| Message ID | 1687955688-20809-1-git-send-email-quic_mojha@quicinc.com |
|---|---|
| State | New |
| Headers | show |
On Wed, Jun 28, 2023 at 9:45 AM Greg KH <gregkh@linuxfoundation.org> wrote: > > On Wed, Jun 28, 2023 at 06:04:27PM +0530, Mukesh Ojha wrote: > > Minidump is a best effort mechanism to collect useful and predefined data > > for first level of debugging on end user devices running on Qualcomm SoCs. > > It is built on the premise that System on Chip (SoC) or subsystem part of > > SoC crashes, due to a range of hardware and software bugs. Hence, the > > ability to collect accurate data is only a best-effort. The data collected > > could be invalid or corrupted, data collection itself could fail, and so on. > > > > Qualcomm devices in engineering mode provides a mechanism for generating > > full system ramdumps for post mortem debugging. But in some cases it's > > however not feasible to capture the entire content of RAM. The minidump > > mechanism provides the means for selecting which snippets should be > > included in the ramdump. > > > > Minidump kernel driver implementation is divided into two parts for > > simplicity, one is minidump core which can also be called minidump > > frontend(As API gets exported from this driver for registration with > > backend) and the other part is minidump backend i.e, where the underlying > > implementation of minidump will be there. There could be different way > > how the backend is implemented like Shared memory, Memory mapped IO > > or Resource manager(gunyah) based where the guest region information is > > passed to hypervisor via hypercalls. > > > > Minidump Client-1 Client-2 Client-5 Client-n > > | | | | > > | | ... | ... | > > | | | | > > | | | | > > | | | | > > | | | | > > | | | | > > | | | | > > | +---+--------------+----+ | > > +-----------+ qcom_minidump(core) +--------+ > > | | > > +------+-----+------+---+ > > | | | > > | | | > > +---------------+ | +--------------------+ > > | | | > > | | | > > | | | > > v v v > > +-------------------+ +-------------------+ +------------------+ > > |qcom_minidump_smem | |qcom_minidump_mmio | | qcom_minidump_rm | > > | | | | | | > > +-------------------+ +-------------------+ +------------------+ > > Shared memory Memory mapped IO Resource manager > > (backend) (backend) (backend) > > > > > > Here, we will be giving all analogy of backend with SMEM as it is the > > only implemented backend at present but general idea remains the same. > > If you only have one "backend" then you don't need the extra compexity > here at all, just remove that whole middle layer please and make this > much simpler and smaller and easier to review and possibly accept. pstore already supports backends. Why aren't the above backends just pstore backends rather than having an intermediate pstore backend in RAM which then somehow gets moved into these minidump backends. > We don't add layers when they are not needed, and never when there is no > actual user. If you need the extra "complexity" later, then add it > later when it is needed as who knows when that will ever be. > > Please redo this series based on that, thanks. My bigger issue with this whole series is what would this all look like if every SoC vendor upstreamed their own custom dumping mechanism. That would be a mess. (I have similar opinions on the $soc-vendor hypervisors.) Rob
On Wed, Jun 28, 2023 at 6:36 AM Mukesh Ojha <quic_mojha@quicinc.com> wrote: > > Add the qualcomm minidump guide for the users which > tries to cover the dependency and the way to test > and collect minidump on Qualcomm supported platforms. > > Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> > --- > Documentation/admin-guide/index.rst | 1 + > Documentation/admin-guide/qcom_minidump.rst | 293 ++++++++++++++++++++++++++++ > 2 files changed, 294 insertions(+) > create mode 100644 Documentation/admin-guide/qcom_minidump.rst > > diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst > index 43ea35613dfc..251d070486c2 100644 > --- a/Documentation/admin-guide/index.rst > +++ b/Documentation/admin-guide/index.rst > @@ -120,6 +120,7 @@ configure specific aspects of kernel behavior to your liking. > perf-security > pm/index > pnp > + qcom_minidump > rapidio > ras > rtc > diff --git a/Documentation/admin-guide/qcom_minidump.rst b/Documentation/admin-guide/qcom_minidump.rst > new file mode 100644 > index 000000000000..a3a8cfee4555 > --- /dev/null > +++ b/Documentation/admin-guide/qcom_minidump.rst > @@ -0,0 +1,293 @@ > +Qualcomm Minidump Feature > +========================= > + > +Introduction > +------------ > + > +Minidump is a best effort mechanism to collect useful and predefined > +data for first level of debugging on end user devices running on > +Qualcomm SoCs. It is built on the premise that System on Chip (SoC) > +or subsystem part of SoC crashes, due to a range of hardware and > +software bugs. Hence, the ability to collect accurate data is only > +a best-effort. The data collected could be invalid or corrupted, data > +collection itself could fail, and so on. > + > +Qualcomm devices in engineering mode provides a mechanism for generating > +full system RAM dumps for post-mortem debugging. But in some cases it's > +however not feasible to capture the entire content of RAM. The minidump > +mechanism provides the means for selecting region should be included in > +the ramdump. > + > +:: > + > + +-----------------------------------------------+ > + | DDR +-------------+ | > + | | SS0-ToC| | > + | +----------------+ +----------------+ | | > + | |Shared memory | | SS1-ToC| | | > + | |(SMEM) | | | | | > + | | | +-->|--------+ | | | > + | |G-ToC | | | SS-ToC \ | | | > + | |+-------------+ | | | +-----------+ | | | > + | ||-------------| | | | |-----------| | | | > + | || SS0-ToC | | | +-|<|SS1 region1| | | | > + | ||-------------| | | | | |-----------| | | | > + | || SS1-ToC |-|>+ | | |SS1 region2| | | | > + | ||-------------| | | | |-----------| | | | > + | || SS2-ToC | | | | | ... | | | | > + | ||-------------| | | | |-----------| | | | > + | || ... | | |-|<|SS1 regionN| | | | > + | ||-------------| | | | |-----------| | | | > + | || SSn-ToC | | | | +-----------+ | | | > + | |+-------------+ | | | | | | > + | | | | |----------------| | | > + | | | +>| regionN | | | > + | | | | |----------------| | | > + | +----------------+ | | | | | > + | | |----------------| | | > + | +>| region1 | | | > + | |----------------| | | > + | | | | | > + | |----------------|-+ | > + | | region5 | | > + | |----------------| | > + | | | | > + | Region information +----------------+ | > + | +---------------+ | > + | |region name | | > + | |---------------| | > + | |region address | | > + | |---------------| | > + | |region size | | > + | +---------------+ | > + +-----------------------------------------------+ > + G-ToC: Global table of contents > + SS-ToC: Subsystem table of contents > + SS0-SSn: Subsystem numbered from 0 to n > + > +It depends on targets how the underlying hardware taking care of the > +implementation part for minidump like above diagram is for shared > +memory and it is possible that this could be implemented via memory > +mapped regions but the general idea remain same. > + > +In this document, SMEM will be used as the backend implementation of > +minidump. > + > +SMEM as backend > +---------------- > + > +The core of minidump feature is part of Qualcomm's boot firmware code. > +It initializes shared memory (SMEM), which is a part of DDR and > +allocates a small section of it to minidump table, i.e. also called > +global table of contents (G-ToC). Each subsystem (APSS, ADSP, ...) has > +its own table of segments to be included in the minidump, all > +references from a descriptor in SMEM (G-ToC). Each segment/region has > +some details like name, physical address and its size etc. and it > +could be anywhere scattered in the DDR. > + > +Minidump kernel driver concept > +------------------------------ > +:: > + > + Minidump Client-1 Client-2 Client-5 Client-n > + | | | | > + | | ... | ... | > + | | | | > + | | | | > + | | | | > + | | | | > + | | | | > + | | | | > + | +---+--------------+----+ | > + +-----------+ qcom_minidump(core) +--------+ > + | | > + +------+-----+------+---+ > + | | | > + | | | > + +---------------+ | +--------------------+ > + | | | > + | | | > + | | | > + v v v > + +-------------------+ +-------------------+ +------------------+ > + |qcom_minidump_smem | |qcom_minidump_mmio | | qcom_minidump_rm | > + | | | | | | > + +-------------------+ +-------------------+ +------------------+ > + Shared memory Memory mapped IO Resource manager > + (backend) (backend) (backend) > + > + > +Kernel implementation of minidump driver is divided into two parts one is, > +the core implementation called frontend driver ``qcom_minidump.c`` and this > +is the driver will be exposing the API for clients and the other part is, > +backend driver and its depends whether it is based on SMEM, MMIO or some > +other way corressponding driver will be hooking itself up with the core > +driver to get itself working. As of now, at a time one and only one backend > +can be attached to the front-end either it is HOST or a guest VM. > + > +Qualcomm minidump kernel driver adds the capability to add Linux region > +to be dumped as part of RAM dump collection. At the moment, shared memory > +driver creates platform device for minidump driver and give a means to > +APSS minidump to initialize itself on probe. > + > +This driver provides ``qcom_minidump_region_register`` and > +``qcom_minidump_region_unregister`` API's to register and unregister > +APSS minidump region. It also gives a mechanism to update physical/virtual > +address for the client whose addresses keeps on changing, e.g., current stack > +address of task keeps on changing on context switch for each core. So these > +clients can update their addresses with ``qcom_minidump_update_region`` > +API. > + > +The driver also supports registration for the clients who came before > +minidump driver was initialized. It maintains pending list of clients > +who came before minidump and once minidump is initialized it registers > +them in one go. > + > +To simplify post-mortem debugging, driver creates and maintain an ELF > +header as first region that gets updated each time a new region gets > +registered. > + > +The solution supports extracting the RAM dump/minidump produced either > +over USB or stored to an attached storage device. > + > +Dependency of minidump kernel driver > +------------------------------------ > + > +It is to note that whole of minidump depends on Qualcomm boot > +firmware whether it supports minidump or not. So, if the minidump > +SMEM ID is present in shared memory, it indicates that minidump > +is supported from boot firmware and it is possible to dump Linux > +(APSS) region as part of minidump collection. > + > +How a kernel client driver can register region with minidump > +------------------------------------------------------------ > + > +Client driver can use ``qcom_minidump_region_register`` API's to > +register and ``qcom_minidump_region_unregister`` to unregister > +their region from minidump driver. > + > +Client needs to fill their region by filling ``qcom_minidump_region`` > +structure object which consists of the region name, region's > +virtual and physical address and its size. > + > +Below is one sample client driver snippet which tries to allocate > +a region from kernel heap of certain size and it writes a certain > +known pattern (that can help in verification after collection > +that we got the exact pattern, what we wrote) and registers it with > +minidump. > + > + .. code-block:: c > + > + #include <soc/qcom/qcom_minidump.h> > + [...] > + > + > + [... inside a function ...] > + struct qcom_minidump_region region; > + > + [...] > + > + client_mem_region = kzalloc(region_size, GFP_KERNEL); > + if (!client_mem_region) > + return -ENOMEM; > + > + [... Just write a pattern ...] > + memset(client_mem_region, 0xAB, region_size); > + > + [... Fill up the region object ...] > + strlcpy(region.name, "REGION_A", sizeof(region.name)); > + region.virt_addr = client_mem_region; > + region.phys_addr = virt_to_phys(client_mem_region); > + region.size = region_size; > + > + ret = qcom_minidump_region_register(®ion); > + if (ret < 0) { > + pr_err("failed to add region in minidump: err: %d\n", ret); > + return ret; > + } > + > + [...] > + > + > +Test > +---- > + > +Existing Qualcomm devices already supports entire RAM dump (also called > +full dump) by writing appropriate value to Qualcomm's top control and > +status register (tcsr) in ``driver/firmware/qcom_scm.c`` . > + > +SCM device Tree bindings required to support download mode > +For example (sm8450) :: > + > + / { > + > + [...] > + > + firmware { > + scm: scm { > + compatible = "qcom,scm-sm8450", "qcom,scm"; > + [... tcsr register ... ] > + qcom,dload-mode = <&tcsr 0x13000>; > + > + [...] > + }; > + }; > + > + [...] > + > + soc: soc@0 { > + > + [...] > + > + tcsr: syscon@1fc0000 { > + compatible = "qcom,sm8450-tcsr", "syscon"; > + reg = <0x0 0x1fc0000 0x0 0x30000>; > + }; > + > + [...] > + }; > + [...] > + > + }; > + > +User of minidump can pass ``qcom_scm.download_mode="mini"`` to kernel > +commandline to set the current download mode to minidump. > +Similarly, ``"full"`` is passed to set the download mode to full dump > +where entire RAM dump will be collected while setting it ``"full,mini"`` > +will collect minidump along with fulldump. > + > +Writing to sysfs node can also be used to set the mode to minidump:: > + > + echo "mini" > /sys/module/qcom_scm/parameter/download_mode > + > +Once the download mode is set, any kind of crash will make the device collect > +respective dump as per set download mode. > + > +Dump collection > +--------------- > + > +The solution supports extracting the minidump produced either over USB or > +stored to an attached storage device. > + > +By default, dumps are downloaded via USB to the attached x86_64 machine > +running PCAT (Qualcomm tool) software. Upon download, we will see > +a set of binary blobs starting with name ``md_*`` in PCAT configured directory > +in x86_64 machine, so for above example from the client it will be So I can't use my QCom laptop or M1 MacBook? This text won't age well, so perhaps reword it. Rob
On Wed, Jun 28, 2023 at 06:04:34PM +0530, Mukesh Ojha wrote: > Add support to update client's region physical/virtual addresses, > which is useful for dynamic loadable modules, dynamic address > changing clients like if we want to collect current stack > information for each core and the current stack is changing on > each sched_switch event, So here virtual/physical address of > the current stack is changing. So, to cover such use cases > add the update region support in minidump driver and the > corresponding smem backend support. > > Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> > --- > drivers/soc/qcom/qcom_minidump.c | 55 +++++++++++++++++++++++++++++++ > drivers/soc/qcom/qcom_minidump_internal.h | 3 ++ > drivers/soc/qcom/qcom_minidump_smem.c | 21 ++++++++++++ > include/soc/qcom/qcom_minidump.h | 5 +++ > 4 files changed, 84 insertions(+) > > diff --git a/drivers/soc/qcom/qcom_minidump.c b/drivers/soc/qcom/qcom_minidump.c > index cfdb63cc29d6..37d6ceb4d85c 100644 > --- a/drivers/soc/qcom/qcom_minidump.c > +++ b/drivers/soc/qcom/qcom_minidump.c > @@ -318,6 +318,61 @@ int qcom_minidump_region_unregister(const struct qcom_minidump_region *region) > } > EXPORT_SYMBOL_GPL(qcom_minidump_region_unregister); > > +/** > + * qcom_minidump_update_region() - Update region information with new physical > + * address and virtual address for already registered region e.g, current task > + * stack for a core keeps on changing on each context switch, there it needs to > + * change registered region with new updated addresses. > + * > + * @region: Should be already registered minidump region. > + * > + * Return: On success, it returns 0 and negative error value on failure. > + */ > +int qcom_minidump_update_region(const struct qcom_minidump_region *region) > +{ > + struct minidump_pregion *md_pregion; > + struct qcom_minidump_region *tmp; > + struct elfhdr *ehdr; > + struct elf_shdr *shdr; > + struct elf_phdr *phdr; > + int idx; > + int ret = 0; > + > + if (!qcom_minidump_valid_region(region)) > + return -EINVAL; > + > + mutex_lock(&md_lock); > + if (!md) { > + md_pregion = check_if_pending_region_exist(region); > + if (!md_pregion) { > + ret = -ENOENT; > + goto unlock; > + } > + tmp = &md_pregion->region; > + tmp->phys_addr = region->phys_addr; > + tmp->virt_addr = region->virt_addr; > + goto unlock; > + } > + > + ret = md->ops->md_update_region(md, &idx, region); > + if (ret) > + goto unlock; > + > + /* Skip predefined shdr/phdr header entry at the start */ > + ehdr = md->elf.ehdr; > + shdr = elf_shdr_entry_addr(ehdr, idx + 4); > + phdr = elf_phdr_entry_addr(ehdr, idx + 1); > + > + shdr->sh_addr = (elf_addr_t)region->virt_addr; > + phdr->p_vaddr = (elf_addr_t)region->virt_addr; > + phdr->p_paddr = region->phys_addr; > + > +unlock: > + mutex_unlock(&md_lock); > + return ret; > +} > +EXPORT_SYMBOL_GPL(qcom_minidump_update_region); > + I don't see any use of this API in the series. Do you plan to add one in the next version? Thanks, Pavan
On Fri, Jun 30, 2023 at 8:25 AM Pavan Kondeti <quic_pkondeti@quicinc.com> wrote: > On Wed, Jun 28, 2023 at 06:04:47PM +0530, Mukesh Ojha wrote: ... > > +static int set_download_mode(const char *val, const struct kernel_param *kp) > > +{ > > + u32 old = download_mode; > > + int ret; > > + > > + ret = sysfs_match_string(download_mode_name, val); > > + if (ret < 0) { > > + download_mode = old; Why is this old variable needed at all? > > + pr_err("qcom_scm: unknown download mode: %s\n", val); > > + return -EINVAL; > > + } > > minor nit: %s/-EINVAL/ret > > > + download_mode = ret; > > + if (__scm) > > + qcom_scm_set_download_mode(download_mode); > > + > > + return 0; > > +}
On 6/29/2023 4:42 AM, Rob Herring wrote: > On Wed, Jun 28, 2023 at 9:45 AM Greg KH <gregkh@linuxfoundation.org> wrote: >> >> On Wed, Jun 28, 2023 at 06:04:27PM +0530, Mukesh Ojha wrote: >>> Minidump is a best effort mechanism to collect useful and predefined data >>> for first level of debugging on end user devices running on Qualcomm SoCs. >>> It is built on the premise that System on Chip (SoC) or subsystem part of >>> SoC crashes, due to a range of hardware and software bugs. Hence, the >>> ability to collect accurate data is only a best-effort. The data collected >>> could be invalid or corrupted, data collection itself could fail, and so on. >>> >>> Qualcomm devices in engineering mode provides a mechanism for generating >>> full system ramdumps for post mortem debugging. But in some cases it's >>> however not feasible to capture the entire content of RAM. The minidump >>> mechanism provides the means for selecting which snippets should be >>> included in the ramdump. >>> >>> Minidump kernel driver implementation is divided into two parts for >>> simplicity, one is minidump core which can also be called minidump >>> frontend(As API