| Message ID | 1552492237-28810-1-git-send-email-fabien.dessenne@st.com (mailing list archive) |
|---|---|
| Headers | show |
| Series | hwspinlock: allow sharing of hwspinlocks | expand |
On Wed 13 Mar 08:50 PDT 2019, Fabien Dessenne wrote: > The current implementation does not allow two different devices to use > a common hwspinlock. This patch set proposes to have, as an option, some > hwspinlocks shared between several users. > > Below is an example that explain the need for this: > exti: interrupt-controller@5000d000 { > compatible = "st,stm32mp1-exti", "syscon"; > interrupt-controller; > #interrupt-cells = <2>; > reg = <0x5000d000 0x400>; > hwlocks = <&hsem 1>; > }; > The two drivers (stm32mp1-exti and syscon) refer to the same hwlock. > With the current hwspinlock implementation, only the first driver succeeds > in requesting (hwspin_lock_request_specific) the hwlock. The second request > fails. > > > The proposed approach does not modify the API, but extends the DT 'hwlocks' > property with a second optional parameter (the first one identifies an > hwlock) that specifies whether an hwlock is requested for exclusive usage > (current behavior) or can be shared between several users. > Examples: > hwlocks = <&hsem 8>; Ref to hwlock #8 for exclusive usage > hwlocks = <&hsem 8 0>; Ref to hwlock #8 for exclusive (0) usage > hwlocks = <&hsem 8 1>; Ref to hwlock #8 for shared (1) usage > > As a constraint, the #hwlock-cells value must be 1 or 2. > In the current implementation, this can have theorically any value but: > - all of the exisiting drivers use the same value : 1. > - the framework supports only one value : 1 (see implementation of > of_hwspin_lock_simple_xlate()) > Hence, it shall not be a problem to restrict this value to 1 or 2 since > it won't break any driver. > Hi Fabien, Your series looks good, but it makes me wonder why the hardware locks should be an exclusive resource. How about just making all (specific) locks shared? Regards, Bjorn > Fabien Dessenne (6): > dt-bindings: hwlock: add support of shared locks > hwspinlock: allow sharing of hwspinlocks > dt-bindings: hwlock: update STM32 #hwlock-cells value > ARM: dts: stm32: Add hwspinlock node for stm32mp157 SoC > ARM: dts: stm32: Add hwlock for irqchip on stm32mp157 > ARM: dts: stm32: hwlocks for GPIO for stm32mp157 > > .../devicetree/bindings/hwlock/hwlock.txt | 27 +++++-- > .../bindings/hwlock/st,stm32-hwspinlock.txt | 6 +- > Documentation/hwspinlock.txt | 10 ++- > arch/arm/boot/dts/stm32mp157-pinctrl.dtsi | 2 + > arch/arm/boot/dts/stm32mp157c.dtsi | 10 +++ > drivers/hwspinlock/hwspinlock_core.c | 82 +++++++++++++++++----- > drivers/hwspinlock/hwspinlock_internal.h | 2 + > 7 files changed, 108 insertions(+), 31 deletions(-) > > -- > 2.7.4 >
On 01/08/2019 9:14 PM, Bjorn Andersson wrote: > On Wed 13 Mar 08:50 PDT 2019, Fabien Dessenne wrote: > >> The current implementation does not allow two different devices to use >> a common hwspinlock. This patch set proposes to have, as an option, some >> hwspinlocks shared between several users. >> >> Below is an example that explain the need for this: >> exti: interrupt-controller@5000d000 { >> compatible = "st,stm32mp1-exti", "syscon"; >> interrupt-controller; >> #interrupt-cells = <2>; >> reg = <0x5000d000 0x400>; >> hwlocks = <&hsem 1>; >> }; >> The two drivers (stm32mp1-exti and syscon) refer to the same hwlock. >> With the current hwspinlock implementation, only the first driver succeeds >> in requesting (hwspin_lock_request_specific) the hwlock. The second request >> fails. >> >> >> The proposed approach does not modify the API, but extends the DT 'hwlocks' >> property with a second optional parameter (the first one identifies an >> hwlock) that specifies whether an hwlock is requested for exclusive usage >> (current behavior) or can be shared between several users. >> Examples: >> hwlocks = <&hsem 8>; Ref to hwlock #8 for exclusive usage >> hwlocks = <&hsem 8 0>; Ref to hwlock #8 for exclusive (0) usage >> hwlocks = <&hsem 8 1>; Ref to hwlock #8 for shared (1) usage >> >> As a constraint, the #hwlock-cells value must be 1 or 2. >> In the current implementation, this can have theorically any value but: >> - all of the exisiting drivers use the same value : 1. >> - the framework supports only one value : 1 (see implementation of >> of_hwspin_lock_simple_xlate()) >> Hence, it shall not be a problem to restrict this value to 1 or 2 since >> it won't break any driver. >> > Hi Fabien, > > Your series looks good, but it makes me wonder why the hardware locks > should be an exclusive resource. > > How about just making all (specific) locks shared? Hi Bjorn, Making all locks shared is a possible implementation (my first implementation was going this way) but there are some drawbacks we must be aware of: A/ This theoretically break the legacy behavior (the legacy works with exclusive (UNUSED radix tag) usage). As a consequence, an existing driver that is currently failing to request a lock (already claimed by another user) would now work fine. Not sure that there are such drivers, so this point is probably not a real issue. B/ This would introduce some inconsistency between the two 'request' API which are hwspin_lock_request() and hwspin_lock_request_specific(). hwspin_lock_request() looks for an unused lock, so requests for an exclusive usage. On the other side, request_specific() would request shared locks. Worst the following sequence can transform an exclusive usage into a shared one: -hwspin_lock_request() -> returns Id#0 (exclusive) -hwspin_lock_request() -> returns Id#1 (exclusive) -hwspin_lock_request_specific(0) -> returns Id#0 and makes Id#0 shared Honestly I am not sure that this is a real issue, but it's better to have it in mind before we take ay decision I could not find any driver using the hwspin_lock_request() API, we may decide to remove (or to make deprecated) this API, having everything 'shared without any conditions'. I can see three options: 1- Keep my initial proposition 2- Have hwspin_lock_request_specific() using shared locks and hwspin_lock_request() using unused (so 'initially' exclusive) locks. 3- Have hwspin_lock_request_specific() using shared locks and remove/make deprecated hwspin_lock_request(). Just let me know what is your preference. BR Fabien > > Regards, > Bjorn > >> Fabien Dessenne (6): >> dt-bindings: hwlock: add support of shared locks >> hwspinlock: allow sharing of hwspinlocks >> dt-bindings: hwlock: update STM32 #hwlock-cells value >> ARM: dts: stm32: Add hwspinlock node for stm32mp157 SoC >> ARM: dts: stm32: Add hwlock for irqchip on stm32mp157 >> ARM: dts: stm32: hwlocks for GPIO for stm32mp157 >> >> .../devicetree/bindings/hwlock/hwlock.txt | 27 +++++-- >> .../bindings/hwlock/st,stm32-hwspinlock.txt | 6 +- >> Documentation/hwspinlock.txt | 10 ++- >> arch/arm/boot/dts/stm32mp157-pinctrl.dtsi | 2 + >> arch/arm/boot/dts/stm32mp157c.dtsi | 10 +++ >> drivers/hwspinlock/hwspinlock_core.c | 82 +++++++++++++++++----- >> drivers/hwspinlock/hwspinlock_internal.h | 2 + >> 7 files changed, 108 insertions(+), 31 deletions(-) >> >> -- >> 2.7.4 >>
On Mon 05 Aug 01:48 PDT 2019, Fabien DESSENNE wrote: > > On 01/08/2019 9:14 PM, Bjorn Andersson wrote: > > On Wed 13 Mar 08:50 PDT 2019, Fabien Dessenne wrote: > > > >> The current implementation does not allow two different devices to use > >> a common hwspinlock. This patch set proposes to have, as an option, some > >> hwspinlocks shared between several users. > >> > >> Below is an example that explain the need for this: > >> exti: interrupt-controller@5000d000 { > >> compatible = "st,stm32mp1-exti", "syscon"; > >> interrupt-controller; > >> #interrupt-cells = <2>; > >> reg = <0x5000d000 0x400>; > >> hwlocks = <&hsem 1>; > >> }; > >> The two drivers (stm32mp1-exti and syscon) refer to the same hwlock. > >> With the current hwspinlock implementation, only the first driver succeeds > >> in requesting (hwspin_lock_request_specific) the hwlock. The second request > >> fails. > >> > >> > >> The proposed approach does not modify the API, but extends the DT 'hwlocks' > >> property with a second optional parameter (the first one identifies an > >> hwlock) that specifies whether an hwlock is requested for exclusive usage > >> (current behavior) or can be shared between several users. > >> Examples: > >> hwlocks = <&hsem 8>; Ref to hwlock #8 for exclusive usage > >> hwlocks = <&hsem 8 0>; Ref to hwlock #8 for exclusive (0) usage > >> hwlocks = <&hsem 8 1>; Ref to hwlock #8 for shared (1) usage > >> > >> As a constraint, the #hwlock-cells value must be 1 or 2. > >> In the current implementation, this can have theorically any value but: > >> - all of the exisiting drivers use the same value : 1. > >> - the framework supports only one value : 1 (see implementation of > >> of_hwspin_lock_simple_xlate()) > >> Hence, it shall not be a problem to restrict this value to 1 or 2 since > >> it won't break any driver. > >> > > Hi Fabien, > > > > Your series looks good, but it makes me wonder why the hardware locks > > should be an exclusive resource. > > > > How about just making all (specific) locks shared? > > Hi Bjorn, > > Making all locks shared is a possible implementation (my first > implementation > was going this way) but there are some drawbacks we must be aware of: > > A/ This theoretically break the legacy behavior (the legacy works with > exclusive (UNUSED radix tag) usage). As a consequence, an existing driver > that is currently failing to request a lock (already claimed by another > user) would now work fine. Not sure that there are such drivers, so this > point is probably not a real issue. > Right, it's possible that a previously misconfigured system now successfully probes more than one device that uses a particular spinlock. But such system would be suffering from issues related to e.g. probe ordering. So I think we should ignore this issue. > B/ This would introduce some inconsistency between the two 'request' API > which are hwspin_lock_request() and hwspin_lock_request_specific(). > hwspin_lock_request() looks for an unused lock, so requests for an exclusive > usage. On the other side, request_specific() would request shared locks. > Worst the following sequence can transform an exclusive usage into a shared > There is already an inconsistency in between these; as with above any system that uses both request() and request_specific() will be suffering from intermittent failures due to probe ordering. > one: > -hwspin_lock_request() -> returns Id#0 (exclusive) > -hwspin_lock_request() -> returns Id#1 (exclusive) > -hwspin_lock_request_specific(0) -> returns Id#0 and makes Id#0 shared > Honestly I am not sure that this is a real issue, but it's better to have it > in mind before we take ay decision The case where I can see a problem with this would be if the two clients somehow would nest their locking regions. But generally I think this could consider this an improvement, because the request_specific() would now be able to acquire its hwlock, with some additional contention due to the multiple use. > I could not find any driver using the hwspin_lock_request() API, we > may decide to remove (or to make deprecated) this API, having > everything 'shared without any conditions'. > It would be nice to have an upstream user of this API. > > I can see three options: > 1- Keep my initial proposition > 2- Have hwspin_lock_request_specific() using shared locks and > hwspin_lock_request() using unused (so 'initially' exclusive) locks. > 3- Have hwspin_lock_request_specific() using shared locks and > remove/make deprecated hwspin_lock_request(). > > Just let me know what is your preference. > I think we should start with #2 and would like input from e.g. Suman regarding #3. Regards, Bjorn > BR > > Fabien > > > > > Regards, > > Bjorn > > > >> Fabien Dessenne (6): > >> dt-bindings: hwlock: add support of shared locks > >> hwspinlock: allow sharing of hwspinlocks > >> dt-bindings: hwlock: update STM32 #hwlock-cells value > >> ARM: dts: stm32: Add hwspinlock node for stm32mp157 SoC > >> ARM: dts: stm32: Add hwlock for irqchip on stm32mp157 > >> ARM: dts: stm32: hwlocks for GPIO for stm32mp157 > >> > >> .../devicetree/bindings/hwlock/hwlock.txt | 27 +++++-- > >> .../bindings/hwlock/st,stm32-hwspinlock.txt | 6 +- > >> Documentation/hwspinlock.txt | 10 ++- > >> arch/arm/boot/dts/stm32mp157-pinctrl.dtsi | 2 + > >> arch/arm/boot/dts/stm32mp157c.dtsi | 10 +++ > >> drivers/hwspinlock/hwspinlock_core.c | 82 +++++++++++++++++----- > >> drivers/hwspinlock/hwspinlock_internal.h | 2 + > >> 7 files changed, 108 insertions(+), 31 deletions(-) > >> > >> -- > >> 2.7.4 > >>
Hi Suman, Could you please let us know your thoughts or comments? BR Fabien > -----Original Message----- > From: Bjorn Andersson <bjorn.andersson@linaro.org> > Sent: lundi 5 août 2019 19:47 > To: Fabien DESSENNE <fabien.dessenne@st.com> > Cc: Ohad Ben-Cohen <ohad@wizery.com>; Rob Herring <robh+dt@kernel.org>; > Mark Rutland <mark.rutland@arm.com>; Maxime Coquelin > <mcoquelin.stm32@gmail.com>; Alexandre TORGUE > <alexandre.torgue@st.com>; Jonathan Corbet <corbet@lwn.net>; linux- > remoteproc@vger.kernel.org; devicetree@vger.kernel.org; linux- > kernel@vger.kernel.org; linux-stm32@st-md-mailman.stormreply.com; linux-arm- > kernel@lists.infradead.org; linux-doc@vger.kernel.org; Benjamin GAIGNARD > <benjamin.gaignard@st.com> > Subject: Re: [PATCH 0/6] hwspinlock: allow sharing of hwspinlocks > > On Mon 05 Aug 01:48 PDT 2019, Fabien DESSENNE wrote: > > > > > On 01/08/2019 9:14 PM, Bjorn Andersson wrote: > > > On Wed 13 Mar 08:50 PDT 2019, Fabien Dessenne wrote: > > > > > >> The current implementation does not allow two different devices to > > >> use a common hwspinlock. This patch set proposes to have, as an > > >> option, some hwspinlocks shared between several users. > > >> > > >> Below is an example that explain the need for this: > > >> exti: interrupt-controller@5000d000 { > > >> compatible = "st,stm32mp1-exti", "syscon"; > > >> interrupt-controller; > > >> #interrupt-cells = <2>; > > >> reg = <0x5000d000 0x400>; > > >> hwlocks = <&hsem 1>; > > >> }; > > >> The two drivers (stm32mp1-exti and syscon) refer to the same hwlock. > > >> With the current hwspinlock implementation, only the first driver > > >> succeeds in requesting (hwspin_lock_request_specific) the hwlock. > > >> The second request fails. > > >> > > >> > > >> The proposed approach does not modify the API, but extends the DT > 'hwlocks' > > >> property with a second optional parameter (the first one identifies > > >> an > > >> hwlock) that specifies whether an hwlock is requested for exclusive > > >> usage (current behavior) or can be shared between several users. > > >> Examples: > > >> hwlocks = <&hsem 8>; Ref to hwlock #8 for exclusive usage > > >> hwlocks = <&hsem 8 0>; Ref to hwlock #8 for exclusive (0) usage > > >> hwlocks = <&hsem 8 1>; Ref to hwlock #8 for shared (1) usage > > >> > > >> As a constraint, the #hwlock-cells value must be 1 or 2. > > >> In the current implementation, this can have theorically any value but: > > >> - all of the exisiting drivers use the same value : 1. > > >> - the framework supports only one value : 1 (see implementation of > > >> of_hwspin_lock_simple_xlate()) > > >> Hence, it shall not be a problem to restrict this value to 1 or 2 > > >> since it won't break any driver. > > >> > > > Hi Fabien, > > > > > > Your series looks good, but it makes me wonder why the hardware > > > locks should be an exclusive resource. > > > > > > How about just making all (specific) locks shared? > > > > Hi Bjorn, > > > > Making all locks shared is a possible implementation (my first > > implementation was going this way) but there are some drawbacks we > > must be aware of: > > > > A/ This theoretically break the legacy behavior (the legacy works with > > exclusive (UNUSED radix tag) usage). As a consequence, an existing > > driver that is currently failing to request a lock (already claimed by > > another > > user) would now work fine. Not sure that there are such drivers, so > > this point is probably not a real issue. > > > > Right, it's possible that a previously misconfigured system now successfully > probes more than one device that uses a particular spinlock. But such system > would be suffering from issues related to e.g. > probe ordering. > > So I think we should ignore this issue. > > > B/ This would introduce some inconsistency between the two 'request' > > API which are hwspin_lock_request() and hwspin_lock_request_specific(). > > hwspin_lock_request() looks for an unused lock, so requests for an > > exclusive usage. On the other side, request_specific() would request shared > locks. > > Worst the following sequence can transform an exclusive usage into a > > shared > > > > There is already an inconsistency in between these; as with above any system > that uses both request() and request_specific() will be suffering from intermittent > failures due to probe ordering. > > > one: > > -hwspin_lock_request() -> returns Id#0 (exclusive) > > -hwspin_lock_request() -> returns Id#1 (exclusive) > > -hwspin_lock_request_specific(0) -> returns Id#0 and makes Id#0 > > shared Honestly I am not sure that this is a real issue, but it's > > better to have it in mind before we take ay decision > > The case where I can see a > problem with this would be if the two clients somehow would nest their locking > regions. > > But generally I think this could consider this an improvement, because the > request_specific() would now be