[v3] spmi: mtk-pmif: Serialize PMIF status check and command submission
Commit Message
Before writing the read or write command to the SPMI arbiter through the
PMIF interface, the current status of the channel is checked to ensure
it is idle. However, since the status only changes from idle when the
command is written, it is possible for two concurrent calls to determine
that the channel is idle and simultaneously send their commands. At this
point the PMIF interface hangs, with the status register no longer being
updated, and thus causing all subsequent operations to time out.
This was observed on the mt8195-cherry-tomato-r2 machine, particularly
after commit 46600ab142f8 ("regulator: Set PROBE_PREFER_ASYNCHRONOUS for
drivers between 5.10 and 5.15") was applied, since then the two MT6315
devices present on the SPMI bus would probe assynchronously and
sometimes (during probe or at a later point) read the bus
simultaneously, breaking the PMIF interface and consequently slowing
down the whole system.
To fix the issue at its root cause, introduce locking around the channel
status check and the command write, so that both become an atomic
operation, preventing race conditions between two (or more) SPMI bus
read/write operations. A spinlock is used since this is a fast bus, as
indicated by the usage of the atomic variant of readl_poll, and
'.fast_io = true' being used in the mt6315 driver, so spinlocks are
already used for the regmap access.
Fixes: b45b3ccef8c0 ("spmi: mediatek: Add support for MT6873/8192")
Signed-off-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
---
Changes in v3:
- Switched to raw spinlock to avoid overhead in PREEMPT_RT
- Moved spin_unlock to after marking the channel ready on the error
paths
Changes in v2:
- Added missing spin_unlocks to error paths
- Moved memcpy outside spinlock region in the write_cmd function
- Reworded commit message to make clear that issue can happen at any
point in runtime, not only during boot
drivers/spmi/spmi-mtk-pmif.c | 20 ++++++++++++++++----
1 file changed, 16 insertions(+), 4 deletions(-)
Comments
Il 24/07/23 17:47, Nícolas F. R. A. Prado ha scritto:
> Before writing the read or write command to the SPMI arbiter through the
> PMIF interface, the current status of the channel is checked to ensure
> it is idle. However, since the status only changes from idle when the
> command is written, it is possible for two concurrent calls to determine
> that the channel is idle and simultaneously send their commands. At this
> point the PMIF interface hangs, with the status register no longer being
> updated, and thus causing all subsequent operations to time out.
>
> This was observed on the mt8195-cherry-tomato-r2 machine, particularly
> after commit 46600ab142f8 ("regulator: Set PROBE_PREFER_ASYNCHRONOUS for
> drivers between 5.10 and 5.15") was applied, since then the two MT6315
> devices present on the SPMI bus would probe assynchronously and
> sometimes (during probe or at a later point) read the bus
> simultaneously, breaking the PMIF interface and consequently slowing
> down the whole system.
>
> To fix the issue at its root cause, introduce locking around the channel
> status check and the command write, so that both become an atomic
> operation, preventing race conditions between two (or more) SPMI bus
> read/write operations. A spinlock is used since this is a fast bus, as
> indicated by the usage of the atomic variant of readl_poll, and
> '.fast_io = true' being used in the mt6315 driver, so spinlocks are
> already used for the regmap access.
>
> Fixes: b45b3ccef8c0 ("spmi: mediatek: Add support for MT6873/8192")
> Signed-off-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
Perfect! :-)
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
>
> ---
>
> Changes in v3:
> - Switched to raw spinlock to avoid overhead in PREEMPT_RT
> - Moved spin_unlock to after marking the channel ready on the error
> paths
>
> Changes in v2:
> - Added missing spin_unlocks to error paths
> - Moved memcpy outside spinlock region in the write_cmd function
> - Reworded commit message to make clear that issue can happen at any
> point in runtime, not only during boot
>
> drivers/spmi/spmi-mtk-pmif.c | 20 ++++++++++++++++----
> 1 file changed, 16 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/spmi/spmi-mtk-pmif.c b/drivers/spmi/spmi-mtk-pmif.c
> index b3c991e1ea40..54c35f5535cb 100644
> --- a/drivers/spmi/spmi-mtk-pmif.c
> +++ b/drivers/spmi/spmi-mtk-pmif.c
> @@ -50,6 +50,7 @@ struct pmif {