gets exported from this driver for registration with >>> backend) and the other part is minidump backend i.e, where the underlying >>> implementation of minidump will be there. There could be different way >>> how the backend is implemented like Shared memory, Memory mapped IO >>> or Resource manager(gunyah) based where the guest region information is >>> passed to hypervisor via hypercalls. >>> >>> Minidump Client-1 Client-2 Client-5 Client-n >>> | | | | >>> | | ... | ... | >>> | | | | >>> | | | | >>> | | | | >>> | | | | >>> | | | | >>> | | | | >>> | +---+--------------+----+ | >>> +-----------+ qcom_minidump(core) +--------+ >>> | | >>> +------+-----+------+---+ >>> | | | >>> | | | >>> +---------------+ | +--------------------+ >>> | | | >>> | | | >>> | | | >>> v v v >>> +-------------------+ +-------------------+ +------------------+ >>> |qcom_minidump_smem | |qcom_minidump_mmio | | qcom_minidump_rm | >>> | | | | | | >>> +-------------------+ +-------------------+ +------------------+ >>> Shared memory Memory mapped IO Resource manager >>> (backend) (backend) (backend) >>> >>> >>> Here, we will be giving all analogy of backend with SMEM as it is the >>> only implemented backend at present but general idea remains the same. >> >> If you only have one "backend" then you don't need the extra compexity >> here at all, just remove that whole middle layer please and make this >> much simpler and smaller and easier to review and possibly accept. > > pstore already supports backends. Why aren't the above backends just > pstore backends rather than having an intermediate pstore backend in > RAM which then somehow gets moved into these minidump backends. It can't be another pstore backend since, pstore backend(ram) is for the system where there is a guarantees of fixed ram range content persist across boot, but that is not true with minidump, there is no pstorefs kind of support with minidump. Instead, the whole idea of backend/front-end of minidump here, is entirely related to minidump and here minidump backend could be anything like could be Shared memory in DDR which is shared across multiple subsystem (CPUSS) is one of them or it could be something where you want to collect minidump for a guest vm which guest does not have access to backend instead it may be the hypervisor do the register the region for the guest. Pstore(ram) is one of the clients of minidump where, we want to collect the console/pmsg/ftrace/dmesg logs for production devices where DDR dump is difficult and the reason of doing this to not re-invent the wheel and it just need physical address/size . +---------+ +---------+ +--------+ +---------+ | console | | pmsg | | ftrace | | dmesg | +---------+ +---------+ +--------+ +---------+ | | | | | | | | +------------------------------------------+ | \ / +----------------+ (1) |pstore frontends| +----------------+ | \ / +------------------- + (2) | pstore backend(ram)| +--------------------+ | \ / +--------------------+ (3) |qcom_pstore_minidump| +--------------------+ -Mukesh > >> We don't add layers when they are not needed, and never when there is no >> actual user. If you need the extra "complexity" later, then add it >> later when it is needed as who knows when that will ever be. >> >> Please redo this series based on that, thanks. > > My bigger issue with this whole series is what would this all look > like if every SoC vendor upstreamed their own custom dumping > mechanism. That would be a mess. (I have similar opinions on the > $soc-vendor hypervisors.) > > Rob
On 30/06/2023 18:04, Mukesh Ojha wrote: >> >>> We don't add layers when they are not needed, and never when there is no >>> actual user. If you need the extra "complexity" later, then add it >>> later when it is needed as who knows when that will ever be. >>> >>> Please redo this series based on that, thanks. >> >> My bigger issue with this whole series is what would this all look >> like if every SoC vendor upstreamed their own custom dumping >> mechanism. That would be a mess. (I have similar opinions on the >> $soc-vendor hypervisors.) Mukesh, LPC CFP is still open. There will be also Android and Kernel Debugging LPC microconference tracks. Coming with a unified solution could be a great topic for LPC. Solutions targeting only one user are quite often frowned upon. Best regards, Krzysztof
On 7/2/2023 1:29 AM, Krzysztof Kozlowski wrote: > On 30/06/2023 18:04, Mukesh Ojha wrote: >>> >>>> We don't add layers when they are not needed, and never when there is no >>>> actual user. If you need the extra "complexity" later, then add it >>>> later when it is needed as who knows when that will ever be. >>>> >>>> Please redo this series based on that, thanks. >>> >>> My bigger issue with this whole series is what would this all look >>> like if every SoC vendor upstreamed their own custom dumping >>> mechanism. That would be a mess. (I have similar opinions on the >>> $soc-vendor hypervisors.) > > Mukesh, > > LPC CFP is still open. There will be also Android and Kernel Debugging > LPC microconference tracks. Coming with a unified solution could be a > great topic for LPC. Solutions targeting only one user are quite often > frowned upon. LPC is far out and in November. Can we not have others speak up if they have the similar solution now? We can expand this to linux-kernel and ask for the other SOC vendors to chime in. I am sure that we may have existing solutions which came in for the one user first like Intel RDT if I remember. I am sure ARM MPAM usecase was present at that time but Intel RDT based solution which was x86 specific but accepted. ---Trilok Soni
On Thu, Jun 29, 2023 at 1:12 AM Rob Herring <robh+dt@kernel.org> wrote: > My bigger issue with this whole series is what would this all look > like if every SoC vendor upstreamed their own custom dumping > mechanism. That would be a mess. (I have similar opinions on the > $soc-vendor hypervisors.) I agree with Rob's stance. I think it would be useful to get input from the hwtracing developers (Alexander and Mathieu) who faced this "necessarily different" issue with all the hwtrace mechanisms and found a way out of it. I suspect they can have an idea of how this should be abstracted. Yours, Linus Walleij