able to acquire its hwlock, with some additional > contention due to the multiple use. > > > I could not find any driver using the hwspin_lock_request() API, we > > may decide to remove (or to make deprecated) this API, having > > everything 'shared without any conditions'. > > > > It would be nice to have an upstream user of this API. > > > > > I can see three options: > > 1- Keep my initial proposition > > 2- Have hwspin_lock_request_specific() using shared locks and > > hwspin_lock_request() using unused (so 'initially' exclusive) locks. > > 3- Have hwspin_lock_request_specific() using shared locks and > > remove/make deprecated hwspin_lock_request(). > > > > Just let me know what is your preference. > > > > I think we should start with #2 and would like input from e.g. Suman regarding #3. > > Regards, > Bjorn > > > BR > > > > Fabien > > > > > > > > Regards, > > > Bjorn > > > > > >> Fabien Dessenne (6): > > >> dt-bindings: hwlock: add support of shared locks > > >> hwspinlock: allow sharing of hwspinlocks > > >> dt-bindings: hwlock: update STM32 #hwlock-cells value > > >> ARM: dts: stm32: Add hwspinlock node for stm32mp157 SoC > > >> ARM: dts: stm32: Add hwlock for irqchip on stm32mp157 > > >> ARM: dts: stm32: hwlocks for GPIO for stm32mp157 > > >> > > >> .../devicetree/bindings/hwlock/hwlock.txt | 27 +++++-- > > >> .../bindings/hwlock/st,stm32-hwspinlock.txt | 6 +- > > >> Documentation/hwspinlock.txt | 10 ++- > > >> arch/arm/boot/dts/stm32mp157-pinctrl.dtsi | 2 + > > >> arch/arm/boot/dts/stm32mp157c.dtsi | 10 +++ > > >> drivers/hwspinlock/hwspinlock_core.c | 82 +++++++++++++++++- > ---- > > >> drivers/hwspinlock/hwspinlock_internal.h | 2 + > > >> 7 files changed, 108 insertions(+), 31 deletions(-) > > >> > > >> -- > > >> 2.7.4 > > >>
Hi Fabien, On 8/5/19 12:46 PM, Bjorn Andersson wrote: > On Mon 05 Aug 01:48 PDT 2019, Fabien DESSENNE wrote: > >> >> On 01/08/2019 9:14 PM, Bjorn Andersson wrote: >>> On Wed 13 Mar 08:50 PDT 2019, Fabien Dessenne wrote: >>> >>>> The current implementation does not allow two different devices to use >>>> a common hwspinlock. This patch set proposes to have, as an option, some >>>> hwspinlocks shared between several users. >>>> >>>> Below is an example that explain the need for this: >>>> exti: interrupt-controller@5000d000 { >>>> compatible = "st,stm32mp1-exti", "syscon"; >>>> interrupt-controller; >>>> #interrupt-cells = <2>; >>>> reg = <0x5000d000 0x400>; >>>> hwlocks = <&hsem 1>; >>>> }; >>>> The two drivers (stm32mp1-exti and syscon) refer to the same hwlock. >>>> With the current hwspinlock implementation, only the first driver succeeds >>>> in requesting (hwspin_lock_request_specific) the hwlock. The second request >>>> fails. Help me understand the problem that you are trying to solve here. Is this a case of you having two clients on Linux-side needing to use the same lock but still requiring the arbitration with software running on some other remote processor? Are they talking to the same entity on the remote-side or different peers. I see the series is all about getting a handle so that they can use the API, and is the expected usage that the same entity will lock and unlock before the other driver can lock it. >>>> >>>> >>>> The proposed approach does not modify the API, but extends the DT 'hwlocks' >>>> property with a second optional parameter (the first one identifies an >>>> hwlock) that specifies whether an hwlock is requested for exclusive usage >>>> (current behavior) or can be shared between several users. >>>> Examples: >>>> hwlocks = <&hsem 8>; Ref to hwlock #8 for exclusive usage >>>> hwlocks = <&hsem 8 0>; Ref to hwlock #8 for exclusive (0) usage >>>> hwlocks = <&hsem 8 1>; Ref to hwlock #8 for shared (1) usage >>>> >>>> As a constraint, the #hwlock-cells value must be 1 or 2. >>>> In the current implementation, this can have theorically any value but: >>>> - all of the exisiting drivers use the same value : 1. >>>> - the framework supports only one value : 1 (see implementation of >>>> of_hwspin_lock_simple_xlate()) >>>> Hence, it shall not be a problem to restrict this value to 1 or 2 since >>>> it won't break any driver. >>>> >>> Hi Fabien, >>> >>> Your series looks good, but it makes me wonder why the hardware locks >>> should be an exclusive resource. >>> >>> How about just making all (specific) locks shared? >> >> Hi Bjorn, >> >> Making all locks shared is a possible implementation (my first >> implementation >> was going this way) but there are some drawbacks we must be aware of: >> >> A/ This theoretically break the legacy behavior (the legacy works with >> exclusive (UNUSED radix tag) usage). As a consequence, an existing driver >> that is currently failing to request a lock (already claimed by another >> user) would now work fine. Not sure that there are such drivers, so this >> point is probably not a real issue. >> > > Right, it's possible that a previously misconfigured system now > successfully probes more than one device that uses a particular > spinlock. But such system would be suffering from issues related to e.g. > probe ordering. > > So I think we should ignore this issue. > >> B/ This would introduce some inconsistency between the two 'request' API >> which are hwspin_lock_request() and hwspin_lock_request_specific(). >> hwspin_lock_request() looks for an unused lock, so requests for an exclusive >> usage. On the other side, request_specific() would request shared locks. >> Worst the following sequence can transform an exclusive usage into a shared >> > > There is already an inconsistency in between these; as with above any > system that uses both request() and request_specific() will be suffering > from intermittent failures due to probe ordering. > >> one: >> -hwspin_lock_request() -> returns Id#0 (exclusive) >> -hwspin_lock_request() -> returns Id#1 (exclusive) >> -hwspin_lock_request_specific(0) -> returns Id#0 and makes Id#0 shared >> Honestly I am not sure that this is a real issue, but it's better to have it >> in mind before we take ay decision Wouldn't it be actually simpler to just introduce a new specific API variant for this, similar to the reset core for example (it uses a separate exclusive API), without having to modify the bindings at all. It is just a case of your driver using the right API, and the core can be modified to use the additional tag semantics based on the API. It should avoid any confusion with say using a different second cell value for the same lock in two different nodes. If you are sharing a hwlock on the Linux side, surely your driver should be aware that it is a shared lock. The tag can be set during the first request API, and you look through both tags when giving out a handle. Obviously, the hwspin_lock_request() API usage semantics always had the implied additional need for communicating the lock id to the other peer entity, so a realistic usage is most always the specific API variant. I doubt this API would be of much use for the shared driver usage. This also implies that the client user does not care about specifying a lock in DT. regards Suman > > The case where I can see a > problem with this would be if the two clients somehow would nest their > locking regions. > > But generally I think this could consider this an improvement, because > the request_specific() would now be able to acquire its hwlock, with > some additional contention due to the multiple use. > >> I could not find any driver using the hwspin_lock_request() API, we >> may decide to remove (or to make deprecated) this API, having >> everything 'shared without any conditions'. >> > > It would be nice to have an upstream user of this API. > >> >> I can see three options: >> 1- Keep my initial proposition >> 2- Have hwspin_lock_request_specific() using shared locks and >> hwspin_lock_request() using unused (so 'initially' exclusive) locks. >> 3- Have hwspin_lock_request_specific() using shared locks and >> remove/make deprecated hwspin_lock_request(). >> >> Just let me know what is your preference. >> > > I think we should start with #2 and would like input from e.g. Suman > regarding #3. > > Regards, > Bjorn > >> BR >> >> Fabien >> >>> >>> Regards, >>> Bjorn >>> >>>> Fabien Dessenne (6): >>>> dt-bindings: hwlock: add support of shared locks >>>> hwspinlock: allow sharing of hwspinlocks >>>> dt-bindings: hwlock: update STM32 #hwlock-cells value >>>> ARM: dts: stm32: Add hwspinlock node for stm32mp157 SoC >>>> ARM: dts: stm32: Add hwlock for irqchip on stm32mp157 >>>> ARM: dts: stm32: hwlocks for GPIO for stm32mp157 >>>> >>>> .../devicetree/bindings/hwlock/hwlock.txt | 27 +++++-- >>>> .../bindings/hwlock/st,stm32-hwspinlock.txt | 6 +- >>>> Documentation/hwspinlock.txt | 10 ++- >>>> arch/arm/boot/dts/stm32mp157-pinctrl.dtsi | 2 + >>>> arch/arm/boot/dts/stm32mp157c.dtsi | 10 +++ >>>> drivers/hwspinlock/hwspinlock_core.c | 82 +++++++++++++++++----- >>>> drivers/hwspinlock/hwspinlock_internal.h | 2 + >>>> 7 files changed, 108 insertions(+), 31 deletions(-) >>>> >>>> -- >>>> 2.7.4 >>>>