> struct clk_bulk_data clks[PMIF_MAX_CLKS];
> size_t nclks;
> const struct pmif_data *data;
> + raw_spinlock_t lock;
> };
>
> static const char * const pmif_clock_names[] = {
> @@ -314,6 +315,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> struct ch_reg *inf_reg;
> int ret;
> u32 data, cmd;
> + unsigned long flags;
>
> /* Check for argument validation. */
> if (sid & ~0xf) {
> @@ -334,6 +336,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> else
> return -EINVAL;
>
> + raw_spin_lock_irqsave(&arb->lock, flags);
> /* Wait for Software Interface FSM state to be IDLE. */
> inf_reg = &arb->chan;
> ret = readl_poll_timeout_atomic(arb->base + arb->data->regs[inf_reg->ch_sta],
> @@ -343,6 +346,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> /* set channel ready if the data has transferred */
> if (pmif_is_fsm_vldclr(arb))
> pmif_writel(arb, 1, inf_reg->ch_rdy);
> + raw_spin_unlock_irqrestore(&arb->lock, flags);
> dev_err(&ctrl->dev, "failed to wait for SWINF_IDLE\n");
> return ret;
> }
> @@ -350,6 +354,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> /* Send the command. */
> cmd = (opc << 30) | (sid << 24) | ((len - 1) << 16) | addr;
> pmif_writel(arb, cmd, inf_reg->ch_send);
> + raw_spin_unlock_irqrestore(&arb->lock, flags);
>
> /*
> * Wait for Software Interface FSM state to be WFVLDCLR,
> @@ -376,7 +381,8 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> struct pmif *arb = spmi_controller_get_drvdata(ctrl);
> struct ch_reg *inf_reg;
> int ret;
> - u32 data, cmd;
> + u32 data, wdata, cmd;
> + unsigned long flags;
>
> if (len > 4) {
> dev_err(&ctrl->dev, "pmif supports 1..4 bytes per trans, but:%zu requested", len);
> @@ -394,6 +400,10 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> else
> return -EINVAL;
>
> + /* Set the write data. */
> + memcpy(&wdata, buf, len);
> +
> + raw_spin_lock_irqsave(&arb->lock, flags);
> /* Wait for Software Interface FSM state to be IDLE. */
> inf_reg = &arb->chan;
> ret = readl_poll_timeout_atomic(arb->base + arb->data->regs[inf_reg->ch_sta],
> @@ -403,17 +413,17 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
> /* set channel ready if the data has transferred */
> if (pmif_is_fsm_vldclr(arb))
> pmif_writel(arb, 1, inf_reg->ch_rdy);
> + raw_spin_unlock_irqrestore(&arb->lock, flags);
> dev_err(&ctrl->dev, "failed to wait for SWINF_IDLE\n");
> return ret;
> }
>
> - /* Set the write data. */
> - memcpy(&data, buf, len);
> - pmif_writel(arb, data, inf_reg->wdata);
> + pmif_writel(arb, wdata, inf_reg->wdata);
>
> /* Send the command. */
> cmd = (opc << 30) | BIT(29) | (sid << 24) | ((len - 1) << 16) | addr;
> pmif_writel(arb, cmd, inf_reg->ch_send);
> + raw_spin_unlock_irqrestore(&arb->lock, flags);
>
> return 0;
> }
> @@ -488,6 +498,8 @@ static int mtk_spmi_probe(struct platform_device *pdev)
> arb->chan.ch_send = PMIF_SWINF_0_ACC + chan_offset;
> arb->chan.ch_rdy = PMIF_SWINF_0_VLD_CLR + chan_offset;
>
> + raw_spin_lock_init(&arb->lock);
> +
> platform_set_drvdata(pdev, ctrl);
>
> err = spmi_controller_add(ctrl);
On Mon, Jul 24, 2023 at 11:47:33AM -0400, Nícolas F. R. A. Prado wrote:
> Before writing the read or write command to the SPMI arbiter through the
> PMIF interface, the current status of the channel is checked to ensure
> it is idle. However, since the status only changes from idle when the
> command is written, it is possible for two concurrent calls to determine
> that the channel is idle and simultaneously send their commands. At this
> point the PMIF interface hangs, with the status register no longer being
> updated, and thus causing all subsequent operations to time out.
>
> This was observed on the mt8195-cherry-tomato-r2 machine, particularly
> after commit 46600ab142f8 ("regulator: Set PROBE_PREFER_ASYNCHRONOUS for
> drivers between 5.10 and 5.15") was applied, since then the two MT6315
> devices present on the SPMI bus would probe assynchronously and
> sometimes (during probe or at a later point) read the bus
> simultaneously, breaking the PMIF interface and consequently slowing
> down the whole system.
>
> To fix the issue at its root cause, introduce locking around the channel
> status check and the command write, so that both become an atomic
> operation, preventing race conditions between two (or more) SPMI bus
> read/write operations. A spinlock is used since this is a fast bus, as
> indicated by the usage of the atomic variant of readl_poll, and
> '.fast_io = true' being used in the mt6315 driver, so spinlocks are
> already used for the regmap access.