On Mon, Jul 03, 2023 at 02:05:58PM -0700, Trilok Soni wrote: > On 7/2/2023 1:29 AM, Krzysztof Kozlowski wrote: > > On 30/06/2023 18:04, Mukesh Ojha wrote: > > > > > > > > > We don't add layers when they are not needed, and never when there is no > > > > > actual user. If you need the extra "complexity" later, then add it > > > > > later when it is needed as who knows when that will ever be. > > > > > > > > > > Please redo this series based on that, thanks. > > > > > > > > My bigger issue with this whole series is what would this all look > > > > like if every SoC vendor upstreamed their own custom dumping > > > > mechanism. That would be a mess. (I have similar opinions on the > > > > $soc-vendor hypervisors.) > > > > Mukesh, > > > > LPC CFP is still open. There will be also Android and Kernel Debugging > > LPC microconference tracks. Coming with a unified solution could be a > > great topic for LPC. Solutions targeting only one user are quite often > > frowned upon. > > LPC is far out and in November. Can we not have others speak up if they have > the similar solution now? We can expand this to linux-kernel and ask for the > other SOC vendors to chime in. I am sure that we may have existing solutions > which came in for the one user first like Intel RDT if I remember. I am sure > ARM MPAM usecase was present at that time but Intel RDT based solution which > was x86 specific but accepted. I am not familiar with Intel RDT and Arm MPAM but the community is always improving on the way it does things. LPC is indeed far out in November but it is an opportunity to cover the groundwork needed to have this discussion. It is always best to improve on something then introduce something new. Even better if something specific such as Intel RDT and Arm MPAM can be made more generic. A perfect example is hwtracing Linus referred to. The perf framework wasn't a perfect fit but it was enhanced to accommodate our requirements. I suggest to look at what is currently available and come up with a strategy to be presented at LPC - event better if you have a prototype. If you can't find anything or the drawbacks inherent to each avenue outweigh the benefits then we can have that conversation at LPC. > > ---Trilok Soni
On Mon, Jul 3, 2023 at 3:06 PM Trilok Soni <quic_tsoni@quicinc.com> wrote: > > On 7/2/2023 1:29 AM, Krzysztof Kozlowski wrote: > > On 30/06/2023 18:04, Mukesh Ojha wrote: > >>> > >>>> We don't add layers when they are not needed, and never when there is no > >>>> actual user. If you need the extra "complexity" later, then add it > >>>> later when it is needed as who knows when that will ever be. > >>>> > >>>> Please redo this series based on that, thanks. > >>> > >>> My bigger issue with this whole series is what would this all look > >>> like if every SoC vendor upstreamed their own custom dumping > >>> mechanism. That would be a mess. (I have similar opinions on the > >>> $soc-vendor hypervisors.) > > > > Mukesh, > > > > LPC CFP is still open. There will be also Android and Kernel Debugging > > LPC microconference tracks. Coming with a unified solution could be a > > great topic for LPC. Solutions targeting only one user are quite often > > frowned upon. > > LPC is far out and in November. Can we not have others speak up if they > have the similar solution now? We can expand this to linux-kernel and > ask for the other SOC vendors to chime in. I am sure that we may have > existing solutions which came in for the one user first like Intel RDT > if I remember. I am sure ARM MPAM usecase was present at that time but > Intel RDT based solution which was x86 specific but accepted. RDT predated MPAM. resctrl is the kernel feature, and it supports Intel and AMD which are not identical. resctrl is being (extensively) refactored to add in MPAM support. You are not the first here like Intel RDT, so I fail to see the parallel with minidump. We have an existing logging to persistent storage mechanism which is pstore. You should integrate into that rather than grafting something on to the side or underneath. Rob
On 7/6/2023 10:40 AM, Rob Herring wrote: > On Mon, Jul 3, 2023 at 3:06 PM Trilok Soni <quic_tsoni@quicinc.com> wrote: >> >> On 7/2/2023 1:29 AM, Krzysztof Kozlowski wrote: >>> On 30/06/2023 18:04, Mukesh Ojha wrote: >>>>> >>>>>> We don't add layers when they are not needed, and never when there is no >>>>>> actual user. If you need the extra "complexity" later, then add it >>>>>> later when it is needed as who knows when that will ever be. >>>>>> >>>>>> Please redo this series based on that, thanks. >>>>> >>>>> My bigger issue with this whole series is what would this all look >>>>> like if every SoC vendor upstreamed their own custom dumping >>>>> mechanism. That would be a mess. (I have similar opinions on the >>>>> $soc-vendor hypervisors.) >>> >>> Mukesh, >>> >>> LPC CFP is still open. There will be also Android and Kernel Debugging >>> LPC microconference tracks. Coming with a unified solution could be a >>> great topic for LPC. Solutions targeting only one user are quite often >>> frowned upon. >> >> LPC is far out and in November. Can we not have others speak up if they >> have the similar solution now? We can expand this to linux-kernel and >> ask for the other SOC vendors to chime in. I am sure that we may have >> existing solutions which came in for the one user first like Intel RDT >> if I remember. I am sure ARM MPAM usecase was present at that time but >> Intel RDT based solution which was x86 specific but accepted. > > RDT predated MPAM. resctrl is the kernel feature, and it supports > Intel and AMD which are not identical. resctrl is being (extensively) > refactored to add in MPAM support. > > You are not the first here like Intel RDT, so I fail to see the > parallel with minidump. We have an existing logging to persistent > storage mechanism which is pstore. You should integrate into that > rather than grafting something on to the side or underneath. > Mukesh will chime in once he looks at the hwtracing suggested by Linus W and see if it fits. Mukesh seems have already looked at pstore and discussions/patches are there w/ pstore logic I believe, but it is okay if they are not perfect if we are still not decided on the right framework. Best to decide if the existing frameworks fits or not or we need to create the new one. I would still prefer if other SOC vendors chime in here, since I am sure in the Mobile and Embedded world various SOCs may have requirements to get specific portion of the ramdump only for the quick analysis and meeting the storage requirements on the device for its collection. As mentioned on another patch, we are fine the submit abstract at LPC debug MC, but I would like the framework discussion to continue so that we can decide during the LPC that either existing frameworks fits the needs or they need to be extended or new fwk is needed. ---Trilok Soni