On Tue 06 Aug 10:38 PDT 2019, Suman Anna wrote: > Hi Fabien, > > On 8/5/19 12:46 PM, Bjorn Andersson wrote: > > On Mon 05 Aug 01:48 PDT 2019, Fabien DESSENNE wrote: > > > >> > >> On 01/08/2019 9:14 PM, Bjorn Andersson wrote: > >>> On Wed 13 Mar 08:50 PDT 2019, Fabien Dessenne wrote: [..] > >> B/ This would introduce some inconsistency between the two 'request' API > >> which are hwspin_lock_request() and hwspin_lock_request_specific(). > >> hwspin_lock_request() looks for an unused lock, so requests for an exclusive > >> usage. On the other side, request_specific() would request shared locks. > >> Worst the following sequence can transform an exclusive usage into a shared > >> > > > > There is already an inconsistency in between these; as with above any > > system that uses both request() and request_specific() will be suffering > > from intermittent failures due to probe ordering. > > > >> one: > >> -hwspin_lock_request() -> returns Id#0 (exclusive) > >> -hwspin_lock_request() -> returns Id#1 (exclusive) > >> -hwspin_lock_request_specific(0) -> returns Id#0 and makes Id#0 shared > >> Honestly I am not sure that this is a real issue, but it's better to have it > >> in mind before we take ay decision > > Wouldn't it be actually simpler to just introduce a new specific API > variant for this, similar to the reset core for example (it uses a > separate exclusive API), without having to modify the bindings at all. > It is just a case of your driver using the right API, and the core can > be modified to use the additional tag semantics based on the API. It > should avoid any confusion with say using a different second cell value > for the same lock in two different nodes. > But this implies that there is an actual need to hold these locks exclusively. Given that they are (except for the raw case) all wrapped by Linux locking primitives there shouldn't be a problem sharing a lock (except possibly for the raw case). I agree that we shouldn't specify this property in DT - if anything it should be a variant of the API. > If you are sharing a hwlock on the Linux side, surely your driver should > be aware that it is a shared lock. The tag can be set during the first > request API, and you look through both tags when giving out a handle. > Why would the driver need to know about it? > Obviously, the hwspin_lock_request() API usage semantics always had the > implied additional need for communicating the lock id to the other peer > entity, so a realistic usage is most always the specific API variant. I > doubt this API would be of much use for the shared driver usage. This > also implies that the client user does not care about specifying a lock > in DT. > Afaict if the lock are shared then there shouldn't be a problem with some clients using the request API and others request_specific(). As any collisions would simply mean that there are more contention on the lock. With the current exclusive model that is not possible and the success of the request_specific will depend on probe order. But perhaps it should be explicitly prohibited to use both APIs on the same hwspinlock instance? Regards, Bjorn
On 8/6/19 1:21 PM, Bjorn Andersson wrote: > On Tue 06 Aug 10:38 PDT 2019, Suman Anna wrote: > >> Hi Fabien, >> >> On 8/5/19 12:46 PM, Bjorn Andersson wrote: >>> On Mon 05 Aug 01:48 PDT 2019, Fabien DESSENNE wrote: >>> >>>> >>>> On 01/08/2019 9:14 PM, Bjorn Andersson wrote: >>>>> On Wed 13 Mar 08:50 PDT 2019, Fabien Dessenne wrote: > [..] >>>> B/ This would introduce some inconsistency between the two 'request' API >>>> which are hwspin_lock_request() and hwspin_lock_request_specific(). >>>> hwspin_lock_request() looks for an unused lock, so requests for an exclusive >>>> usage. On the other side, request_specific() would request shared locks. >>>> Worst the following sequence can transform an exclusive usage into a shared >>>> >>> >>> There is already an inconsistency in between these; as with above any >>> system that uses both request() and request_specific() will be suffering >>> from intermittent failures due to probe ordering. >>> >>>> one: >>>> -hwspin_lock_request() -> returns Id#0 (exclusive) >>>> -hwspin_lock_request() -> returns Id#1 (exclusive) >>>> -hwspin_lock_request_specific(0) -> returns Id#0 and makes Id#0 shared >>>> Honestly I am not sure that this is a real issue, but it's better to have it >>>> in mind before we take ay decision >> >> Wouldn't it be actually simpler to just introduce a new specific API >> variant for this, similar to the reset core for example (it uses a >> separate exclusive API), without having to modify the bindings at all. >> It is just a case of your driver using the right API, and the core can >> be modified to use the additional tag semantics based on the API. It >> should avoid any confusion with say using a different second cell value >> for the same lock in two different nodes. >> > > But this implies that there is an actual need to hold these locks > exclusively. Given that they are (except for the raw case) all wrapped > by Linux locking primitives there shouldn't be a problem sharing a lock > (except possibly for the raw case). Yes agreed, the HWLOCK_RAW and HWLOCK_IN_ATOMIC cases are unprotected. I am still trying to understand better the usecase to see if the same lock is being multiplexed for different protection contexts, or if all of them are protecting the same context. > > I agree that we shouldn't specify this property in DT - if anything it > should be a variant of the API. > >> If you are sharing a hwlock on the Linux side, surely your driver should >> be aware that it is a shared lock. The tag can be set during the first >> request API, and you look through both tags when giving out a handle. >> > > Why would the driver need to know about it? Just the semantics if we were to support single user vs multiple users on Linux-side to even get a handle. Your point is that this may be moot since we have protection anyway other than the raw cases. But we need to be able to have the same API work across all cases. So far, it had mostly been that there would be one user on Linux competing with other equivalent peer entities on different processors. It is not common to have multiple users since these protection schemes are usually needed only at the lowest levels of a stack, so the exclusive handle stuff had been sufficient. > >> Obviously, the hwspin_lock_request() API usage semantics always had the >> implied additional need for communicating the lock id to the other peer >> entity, so a realistic usage is most always the specific API variant. I >> doubt this API would be of much use for the shared driver usage. This >> also implies that the client user does not care about specifying a lock >> in DT. >> > > Afaict if the lock are shared then there shouldn't be a problem with > some clients using the request API and others request_specific(). As any > collisions would simply mean that there are more contention on the lock. > > With the current exclusive model that is not possible and the success of > the request_specific will depend on probe order. > > But perhaps it should be explicitly prohibited to use both APIs on the > same hwspinlock instance? Yeah, they are meant to be complimentary usage, though I doubt we will ever have any realistic users for the generic API if we haven't had a usage so far. I had posted a concept of reserved locks long back [1] to keep away certain locks from the generic requestor, but dropped it since we did not have an actual use-case needing it. regards Suman [1] https://lwn.net/Articles/611944/
