flags); + spin_lock(&ctrlr->cache_lock); req = __find_req(ctrlr, cmd->addr); if (req) goto existing; @@ -153,7 +152,7 @@ static struct cache_req *cache_rpm_request(struct rpmh_ctrlr *ctrlr, ctrlr->dirty = true; unlock: - spin_unlock_irqrestore(&ctrlr->cache_lock, flags); + spin_unlock(&ctrlr->cache_lock); return req; } @@ -283,23 +282,21 @@ int rpmh_write(const struct device *dev, enum rpmh_state state, static void cache_batch(struct rpmh_ctrlr *ctrlr, struct batch_cache_req *req) { - unsigned long flags; - spin_lock_irqsave(&ctrlr->cache_lock, flags); + spin_lock(&ctrlr->cache_lock); list_add_tail(&req->list, &ctrlr->batch_cache); - spin_unlock_irqrestore(&ctrlr->cache_lock, flags); + spin_unlock(&ctrlr->cache_lock); } static int flush_batch(struct rpmh_ctrlr *ctrlr) { struct batch_cache_req *req; const struct rpmh_request *rpm_msg; - unsigned long flags; int ret = 0; int i; /* Send Sleep/Wake requests to the controller, expect no response */ - spin_lock_irqsave(&ctrlr->cache_lock, flags); + spin_lock(&ctrlr->cache_lock); list_for_each_entry(req, &ctrlr->batch_cache, list) { for (i = 0; i < req->count; i++) { rpm_msg = req->rpm_msgs + i; @@ -309,7 +306,7 @@ static int flush_batch(struct rpmh_ctrlr *ctrlr) break; } } - spin_unlock_irqrestore(&ctrlr->cache_lock, flags); + spin_unlock(&ctrlr->cache_lock); return ret; } @@ -317,13 +314,12 @@ static int flush_batch(struct rpmh_ctrlr *ctrlr) static void invalidate_batch(struct rpmh_ctrlr *ctrlr) { struct batch_cache_req *req, *tmp; - unsigned long flags; - spin_lock_irqsave(&ctrlr->cache_lock, flags); + spin_lock(&ctrlr->cache_lock); list_for_each_entry_safe(req, tmp, &ctrlr->batch_cache, list) kfree(req); INIT_LIST_HEAD(&ctrlr->batch_cache); - spin_unlock_irqrestore(&ctrlr->cache_lock, flags); + spin_unlock(&ctrlr->cache_lock); } /**
tcs->lock was introduced to serialize access with in TCS group. But even without tcs->lock, drv->lock is serving the same purpose. So use single drv->lock. Other optimizations include - - Remove locking around clear_bit() in IRQ handler. clear_bit() is atomic. - Remove redundant read of TCS registers. - Use spin_lock instead of _irq variants as the locks are not held in interrupt context Suggested-by: Lina Iyer <ilina@codeaurora.org> Signed-off-by: Raju P.L.S.S.S.N <rplsssn@codeaurora.org> --- This patch is based on https://lkml.org/lkml/2018/10/3/422 --- drivers/soc/qcom/rpmh-internal.h | 2 -- drivers/soc/qcom/rpmh-rsc.c | 37 +++++++++++++------------------------ drivers/soc/qcom/rpmh.c | 20 ++++++++------------ 3 files changed, 21 insertions(+), 38 deletions(-)