On 6/28/2023 6:04 PM, Mukesh Ojha wrote: > Minidump is a best effort mechanism to collect useful and predefined data > for first level of debugging on end user devices running on Qualcomm SoCs. > It is built on the premise that System on Chip (SoC) or subsystem part of > SoC crashes, due to a range of hardware and software bugs. Hence, the > ability to collect accurate data is only a best-effort. The data collected > could be invalid or corrupted, data collection itself could fail, and so on. > > Qualcomm devices in engineering mode provides a mechanism for generating > full system ramdumps for post mortem debugging. But in some cases it's > however not feasible to capture the entire content of RAM. The minidump > mechanism provides the means for selecting which snippets should be > included in the ramdump. > > Minidump kernel driver implementation is divided into two parts for > simplicity, one is minidump core which can also be called minidump > frontend(As API gets exported from this driver for registration with > backend) and the other part is minidump backend i.e, where the underlying > implementation of minidump will be there. There could be different way > how the backend is implemented like Shared memory, Memory mapped IO > or Resource manager(gunyah) based where the guest region information is > passed to hypervisor via hypercalls. > > Minidump Client-1 Client-2 Client-5 Client-n > | | | | > | | ... | ... | > | | | | > | | | | > | | | | > | | | | > | | | | > | | | | > | +---+--------------+----+ | > +-----------+ qcom_minidump(core) +--------+ > | | > +------+-----+------+---+ > | | | > | | | > +---------------+ | +--------------------+ > | | | > | | | > | | | > v v v > +-------------------+ +-------------------+ +------------------+ > |qcom_minidump_smem | |qcom_minidump_mmio | | qcom_minidump_rm | > | | | | | | > +-------------------+ +-------------------+ +------------------+ > Shared memory Memory mapped IO Resource manager > (backend) (backend) (backend) > > > Here, we will be giving all analogy of backend with SMEM as it is the > only implemented backend at present but general idea remains the same. > > The core of SMEM based minidump feature is part of Qualcomm's boot > firmware code. It initializes shared memory (SMEM), which is a part of > DDR and allocates a small section of SMEM to minidump table i.e also > called global table of content (G-ToC). Each subsystem (APSS, ADSP, ...) > has their own table of segments to be included in the minidump and all > get their reference from G-ToC. Each segment/region has some details > like name, physical address and it's size etc. and it could be anywhere > scattered in the DDR. > > Existing upstream Qualcomm remoteproc driver[1] already supports SMEM > based minidump feature for remoteproc instances like ADSP, MODEM, ... > where predefined selective segments of subsystem region can be dumped > as part of coredump collection which generates smaller size artifacts > compared to complete coredump of subsystem on crash. > > [1] > https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/tree/drivers/remoteproc/qcom_common.c#n142 > > In addition to managing and querying the APSS minidump description, > the Linux driver maintains a ELF header in a segment. This segment > gets updated with section/program header whenever a new entry gets > registered. > > > docs: qcom: Add qualcomm minidump guide > kallsyms: Export kallsyms_lookup_name > soc: qcom: Add qcom_minidump_smem module > soc: qcom: Add Qualcomm APSS minidump (frontend) feature support > soc: qcom: Add linux minidump smem backend driver support > soc: qcom: minidump: Add pending region registration support > soc: qcom: minidump: Add update region support > dt-bindings: reserved-memory: Add qcom,ramoops binding > pstore/ram : Export ramoops_parse_dt() symbol > soc: qcom: Add qcom's pstore minidump driver support > soc: qcom: Register pstore frontend region with minidump > remoteproc: qcom: Expand MD_* as MINIDUMP_* > remoterproc: qcom: refactor to leverage exported minidump symbol > MAINTAINERS: Add entry for minidump driver related support > arm64: defconfig: Enable Qualcomm Minidump related drivers > arm64: dts: qcom: sm8450: Add Qualcomm ramoops minidump node > firmware: qcom_scm: provide a read-modify-write function > pinctrl: qcom: Use qcom_scm_io_update_field() > firmware: scm: Modify only the download bits in TCSR register > firmware: qcom_scm: Refactor code to support multiple download mode > firmware: qcom_scm: Add multiple download mode support > > Patch 1/21 is qualcomm minidump document > Patch 2/21 will export kallsyms_lookup_name will be needed for minidump module > Patch 3/21 moves the minidump specific data structure and macro to > qcom_minidump_smem.c and later 13/21 will use the API and remove > minidump specific code to qcom_minidump_smem file. > Patch 4/21 is qualcomm minidump core(frontend) driver > Patch 5/21 implements qualcomm smem backend kernel driver > Patch 6/21 add pending region support for the clients who came for > registration before minidump. > Patch 7/21 add update region support for registered clients. > Patch 8/21 Add dt-binding for qualcomm ramoops driver which is also a minidump client driver > Patch 9/21 exported symbol from ramoops driver to avoid copy of the code. > Patch 10/21 Add qcom's pstore minidump driver support which adds ramoops platform device > and 11/21 register existing pstore frontend regions. > Patch 12/21 and 13/21 does some clean up and code reuse. > Patch 16/21 enable qcom_ramoops driver for sm8450 > Patch 17-21 are not new and has already been through 6 versions and > reason of adding here is for minidump testing purpose and it will be rebased > automatically along with new version of minidump series. > > Testing of the patches has been done on sm8450 target after enabling config like > CONFIG_PSTORE_RAM and CONFIG_PSTORE_CONSOLE and once the device boots up. > Try crashing it via devmem2 0xf11c000(this is known to create xpu violation and > and