Hi On 06/08/2019 11:30 PM, Suman Anna wrote: > On 8/6/19 1:21 PM, Bjorn Andersson wrote: >> On Tue 06 Aug 10:38 PDT 2019, Suman Anna wrote: >> >>> Hi Fabien, >>> >>> On 8/5/19 12:46 PM, Bjorn Andersson wrote: >>>> On Mon 05 Aug 01:48 PDT 2019, Fabien DESSENNE wrote: >>>> >>>>> On 01/08/2019 9:14 PM, Bjorn Andersson wrote: >>>>>> On Wed 13 Mar 08:50 PDT 2019, Fabien Dessenne wrote: >> [..] >>>>> B/ This would introduce some inconsistency between the two 'request' API >>>>> which are hwspin_lock_request() and hwspin_lock_request_specific(). >>>>> hwspin_lock_request() looks for an unused lock, so requests for an exclusive >>>>> usage. On the other side, request_specific() would request shared locks. >>>>> Worst the following sequence can transform an exclusive usage into a shared >>>>> >>>> There is already an inconsistency in between these; as with above any >>>> system that uses both request() and request_specific() will be suffering >>>> from intermittent failures due to probe ordering. >>>> >>>>> one: >>>>> -hwspin_lock_request() -> returns Id#0 (exclusive) >>>>> -hwspin_lock_request() -> returns Id#1 (exclusive) >>>>> -hwspin_lock_request_specific(0) -> returns Id#0 and makes Id#0 shared >>>>> Honestly I am not sure that this is a real issue, but it's better to have it >>>>> in mind before we take ay decision >>> Wouldn't it be actually simpler to just introduce a new specific API >>> variant for this, similar to the reset core for example (it uses a >>> separate exclusive API), without having to modify the bindings at all. >>> It is just a case of your driver using the right API, and the core can >>> be modified to use the additional tag semantics based on the API. It >>> should avoid any confusion with say using a different second cell value >>> for the same lock in two different nodes. >>> >> But this implies that there is an actual need to hold these locks >> exclusively. Given that they are (except for the raw case) all wrapped >> by Linux locking primitives there shouldn't be a problem sharing a lock >> (except possibly for the raw case). > Yes agreed, the HWLOCK_RAW and HWLOCK_IN_ATOMIC cases are unprotected. I > am still trying to understand better the usecase to see if the same lock > is being multiplexed for different protection contexts, or if all of > them are protecting the same context. Here are two different examples that explain the need for changes. In both cases the Linux clients are talking to a single entity on the remote-side. Example 1: exti: interrupt-controller@5000d000 { compatible = "st,stm32mp1-exti", "syscon"; interrupt-controller; #interrupt-cells = <2>; reg = <0x5000d000 0x400>; hwlocks = <&hsem 1>; }; The two drivers (stm32mp1-exti and syscon) refer to the same hwlock. With the current hwspinlock implementation, only the first driver succeeds in requesting (hwspin_lock_request_specific) the hwlock. The second request fails. Here, we really need to share the hwlock between the two drivers. Note: hardware spinlock support for regmap was 'recently' introduced in 4.15 see https://lore.kernel.org/patchwork/patch/845941/ Example 2: Here it is more a question of optimization : we want to save the number of hwlocks used to protect resources, using an unique hwlock to protect all pinctrl resources: pinctrl: pin-controller@50002000 { compatible = "st,stm32mp157-pinctrl"; ranges = <0 0x50002000 0xa400>; hwlocks = <&hsem 0 1>; pinctrl_z: pin-controller-z@54004000 { compatible = "st,stm32mp157-z-pinctrl"; ranges = <0 0x54004000 0x400>; pins-are-numbered; hwlocks = <&hsem 0 1>; > >> I agree that we shouldn't specify this property in DT - if anything it >> should be a variant of the API. If we decide to add a 'shared' API, then, what about the generic regmap driver? In the context of above example1, this would require to update the regmap driver. But would this be acceptable for any driver using syscon/regmap? I think it is better to keep the existing API (modifying it so it always allows hwlocks sharing, so no need for bindings update) than adding another API. >> >>> If you are sharing a hwlock on the Linux side, surely your driver should >>> be aware that it is a shared lock. The tag can be set during the first >>> request API, and you look through both tags when giving out a handle. >>> >> Why would the driver need to know about it? > Just the semantics if we were to support single user vs multiple users > on Linux-side to even get a handle. Your point is that this may be moot > since we have protection anyway other than the raw cases. But we need to > be able to have the same API work across all cases. > > So far, it had mostly been that there would be one user on Linux > competing with other equivalent peer entities on different processors. > It is not common to have multiple users since these protection schemes > are usually needed only at the lowest levels of a stack, so the > exclusive handle stuff had been sufficient. > >>> Obviously, the hwspin_lock_request() API usage semantics always had the >>> implied additional need for communicating the lock id to the other peer >>> entity, so a realistic usage is most always the specific API variant. I >>> doubt this API would be of much use for the shared driver usage. This >>> also implies that the client user does not care about specifying a lock >>> in DT. >>> >> Afaict if the lock are shared then there shouldn't be a problem with >> some clients using the request API and others request_specific(). As any >> collisions would simply mean that there are more contention on the lock. >> >> With the current exclusive model that is not possible and the success of >> the request_specific will depend on probe order. >> >> But perhaps it should be explicitly prohibited to use both APIs on the >> same hwspinlock instance? > Yeah, they are meant to be complimentary usage, though I doubt we will > ever have any realistic users for the generic API if we haven't had a > usage so far. I had posted a concept of reserved locks long back [1] to > keep away certain locks from the generic requestor, but dropped it since > we did not have an actual use-case needing it. > > regards > Suman > > [1] https://lwn.net/Articles/611944/
Hi Fabien, On 8/7/19 3:39 AM, Fabien DESSENNE wrote: > Hi > > On 06/08/2019 11:30 PM, Suman Anna wrote: >> On 8/6/19 1:21 PM, Bjorn Andersson wrote: >>> On Tue 06 Aug 10:38 PDT 2019, Suman Anna wrote: >>> >>>> Hi Fabien, >>>> >>>> On 8/5/19 12:46 PM, Bjorn Andersson wrote: >>>>> On Mon 05 Aug 01:48 PDT 2019, Fabien DESSENNE wrote: >>>>> >>>>>> On 01/08/2019 9:14 PM, Bjorn Andersson wrote: >>>>>>> On Wed 13 Mar 08:50 PDT 2019, Fabien Dessenne wrote: >>> [..] >>>>>> B/ This would introduce some inconsistency between the two 'request' API >>>>>> which are hwspin_lock_request() and hwspin_lock_request_specific(). >>>>>> hwspin_lock_request() looks for an unused lock, so requests for an exclusive >>>>>> usage. On the other side, request_specific() would request shared locks. >>>>>> Worst the following sequence can transform an exclusive usage into a shared >>>>>> >>>>> There is already an inconsistency in between these; as with above any >>>>> system that uses both request() and request_specific() will be suffering >>>>> from intermittent failures due to probe ordering. >>>>> >>>>>> one: >>>>>> -hwspin_lock_request() -> returns Id#0 (exclusive) >>>>>> -hwspin_lock_request() -> returns Id#1 (exclusive) >>>>>> -hwspin_lock_request_specific(0) -> returns Id#0 and makes Id#0 shared >>>>>> Honestly I am not sure that this is a real issue, but it's better to have it >>>>>> in mind before we take ay decision >>>> Wouldn't it be actually simpler to just introduce a new specific API >>>> variant for this, similar to the reset core for example (it uses a >>>> separate exclusive API), without having to modify the bindings at all. >>>> It is just a case of your driver using the right API, and the core can >>>> be modified to use the additional tag semantics based on the API. It >>>> should avoid any confusion with say using a different second cell value >>>> for the same lock in two different nodes. >>>> >>> But this implies that there is an actual need to hold these locks >>> exclusively. Given that they are (except for the raw case) all wrapped >>> by Linux locking primitives there shouldn't be a problem sharing a lock >>> (except possibly for the raw case). >> Yes agreed, the HWLOCK_RAW and HWLOCK_IN_ATOMIC cases are unprotected. I >> am still trying to understand better the usecase to see if the same lock >> is being multiplexed for different protection contexts, or if all of >> them are protecting the same context. > > > Here are two different examples that explain the need for changes. > In both cases the Linux clients are talking to a single entity on the > remote-side. > > Example 1: > exti: interrupt-controller@5000d000 { > compatible = "st,stm32mp1-exti", "syscon"; > interrupt-controller; > #interrupt-cells = <2>; > reg = <0x5000d000 0x400>; > hwlocks = <&hsem 1>; > }; > The two drivers (stm32mp1-exti and syscon) refer to the same hwlock. > With the current hwspinlock implementation, only the first driver succeeds > in requesting (hwspin_lock_request_specific) the hwlock. The second request > fails. > Here, we really need to share the hwlock between the two drivers. > Note: hardware spinlock support for regmap was 'recently' introduced in 4.15 > see https://lore.kernel.org/patchwork/patch/845941/ > > > > Example 2: > Here it is more a question of optimization : we want to save the number of > hwlocks used to protect resources, using an unique hwlock to protect all > pinctrl resources: > pinctrl: pin-controller@50002000 { > compatible = "st,stm32mp157-pinctrl"; > ranges = <0 0x50002000 0xa400>; > hwlocks = <&hsem 0 1>; > > pinctrl_z: pin-controller-z@54004000 { > compatible = "st,stm32mp157-z-pinctrl"; > ranges = <0 0x54004000 0x400>; > pins-are-numbered; > hwlocks = <&hsem 0 1>; Thanks for the examples. > >> >>> I agree that we shouldn't specify this property in DT - if anything it >>> should be a variant of the API. > > > If we decide to add a 'shared' API, then, what about the generic regmap > driver? > > In the context of above example1, this would require to update the > regmap driver. > > But would this be acceptable for any driver using syscon/regmap? > > > I think it is better to keep the existing API (modifying it so it always > allows > > hwlocks sharing, so no need for bindings update) than adding another API. For your usecases, you would definitely need the syscon/regmap behavior to be shared right. Whether we introduce a 'shared' API or an 'exclusive' API and change the current API behavior to shared, it is definitely a case-by-case usage scenario for the existing drivers and usage right. The main contention point is what to do with the unprotected usecases like Bjorn originally pointed out. regards Suman > > > >>> >>>> If you are sharing a hwlock on the Linux side, surely your driver should >>>> be aware that it is a shared lock. The tag can be set during the first >>>> request API, and you look through both tags when giving out a handle. >>>> >>> Why would the driver need to know about it? >> Just the semantics if we were to support single user vs multiple users >> on Linux-side to even get a handle. Your point is that this may be moot >> since we have protection anyway other than the raw cases. But we need to >> be able to have the same API work across all cases. >> >> So far, it had mostly been that there would be one user on Linux >> competing with other equivalent peer entities on different processors. >> It is not common to have multiple users since these protection schemes >> are usually needed only at the lowest levels of a stack, so the >> exclusive handle stuff had been sufficient. >> >>>> Obviously, the hwspin_lock_request() API usage semantics always had the >>>> implied additional need for communicating the lock id to the other peer >>>> entity, so a realistic usage is most always the specific API variant. I >>>> doubt this API would be of much use for the shared driver usage. This >>>> also implies that the client user does not care about specifying a lock >>>> in DT. >>>> >>> Afaict if the lock are shared then there shouldn't be a problem with >>> some clients using the request API and others request_specific(). As any >>> collisions would simply mean that there are more contention on the lock. >>> >>> With the current exclusive model that is not possible and the success of >>> the request_specific will depend on probe order. >>> >>> But perhaps it should be explicitly prohibited to use both APIs on the >>> same hwspinlock instance? >> Yeah, they are meant to be complimentary usage, though I doubt we will >> ever have any realistic users for the generic API if we haven't had a >> usage so far. I had posted a concept of reserved locks long back [1] to >> keep away certain locks from the generic requestor, but dropped it since >> we did not have an actual use-case needing it. >> >> regards >> Suman >> >> [1] https://lwn.net/Articles/611944/
On 07/08/2019 6:19 PM, Suman Anna wrote: > Hi Fabien, > > On 8/7/19 3:39 AM, Fabien DESSENNE wrote: >> Hi >> >> On 06/08/2019 11:30 PM, Suman Anna wrote: >>> On 8/6/19 1:21 PM, Bjorn Andersson wrote: >>>> On Tue 06 Aug 10:38 PDT 2019, Suman Anna wrote: >>>> >>>>> Hi Fabien, >>>>> >>>>> On 8/5/19 12:46 PM, Bjorn Andersson wrote: >>>>>> On Mon 05 Aug 01:48 PDT 2019, Fabien DESSENNE wrote: >>>>>> >>>>>>> On 01/08/2019 9:14 PM, Bjorn Andersson wrote: >>>>>>>> On Wed 13 Mar 08:50 PDT 2019, Fabien Dessenne wrote: >>>> [..] >>>>>>> B/ This would introduce some inconsistency between the two 'request' API >>>>>>> which are hwspin_lock_request() and hwspin_lock_request_specific(). >>>>>>> hwspin_lock_request() looks for an unused lock, so requests for an exclusive >>>>>>> usage. On the other side, request_specific() would request shared locks. >>>>>>> Worst the following sequence can transform an exclusive usage into a shared >>>>>>> >>>>>> There is already an inconsistency in between these; as with above any >>>>>> system that uses both request() and request_specific() will be suffering >>>>>> from intermittent failures due to probe ordering. >>>>>> >>>>>>> one: >>>>>>> -hwspin_lock_request() -> returns Id#0 (exclusive) >>>>>>> -hwspin_lock_request() -> returns Id#1 (exclusive) >>>>>>> -hwspin_lock_request_specific(0) -> returns Id#0 and makes Id#0 shared >>>>>>> Honestly I am not sure that this is a real issue, but it's better to have it >>>>>>> in mind before we take ay decision >>>>> Wouldn't it be actually simpler to just introduce a new specific API >>>>> variant for this, similar to the reset core for example (it uses a >>>>> separate exclusive API), without having to modify the bindings at all. >>>>> It is just a case of your driver using the right API, and the core can >>>>> be modified to use the additional tag semantics based on the API. It >>>>> should avoid any confusion with say using a different second cell value >>>>> for the same lock in two different nodes. >>>>> >>>> But this implies that there is an actual need to hold these locks >>>> exclusively. Given that they are (except for the raw case) all wrapped >>>> by Linux locking primitives there shouldn't be a problem sharing a lock >>>> (except possibly for the raw case). >>> Yes agreed, the HWLOCK_RAW and HWLOCK_IN_ATOMIC cases are unprotected. I >>> am still trying to understand better the usecase to see if the same lock >>> is being multiplexed for different protection contexts, or if all of >>> them are protecting the same context. >> >> Here are two different examples that explain the need for changes. >> In both cases the Linux clients are talking to a single entity on the >> remote-side. >> >> Example 1: >> exti: interrupt-controller@5000d000 { >> compatible = "st,stm32mp1-exti", "syscon"; >> interrupt-controller; >> #interrupt-cells = <2>; >> reg = <0x5000d000 0x400>; >> hwlocks = <&hsem 1>; >> }; >> The two drivers (stm32mp1-exti and syscon) refer to the same hwlock. >> With the current hwspinlock implementation, only the first driver succeeds >> in requesting (hwspin_lock_request_specific) the hwlock. The second request >> fails. >> Here, we really need to share the hwlock between the two drivers. >> Note: hardware spinlock support for regmap was 'recently' introduced in 4.15 >> see https://lore.kernel.org/patchwork/patch/845941/ >> >> >> >> Example 2: >> Here it is more a question of optimization : we want to save the number of >> hwlocks used to protect resources, using an unique hwlock to protect all >> pinctrl resources: >> pinctrl: pin-controller@50002000 { >> compatible = "st,stm32mp157-pinctrl"; >> ranges = <0 0x50002000 0xa400>; >> hwlocks = <&hsem 0 1>; >> >> pinctrl_z: pin-controller-z@54004000 { >> compatible = "st,stm32mp157-z-pinctrl"; >> ranges = <0 0x54004000 0x400>; >> pins-are-numbered; >> hwlocks = <&hsem 0 1>; > Thanks for the examples. > >>>> I agree that we shouldn't specify this property in DT - if anything it >>>> should be a variant of the API. >> >> If we decide to add a 'shared' API, then, what about the generic regmap >> driver? >> >> In the context of above example1, this would require to update the >> regmap driver. >> >> But would this be acceptable for any driver using syscon/regmap? >> >> >> I think it is better to keep the existing API (modifying it so it always >> allows >> >> hwlocks sharing, so no need for bindings update) than adding another API. > For your usecases, you would definitely need the syscon/regmap behavior > to be shared right. Whether we introduce a 'shared' API or an > 'exclusive' API and change the current API behavior to shared, it is > definitely a case-by-case usage scenario for the existing drivers and > usage right. The main contention point is what to do with the > unprotected usecases like Bjorn originally pointed out. OK, I see : the hwspinlock framework does not offer any lock protection with the RAW/IN_ATOMIC modes. This is an issue if several different 'local' drivers try to get a shared lock in the same time. And this is a personal problem since I need to use shared locks in ...atomic mode. I have tried to see how it is possible to put a constraint on the callers, just like this is documented for the RAW mode which is: "Caution: If the mode is HWLOCK_RAW, that means user must protect the routine of getting hardware lock with mutex or spinlock.." I do not think