>
> Fixes: b45b3ccef8c0 ("spmi: mediatek: Add support for MT6873/8192")
> Signed-off-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
Hi,
gentle ping on this one. MT8195 Chromebooks sometimes boot to a broken state
without it.
Thanks,
Nícolas
Reviewed-by: Alexandre Mergnat <amergnat@baylibre.com>
On 24/07/2023 17:47, Nícolas F. R. A. Prado wrote:
> Before writing the read or write command to the SPMI arbiter through the
> PMIF interface, the current status of the channel is checked to ensure
> it is idle. However, since the status only changes from idle when the
> command is written, it is possible for two concurrent calls to determine
> that the channel is idle and simultaneously send their commands. At this
> point the PMIF interface hangs, with the status register no longer being
> updated, and thus causing all subsequent operations to time out.
>
> This was observed on the mt8195-cherry-tomato-r2 machine, particularly
> after commit 46600ab142f8 ("regulator: Set PROBE_PREFER_ASYNCHRONOUS for
> drivers between 5.10 and 5.15") was applied, since then the two MT6315
> devices present on the SPMI bus would probe assynchronously and
> sometimes (during probe or at a later point) read the bus
> simultaneously, breaking the PMIF interface and consequently slowing
> down the whole system.
>
> To fix the issue at its root cause, introduce locking around the channel
> status check and the command write, so that both become an atomic
> operation, preventing race conditions between two (or more) SPMI bus
> read/write operations. A spinlock is used since this is a fast bus, as
> indicated by the usage of the atomic variant of readl_poll, and
> '.fast_io = true' being used in the mt6315 driver, so spinlocks are
> already used for the regmap access.
On Thu, Aug 10, 2023 at 06:03:53PM -0400, Nícolas F. R. A. Prado wrote:
> On Mon, Jul 24, 2023 at 11:47:33AM -0400, Nícolas F. R. A. Prado wrote:
> > Before writing the read or write command to the SPMI arbiter through the
> > PMIF interface, the current status of the channel is checked to ensure
> > it is idle. However, since the status only changes from idle when the
> > command is written, it is possible for two concurrent calls to determine
> > that the channel is idle and simultaneously send their commands. At this
> > point the PMIF interface hangs, with the status register no longer being
> > updated, and thus causing all subsequent operations to time out.
> >
> > This was observed on the mt8195-cherry-tomato-r2 machine, particularly
> > after commit 46600ab142f8 ("regulator: Set PROBE_PREFER_ASYNCHRONOUS for
> > drivers between 5.10 and 5.15") was applied, since then the two MT6315
> > devices present on the SPMI bus would probe assynchronously and
> > sometimes (during probe or at a later point) read the bus
> > simultaneously, breaking the PMIF interface and consequently slowing
> > down the whole system.
> >
> > To fix the issue at its root cause, introduce locking around the channel
> > status check and the command write, so that both become an atomic
> > operation, preventing race conditions between two (or more) SPMI bus
> > read/write operations. A spinlock is used since this is a fast bus, as
> > indicated by the usage of the atomic variant of readl_poll, and
> > '.fast_io = true' being used in the mt6315 driver, so spinlocks are
> > already used for the regmap access.
> >
> > Fixes: b45b3ccef8c0 ("spmi: mediatek: Add support for MT6873/8192")
> > Signed-off-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
>
> Hi,
>
> gentle ping on this one. MT8195 Chromebooks sometimes boot to a broken state
> without it.
Hi Stephen,
once again kindling reminding you of this important fix for MediaTek platforms,
solving a real issue impacting basic functionality observed on the MT8195
Chromebook.
Thanks,
Nícolas
Il 19/09/23 22:12, Nícolas F. R. A. Prado ha scritto:
> On Thu, Aug 10, 2023 at 06:03:53PM -0400, Nícolas F. R. A. Prado wrote:
>> On Mon, Jul 24, 2023 at 11:47:33AM -0400, Nícolas F. R. A. Prado wrote:
>>> Before writing the read or write command to the SPMI arbiter through the
>>> PMIF interface, the current status of the channel is checked to ensure
>>> it is idle. However, since the status only changes from idle when the
>>> command is written, it is possible for two concurrent calls to determine
>>> that the channel is idle and simultaneously send their commands. At this
>>> point the PMIF interface hangs, with the status register no longer being
>>> updated, and thus causing all subsequent operations to time out.
>>>
>>> This was observed on the mt8195-cherry-tomato-r2 machine, particularly
>>> after commit 46600ab142f8 ("regulator: Set PROBE_PREFER_ASYNCHRONOUS for
>>> drivers between 5.10 and 5.15") was applied, since then the two MT6315
>>> devices present on the SPMI bus would probe assynchronously and
>>> sometimes (during probe or at a later point) read the bus
>>> simultaneously, breaking the PMIF interface and consequently slowing
>>> down the whole system.