put the device in download mode) on command prompt. > > I have added download patch here numbered from 14/18 to 18/18 > Earlier download mode setting patches were sent separately > https://lore.kernel.org/lkml/1680076012-10785-1-git-send-email-quic_mojha@quicinc.com/ > > Default storage type is set to via USB, so minidump would be downloaded with the > help of x86_64 machine (running PCAT tool) attached to Qualcomm device which has > backed minidump boot firmware support (more can be found patch 3/18) > > Below patch [1] is to warm reset Qualcomm device which has upstream qcom > watchdog driver support. > > After applying all patches, we can boot the device and can execute > following command. > > echo mini > /sys/module/qcom_scm/parameters/download_mode > echo c > /proc/sysrq-trigger > > This will make the device go to download mode and collect the minidump on to the > attached x86 machine running the Qualcomm PCAT tool(This comes as part Qualcomm > package manager kit). > After that we will see a bunch of predefined registered region as binary blobs files > starts with md_* downloaded on the x86 machine on given location in PCAT tool from > the target device. > > A sample client example to dump a linux region has been given in patch 3/18 and as > well as can be seen in patch 12/18. > > [1] > --------------------------->8------------------------------------- > > commit f1124ccebd47550b4c9627aa162d9cdceba2b76f > Author: Mukesh Ojha <quic_mojha@quicinc.com> > Date: Thu Mar 16 14:08:35 2023 +0530 > > do not merge: watchdog bite on panic > > Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> > > diff --git a/drivers/watchdog/qcom-wdt.c b/drivers/watchdog/qcom-wdt.c > index 0d2209c..767e84a 100644 > --- a/drivers/watchdog/qcom-wdt.c > +++ b/drivers/watchdog/qcom-wdt.c > @@ -12,6 +12,7 @@ > #include <linux/platform_device.h> > #include <linux/watchdog.h> > #include <linux/of_device.h> > +#include <linux/panic.h> > > enum wdt_reg { > WDT_RST, > @@ -114,12 +115,28 @@ static int qcom_wdt_set_pretimeout(struct watchdog_device *wdd, > return qcom_wdt_start(wdd); > } > > +static void qcom_wdt_bite_on_panic(struct qcom_wdt *wdt) > +{ > + writel(0, wdt_addr(wdt, WDT_EN)); > + writel(1, wdt_addr(wdt, WDT_BITE_TIME)); > + writel(1, wdt_addr(wdt, WDT_RST)); > + writel(QCOM_WDT_ENABLE, wdt_addr(wdt, WDT_EN)); > + > + wmb(); > + > + while(1) > + udelay(1); > +} > + > static int qcom_wdt_restart(struct watchdog_device *wdd, unsigned long action, > void *data) > { > struct qcom_wdt *wdt = to_qcom_wdt(wdd); > u32 timeout; > > + if (in_panic) > + qcom_wdt_bite_on_panic(wdt); > + > /* > * Trigger watchdog bite: > * Setup BITE_TIME to be 128ms, and enable WDT. > diff --git a/include/linux/panic.h b/include/linux/panic.h > index 979b776..f913629 100644 > --- a/include/linux/panic.h > +++ b/include/linux/panic.h > @@ -22,6 +22,7 @@ extern int panic_on_oops; > extern int panic_on_unrecovered_nmi; > extern int panic_on_io_nmi; > extern int panic_on_warn; > +extern bool in_panic; > > extern unsigned long panic_on_taint; > extern bool panic_on_taint_nousertaint; > diff --git a/kernel/panic.c b/kernel/panic.c > index 487f5b0..714f7f4 100644 > --- a/kernel/panic.c > +++ b/kernel/panic.c > @@ -65,6 +65,8 @@ static unsigned int warn_limit __read_mostly; > > int panic_timeout = CONFIG_PANIC_TIMEOUT; > EXPORT_SYMBOL_GPL(panic_timeout); > +bool in_panic = false; > +EXPORT_SYMBOL_GPL(in_panic); > > #define PANIC_PRINT_TASK_INFO 0x00000001 > #define PANIC_PRINT_MEM_INFO 0x00000002 > @@ -261,6 +263,7 @@ void panic(const char *fmt, ...) > int old_cpu, this_cpu; > bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers; > > + in_panic = true; > if (panic_on_warn) { > /* > * This thread may hit another WARN() in the panic path. > -------------------------------------------------------------------------- > > Changes in v4: > - Redesigned the driver and divided the driver into front end and backend (smem) so > that any new backend can be attached easily to avoid code duplication. > - Patch reordering as per the driver and subsystem to easier review of the code. > - Removed minidump specific code from remoteproc to minidump smem based driver. > - Enabled the all the driver as modules. > - Address comments made on documentation and yaml and Device tree file [Krzysztof/Konrad] > - Address comments made qcom_pstore_minidump driver and given its Device tree > same set of properties as ramoops. [Luca/Kees] > - Added patch for MAINTAINER file. > - Include defconfig change as one patch as per [Krzysztof] suggestion. > - Tried to remove the redundant file scope variables from the module as per [Krzysztof] suggestion. > - Addressed comments made on dload mode patch v6 version > https://lore.kernel.org/lkml/1680076012-10785-1-git-send-email-quic_mojha@quicinc.com/ > > Changes in v3: https://lore.kernel.org/lkml/1683133352-10046-1-git-send-email-quic_mojha@quicinc.com/ > - Addressed most of the comments by Srini on v2 and refactored the minidump driver. > - Added platform device support > - Unregister region support. > - Added update region for clients. > - Added pending region support. > - Modified the documentation guide accordingly. > - Added qcom_pstore_ramdump client driver which happen to add ramoops platform > device and also registers ramoops region with minidump. > - Added download mode patch series with this minidump series. > https://lore.kernel.org/lkml/1680076012-10785-1-git-send-email-quic_mojha@quicinc.com/ > > Changes in v2: https://lore.kernel.org/lkml/1679491817-2498-1-git-send-email-quic_mojha@quicinc.com/ > - Addressed review comment made by [quic_tsoni/bmasney] to add documentation. > - Addressed comments made by [srinivas.kandagatla] > - Dropped pstore 6/6 from the last series, till i get conclusion to get pstore > region in minidump. > - Fixed issue reported by kernel test robot. > > Changes in v1: https://lore.kernel.org/lkml/1676978713-7394-1-git-send-email-quic_mojha@quicinc.com/ > > Mukesh Ojha (21): > docs: qcom: Add qualcomm minidump guide > kallsyms: Export kallsyms_lookup_name > soc: qcom: Add qcom_minidump_smem module > soc: qcom: Add Qualcomm APSS minidump (frontend) feature support > soc: qcom: Add linux minidump smem backend driver support > soc: qcom: minidump: Add pending region registration support > soc: qcom: minidump: Add update region support > dt-bindings: reserved-memory: Add