that it is acceptable to ask several drivers to share a common mutex/spinlock for shared locks. But I think about another option: the driver implementing the trylock ops may offer such protection. This is the case if the driver returns "busy" if the lock is already taken, not only by the remote processor, but also by the local host. So what do you think about adding such a documentation note : "Caution : the HWLOCK_RAW / HWLOCK_IN_ATOMIC modes shall not be used with shared locks unless the hwspinlock driver supports local lock protection" Optionally, we may add a "local_lock_protection" flag in the hwspinlock_device struct, set by the driver before it calls hwspin_lock_register(). This flag can then be checked by hwspinlock core to allow/deny use of shared locks in the raw/atomic modes. Let me know what you think about it. BR Fabien > > regards > Suman > >> >> >>>>> If you are sharing a hwlock on the Linux side, surely your driver should >>>>> be aware that it is a shared lock. The tag can be set during the first >>>>> request API, and you look through both tags when giving out a handle. >>>>> >>>> Why would the driver need to know about it? >>> Just the semantics if we were to support single user vs multiple users >>> on Linux-side to even get a handle. Your point is that this may be moot >>> since we have protection anyway other than the raw cases. But we need to >>> be able to have the same API work across all cases. >>> >>> So far, it had mostly been that there would be one user on Linux >>> competing with other equivalent peer entities on different processors. >>> It is not common to have multiple users since these protection schemes >>> are usually needed only at the lowest levels of a stack, so the >>> exclusive handle stuff had been sufficient. >>> >>>>> Obviously, the hwspin_lock_request() API usage semantics always had the >>>>> implied additional need for communicating the lock id to the other peer >>>>> entity, so a realistic usage is most always the specific API variant. I >>>>> doubt this API would be of much use for the shared driver usage. This >>>>> also implies that the client user does not care about specifying a lock >>>>> in DT. >>>>> >>>> Afaict if the lock are shared then there shouldn't be a problem with >>>> some clients using the request API and others request_specific(). As any >>>> collisions would simply mean that there are more contention on the lock. >>>> >>>> With the current exclusive model that is not possible and the success of >>>> the request_specific will depend on probe order. >>>> >>>> But perhaps it should be explicitly prohibited to use both APIs on the >>>> same hwspinlock instance? >>> Yeah, they are meant to be complimentary usage, though I doubt we will >>> ever have any realistic users for the generic API if we haven't had a >>> usage so far. I had posted a concept of reserved locks long back [1] to >>> keep away certain locks from the generic requestor, but dropped it since >>> we did not have an actual use-case needing it. >>> >>> regards >>> Suman >>> >>> [1] https://lwn.net/Articles/611944/
On Thu 08 Aug 05:52 PDT 2019, Fabien DESSENNE wrote: > > On 07/08/2019 6:19 PM, Suman Anna wrote: > > Hi Fabien, > > > > On 8/7/19 3:39 AM, Fabien DESSENNE wrote: > >> Hi > >> > >> On 06/08/2019 11:30 PM, Suman Anna wrote: > >>> On 8/6/19 1:21 PM, Bjorn Andersson wrote: > >>>> On Tue 06 Aug 10:38 PDT 2019, Suman Anna wrote: > >>>> > >>>>> Hi Fabien, > >>>>> > >>>>> On 8/5/19 12:46 PM, Bjorn Andersson wrote: > >>>> I agree that we shouldn't specify this property in DT - if anything it > >>>> should be a variant of the API. > >> > >> If we decide to add a 'shared' API, then, what about the generic regmap > >> driver? > >> > >> In the context of above example1, this would require to update the > >> regmap driver. > >> > >> But would this be acceptable for any driver using syscon/regmap? > >> > >> > >> I think it is better to keep the existing API (modifying it so it always > >> allows > >> > >> hwlocks sharing, so no need for bindings update) than adding another API. > > For your usecases, you would definitely need the syscon/regmap behavior > > to be shared right. Whether we introduce a 'shared' API or an > > 'exclusive' API and change the current API behavior to shared, it is > > definitely a case-by-case usage scenario for the existing drivers and > > usage right. The main contention point is what to do with the > > unprotected usecases like Bjorn originally pointed out. > > OK, I see : the hwspinlock framework does not offer any lock protection > with the RAW/IN_ATOMIC modes. > This is an issue if several different 'local' drivers try to get a > shared lock in the same time. > And this is a personal problem since I need to use shared locks in > ...atomic mode. > Why can't you use HWLOCK_IRQSTATE in this mode? > I have tried to see how it is possible to put a constraint on the > callers, just like this is documented for the RAW mode which is: > "Caution: If the mode is HWLOCK_RAW, that means user must protect > the routine > of getting hardware lock with mutex or spinlock.." > I do not think that it is acceptable to ask several drivers to share a > common mutex/spinlock for shared locks. No it's not. > But I think about another option: the driver implementing the trylock > ops may offer such protection. This is the case if the driver returns > "busy" if the lock is already taken, not only by the remote processor, > but also by the local host. > I think it's typical for hwspinlock hardware to not be able to distinguish between different clients within Linux, so we would need to wrap the usage in some construct that ensures mutual exclusion in Linux - like a spinlock... > So what do you think about adding such a documentation note : > "Caution : the HWLOCK_RAW / HWLOCK_IN_ATOMIC modes shall not be used > with shared locks unless the hwspinlock driver supports local lock > protection" > But having local lock protection in the hwspinlock driver would defeat the purpose of HWLOCK_RAW. Also this kind of warning will at best be consumed by the client driver authors, it will not be read by the dts authors. Regards, Bjorn > Optionally, we may add a "local_lock_protection" flag in the > hwspinlock_device struct, set by the driver before it calls > hwspin_lock_register(). > This flag can then be checked by hwspinlock core to allow/deny use of > shared locks in the raw/atomic modes. > > Let me know what you think about it. > > BR > > Fabien > > > > > regards > > Suman > > > >> > >> > >>>>> If you are sharing a hwlock on the Linux side, surely your driver should > >>>>> be aware that it is a shared lock. The tag can be set during the first > >>>>> request API, and you look through both tags when giving out a handle. > >>>>> > >>>> Why would the driver need to know about it? > >>> Just the semantics if we were to support single user vs multiple users > >>> on Linux-side to even get a handle. Your point is that this may be moot > >>> since we have protection anyway other than the raw cases. But we need to > >>> be able to have the same API work across all cases. > >>> > >>> So far, it had mostly been that there would be one user on Linux > >>> competing with other equivalent peer entities on different processors. > >>> It is not common to have multiple users since these protection schemes > >>> are usually needed only at the lowest levels of a stack, so the > >>> exclusive handle stuff had been sufficient. > >>> > >>>>> Obviously, the hwspin_lock_request() API usage semantics always had the > >>>>> implied additional need for communicating the lock id to the other peer > >>>>> entity, so a realistic usage is most always the specific API variant. I > >>>>> doubt this API would be of much use for the shared driver usage. This > >>>>> also implies that the client user does not care about specifying a lock > >>>>> in DT. > >>>>> > >>>> Afaict if the lock are shared then there shouldn't be a problem with > >>>> some clients using the request API and others request_specific(). As any > >>>> collisions would simply mean that there are more contention on the lock. > >>>> > >>>> With the current exclusive model that is not possible and the success of > >>>> the request_specific will depend on probe order. > >>>> > >>>> But perhaps it should be explicitly prohibited to use both APIs on the > >>>> same hwspinlock instance? > >>> Yeah, they are meant to be complimentary usage, though I doubt we will > >>> ever have any realistic users for the generic API if we haven't had a > >>> usage so far. I had posted a concept of reserved locks long back [1] to > >>> keep away certain locks from the generic requestor, but dropped it since > >>> we did not have an actual use-case needing it. > >>> > >>> regards > >>> Suman > >>> > >>> [1] https://lwn.net/Articles/611944/