>>>
>>> To fix the issue at its root cause, introduce locking around the channel
>>> status check and the command write, so that both become an atomic
>>> operation, preventing race conditions between two (or more) SPMI bus
>>> read/write operations. A spinlock is used since this is a fast bus, as
>>> indicated by the usage of the atomic variant of readl_poll, and
>>> '.fast_io = true' being used in the mt6315 driver, so spinlocks are
>>> already used for the regmap access.
>>>
>>> Fixes: b45b3ccef8c0 ("spmi: mediatek: Add support for MT6873/8192")
>>> Signed-off-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
>>
>> Hi,
>>
>> gentle ping on this one. MT8195 Chromebooks sometimes boot to a broken state
>> without it.
>
> Hi Stephen,
>
> once again kindling reminding you of this important fix for MediaTek platforms,
> solving a real issue impacting basic functionality observed on the MT8195
> Chromebook.
>
Hello Stephen,
can you please pick this one ASAP?
MT8195 is broken without.
Thanks,
Angelo
@@ -50,6 +50,7 @@ struct pmif {
struct clk_bulk_data clks[PMIF_MAX_CLKS];
size_t nclks;
const struct pmif_data *data;
+ raw_spinlock_t lock;
};
static const char * const pmif_clock_names[] = {
@@ -314,6 +315,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
struct ch_reg *inf_reg;
int ret;
u32 data, cmd;
+ unsigned long flags;
/* Check for argument validation. */
if (sid & ~0xf) {
@@ -334,6 +336,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
else
return -EINVAL;
+ raw_spin_lock_irqsave(&arb->lock, flags);
/* Wait for Software Interface FSM state to be IDLE. */
inf_reg = &arb->chan;
ret = readl_poll_timeout_atomic(arb->base + arb->data->regs[inf_reg->ch_sta],
@@ -343,6 +346,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
/* set channel ready if the data has transferred */
if (pmif_is_fsm_vldclr(arb))
pmif_writel(arb, 1, inf_reg->ch_rdy);
+ raw_spin_unlock_irqrestore(&arb->lock, flags);
dev_err(&ctrl->dev, "failed to wait for SWINF_IDLE\n");
return ret;
}
@@ -350,6 +354,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
/* Send the command. */
cmd = (opc << 30) | (sid << 24) | ((len - 1) << 16) | addr;
pmif_writel(arb, cmd, inf_reg->ch_send);
+ raw_spin_unlock_irqrestore(&arb->lock, flags);
/*
* Wait for Software Interface FSM state to be WFVLDCLR,
@@ -376,7 +381,8 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
struct pmif *arb = spmi_controller_get_drvdata(ctrl);
struct ch_reg *inf_reg;
int ret;
- u32 data, cmd;
+ u32 data, wdata, cmd;
+ unsigned long flags;
if (len > 4) {
dev_err(&ctrl->dev, "pmif supports 1..4 bytes per trans, but:%zu requested", len);
@@ -394,6 +400,10 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
else
return -EINVAL;
+ /* Set the write data. */
+ memcpy(&wdata, buf, len);
+
+ raw_spin_lock_irqsave(&arb->lock, flags);
/* Wait for Software Interface FSM state to be IDLE. */
inf_reg = &arb->chan;
ret = readl_poll_timeout_atomic(arb->base + arb->data->regs[inf_reg->ch_sta],
@@ -403,17 +413,17 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
/* set channel ready if the data has transferred */
if (pmif_is_fsm_vldclr(arb))
pmif_writel(arb, 1, inf_reg->ch_rdy);
+ raw_spin_unlock_irqrestore(&arb->lock, flags);
dev_err(&ctrl->dev, "failed to wait for SWINF_IDLE\n");
return ret;
}
- /* Set the write data. */
- memcpy(&data, buf, len);
- pmif_writel(arb, data, inf_reg->wdata);
+ pmif_writel(arb, wdata, inf_reg->wdata);
/* Send the command. */
cmd = (opc << 30) | BIT(29) | (sid << 24) | ((len - 1) << 16) | addr;
pmif_writel(arb, cmd, inf_reg->ch_send);
+ raw_spin_unlock_irqrestore(&arb->lock, flags);
return 0;
}
@@ -488,6 +498,8 @@ static int mtk_spmi_probe(struct platform_device *pdev)
arb->chan.ch_send = PMIF_SWINF_0_ACC + chan_offset;
arb->chan.ch_rdy = PMIF_SWINF_0_VLD_CLR + chan_offset;
+ raw_spin_lock_init(&arb->lock);
+
platform_set_drvdata(pdev, ctrl);
err = spmi_controller_add(ctrl);