Hi Bjorn, On 08/08/2019 5:37 PM, Bjorn Andersson wrote: > On Thu 08 Aug 05:52 PDT 2019, Fabien DESSENNE wrote: > >> On 07/08/2019 6:19 PM, Suman Anna wrote: >>> Hi Fabien, >>> >>> On 8/7/19 3:39 AM, Fabien DESSENNE wrote: >>>> Hi >>>> >>>> On 06/08/2019 11:30 PM, Suman Anna wrote: >>>>> On 8/6/19 1:21 PM, Bjorn Andersson wrote: >>>>>> On Tue 06 Aug 10:38 PDT 2019, Suman Anna wrote: >>>>>> >>>>>>> Hi Fabien, >>>>>>> >>>>>>> On 8/5/19 12:46 PM, Bjorn Andersson wrote: >>>>>> I agree that we shouldn't specify this property in DT - if anything it >>>>>> should be a variant of the API. >>>> If we decide to add a 'shared' API, then, what about the generic regmap >>>> driver? >>>> >>>> In the context of above example1, this would require to update the >>>> regmap driver. >>>> >>>> But would this be acceptable for any driver using syscon/regmap? >>>> >>>> >>>> I think it is better to keep the existing API (modifying it so it always >>>> allows >>>> >>>> hwlocks sharing, so no need for bindings update) than adding another API. >>> For your usecases, you would definitely need the syscon/regmap behavior >>> to be shared right. Whether we introduce a 'shared' API or an >>> 'exclusive' API and change the current API behavior to shared, it is >>> definitely a case-by-case usage scenario for the existing drivers and >>> usage right. The main contention point is what to do with the >>> unprotected usecases like Bjorn originally pointed out. >> OK, I see : the hwspinlock framework does not offer any lock protection >> with the RAW/IN_ATOMIC modes. >> This is an issue if several different 'local' drivers try to get a >> shared lock in the same time. >> And this is a personal problem since I need to use shared locks in >> ...atomic mode. >> > Why can't you use HWLOCK_IRQSTATE in this mode? > >> I have tried to see how it is possible to put a constraint on the >> callers, just like this is documented for the RAW mode which is: >> "Caution: If the mode is HWLOCK_RAW, that means user must protect >> the routine >> of getting hardware lock with mutex or spinlock.." >> I do not think that it is acceptable to ask several drivers to share a >> common mutex/spinlock for shared locks. > No it's not. > >> But I think about another option: the driver implementing the trylock >> ops may offer such protection. This is the case if the driver returns >> "busy" if the lock is already taken, not only by the remote processor, >> but also by the local host. >> > I think it's typical for hwspinlock hardware to not be able to > distinguish between different clients within Linux, so we would need to Agree with that, let's forget this idea. > wrap the usage in some construct that ensures mutual exclusion in Linux > - like a spinlock... > >> So what do you think about adding such a documentation note : >> "Caution : the HWLOCK_RAW / HWLOCK_IN_ATOMIC modes shall not be used >> with shared locks unless the hwspinlock driver supports local lock >> protection" >> > But having local lock protection in the hwspinlock driver would defeat > the purpose of HWLOCK_RAW. My understanding is that the purpose of the RAW mode is to allow the user to do some time-consuming or sleepable operations under the hardware spinlock protection. This is probably the reason why the RAW mode does not uses any spinlock is used in RAW mode. But I do not think that this is a requirement to not use any local protection. So, in this mode, instead of using a spinlock, what about calling the atomic bitop test_and_set_bit() ? This would ensure safe concurrency between the hwspinlock linux users, and will respect the purpose of the RAW mode. Let me know if this is acceptable. BR Fabien > > Also this kind of warning will at best be consumed by the client driver > authors, it will not be read by the dts authors. > > Regards, > Bjorn > >> Optionally, we may add a "local_lock_protection" flag in the >> hwspinlock_device struct, set by the driver before it calls >> hwspin_lock_register(). >> This flag can then be checked by hwspinlock core to allow/deny use of >> shared locks in the raw/atomic modes. >> >> Let me know what you think about it. >> >> BR >> >> Fabien >> >>> regards >>> Suman >>> >>>> >>>>>>> If you are sharing a hwlock on the Linux side, surely your driver should >>>>>>> be aware that it is a shared lock. The tag can be set during the first >>>>>>> request API, and you look through both tags when giving out a handle. >>>>>>> >>>>>> Why would the driver need to know about it? >>>>> Just the semantics if we were to support single user vs multiple users >>>>> on Linux-side to even get a handle. Your point is that this may be moot >>>>> since we have protection anyway other than the raw cases. But we need to >>>>> be able to have the same API work across all cases. >>>>> >>>>> So far, it had mostly been that there would be one user on Linux >>>>> competing with other equivalent peer entities on different processors. >>>>> It is not common to have multiple users since these protection schemes >>>>> are usually needed only at the lowest levels of a stack, so the >>>>> exclusive handle stuff had been sufficient. >>>>> >>>>>>> Obviously, the hwspin_lock_request() API usage semantics always had the >>>>>>> implied additional need for communicating the lock id to the other peer >>>>>>> entity, so a realistic usage is most always the specific API variant. I >>>>>>> doubt this API would be of much use for the shared driver usage. This >>>>>>> also implies that the client user does not care about specifying a lock >>>>>>> in DT. >>>>>>> >>>>>> Afaict if the lock are shared then there shouldn't be a problem with >>>>>> some clients using the request API and others request_specific(). As any >>>>>> collisions would simply mean that there are more contention on the lock. >>>>>> >>>>>> With the current exclusive model that is not possible and the success of >>>>>> the request_specific will depend on probe order. >>>>>> >>>>>> But perhaps it should be explicitly prohibited to use both APIs on the >>>>>> same hwspinlock instance? >>>>> Yeah, they are meant to be complimentary usage, though I doubt we will >>>>> ever have any realistic users for the generic API if we haven't had a >>>>> usage so far. I had posted a concept of reserved locks long back [1] to >>>>> keep away certain locks from the generic requestor, but dropped it since >>>>> we did not have an actual use-case needing it. >>>>> >>>>> regards >>>>> Suman >>>>> >>>>> [1] https://lwn.net/Articles/611944/
The current implementation does not allow two different devices to use a common hwspinlock. This patch set proposes to have, as an option, some hwspinlocks shared between several users. Below is an example that explain the need for this: exti: interrupt-controller@5000d000 { compatible = "st,stm32mp1-exti", "syscon"; interrupt-controller; #interrupt-cells = <2>; reg = <0x5000d000 0x400>; hwlocks = <&hsem 1>; }; The two drivers (stm32mp1-exti and syscon) refer to the same hwlock. With the current hwspinlock implementation, only the first driver succeeds in requesting (hwspin_lock_request_specific) the hwlock. The second request fails. The proposed approach does not modify the API, but extends the DT 'hwlocks' property with a second optional parameter (the first one identifies an hwlock) that specifies whether an hwlock is requested for exclusive usage (current behavior) or can be shared between several users. Examples: hwlocks = <&hsem 8>; Ref to hwlock #8 for exclusive usage hwlocks = <&hsem 8 0>; Ref to hwlock #8 for exclusive (0) usage hwlocks = <&hsem 8 1>; Ref to hwlock #8 for shared (1) usage As a constraint, the #hwlock-cells value must be 1 or 2. In the current implementation, this can have theorically any value but: - all of the exisiting drivers use the same value : 1. - the framework supports only one value : 1 (see implementation of of_hwspin_lock_simple_xlate()) Hence, it shall not be a problem to restrict this value to 1 or 2 since it won't break any driver. Fabien Dessenne (6): dt-bindings: hwlock: add support of shared locks hwspinlock: allow sharing of hwspinlocks dt-bindings: hwlock: update STM32 #hwlock-cells value ARM: dts: stm32: Add hwspinlock node for stm32mp157 SoC ARM: dts: stm32: Add hwlock for irqchip on stm32mp157 ARM: dts: stm32: hwlocks for GPIO for stm32mp157 .../devicetree/bindings/hwlock/hwlock.txt | 27 +++++-- .../bindings/hwlock/st,stm32-hwspinlock.txt | 6 +- Documentation/hwspinlock.txt | 10 ++- arch/arm/boot/dts/stm32mp157-pinctrl.dtsi | 2 + arch/arm/boot/dts/stm32mp157c.dtsi | 10 +++ drivers/hwspinlock/hwspinlock_core.c | 82 +++++++++++++++++----- drivers/hwspinlock/hwspinlock_internal.h | 2 + 7 files changed, 108 insertions(+), 31 deletions(-)