qcom,ramoops binding > pstore/ram : Export ramoops_parse_dt() symbol > soc: qcom: Add qcom's pstore minidump driver support > soc: qcom: Register pstore frontend region with minidump > remoteproc: qcom: Expand MD_* as MINIDUMP_* > remoterproc: qcom: refactor to leverage exported minidump symbol > MAINTAINERS: Add entry for minidump driver related support > arm64: defconfig: Enable Qualcomm Minidump related drivers > arm64: dts: qcom: sm8450: Add Qualcomm ramoops minidump node > firmware: qcom_scm: provide a read-modify-write function > pinctrl: qcom: Use qcom_scm_io_update_field() > firmware: scm: Modify only the download bits in TCSR register > firmware: qcom_scm: Refactor code to support multiple download mode > firmware: qcom_scm: Add multiple download mode support Hi Mukesh, For IPQ chipsets, for the crashdump to work, we need the below patch firmware: scm: Modify only the download bits in TCSR register can you post the below patches separately? Looks like minidump will take some time and also I don't see any dependencies for these to go along with the minidump. Given that, will it be possible to post the below patches separately? firmware: qcom_scm: provide a read-modify-write function pinctrl: qcom: Use qcom_scm_io_update_field() firmware: scm: Modify only the download bits in TCSR register Do let us know if we can take these patches and post it separately. Thanks, Kathiravan T. > > Documentation/admin-guide/index.rst | 1 + > Documentation/admin-guide/qcom_minidump.rst | 293 +++++++++++ > .../devicetree/bindings/soc/qcom/qcom,ramoops.yaml | 126 +++++ > MAINTAINERS | 15 + > arch/arm64/boot/dts/qcom/sm8450.dtsi | 12 + > arch/arm64/configs/defconfig | 4 + > drivers/firmware/Kconfig | 11 - > drivers/firmware/qcom_scm.c | 85 ++- > drivers/pinctrl/qcom/pinctrl-msm.c | 12 +- > drivers/remoteproc/qcom_common.c | 142 +---- > drivers/soc/qcom/Kconfig | 39 ++ > drivers/soc/qcom/Makefile | 3 + > drivers/soc/qcom/qcom_minidump.c | 582 +++++++++++++++++++++ > drivers/soc/qcom/qcom_minidump_internal.h | 98 ++++ > drivers/soc/qcom/qcom_minidump_smem.c | 387 ++++++++++++++ > drivers/soc/qcom/qcom_pstore_minidump.c | 210 ++++++++ > drivers/soc/qcom/smem.c | 9 + > fs/pstore/ram.c | 26 +- > include/linux/firmware/qcom/qcom_scm.h | 2 + > include/linux/pstore_ram.h | 2 + > include/soc/qcom/qcom_minidump.h | 64 +++ > kernel/kallsyms.c | 2 +- > 22 files changed, 1973 insertions(+), 152 deletions(-) > create mode 100644 Documentation/admin-guide/qcom_minidump.rst > create mode 100644 Documentation/devicetree/bindings/soc/qcom/qcom,ramoops.yaml > create mode 100644 drivers/soc/qcom/qcom_minidump.c > create mode 100644 drivers/soc/qcom/qcom_minidump_internal.h > create mode 100644 drivers/soc/qcom/qcom_minidump_smem.c > create mode 100644 drivers/soc/qcom/qcom_pstore_minidump.c > create mode 100644 include/soc/qcom/qcom_minidump.h >
> > Hi Mukesh, > > For IPQ chipsets, for the crashdump to work, we need the below patch > > firmware: scm: Modify only the download bits in TCSR register > > can you post the below patches separately? Looks like minidump will take > some time and also I don't see any dependencies for these to go along > with the minidump. Given that, will it be possible to post the below > patches separately? > > firmware: qcom_scm: provide a read-modify-write function > pinctrl: qcom: Use qcom_scm_io_update_field() > firmware: scm: Modify only the download bits in TCSR register > > Do let us know if we can take these patches and post it separately. Yes, we can post this separately. -Mukesh > >> >> Documentation/admin-guide/index.rst | 1 + >> Documentation/admin-guide/qcom_minidump.rst | 293 +++++++++++ >> .../devicetree/bindings/soc/qcom/qcom,ramoops.yaml | 126 +++++ >> MAINTAINERS | 15 + >> arch/arm64/boot/dts/qcom/sm8450.dtsi | 12 + >> arch/arm64/configs/defconfig | 4 + >> drivers/firmware/Kconfig | 11 - >> drivers/firmware/qcom_scm.c | 85 ++- >> drivers/pinctrl/qcom/pinctrl-msm.c | 12 +- >> drivers/remoteproc/qcom_common.c | 142 +---- >> drivers/soc/qcom/Kconfig | 39 ++ >> drivers/soc/qcom/Makefile | 3 + >> drivers/soc/qcom/qcom_minidump.c | 582 >> +++++++++++++++++++++ >> drivers/soc/qcom/qcom_minidump_internal.h | 98 ++++ >> drivers/soc/qcom/qcom_minidump_smem.c | 387 ++++++++++++++ >> drivers/soc/qcom/qcom_pstore_minidump.c | 210 ++++++++ >> drivers/soc/qcom/smem.c | 9 + >> fs/pstore/ram.c | 26 +- >> include/linux/firmware/qcom/qcom_scm.h | 2 + >> include/linux/pstore_ram.h | 2 + >> include/soc/qcom/qcom_minidump.h | 64 +++ >> kernel/kallsyms.c | 2 +- >> 22 files changed, 1973 insertions(+), 152 deletions(-) >> create mode 100644 Documentation/admin-guide/qcom_minidump.rst >> create mode 100644 >> Documentation/devicetree/bindings/soc/qcom/qcom,ramoops.yaml >> create mode 100644 drivers/soc/qcom/qcom_minidump.c >> create mode 100644 drivers/soc/qcom/qcom_minidump_internal.h >> create mode 100644 drivers/soc/qcom/qcom_minidump_smem.c >> create mode 100644 drivers/soc/qcom/qcom_pstore_minidump.c >> create mode 100644 include/soc/qcom/qcom_minidump.h >>
On 7/5/2023 10:29 AM, Trilok Soni wrote: > On 7/4/2023 2:27 AM, Linus Walleij wrote: >> On Thu, Jun 29, 2023 at 1:12 AM Rob Herring <robh+dt@kernel.org> wrote: >> >>> My bigger issue with this whole series is what would this all look >>> like if every SoC vendor upstreamed their own custom dumping >>> mechanism. That would be a mess. (I have similar opinions on the >>> $soc-vendor hypervisors.) >> >> I agree with Rob's stance. >> >> I think it would be useful to get input from the hwtracing developers >> (Alexander and Mathieu) who faced this "necessarily different" issue >> with all the hwtrace mechanisms and found a way out of it. I suspect >> they can have an idea of how this should be abstracted. > > Any mailing list you suggest we expand to so that we get inputs from the > hwtracing developers and maintainers or just look into the MAINTAINERS > file and start an email thread? > > We are fine to submit the abstract for the LPC in next two weeks, but > prefer to have lot of good discussion before it on the mailing list, so > that we have code to talk about in LPC. We have submitted abstract at LPC MC. Let's continue the discussion here though. Mukesh, do you want to expand the lists as necessary to see if other soc-vendors are having any inputs here? May be add Exynos or MTK kernel mailing lists + linux-kernel? I don't know if anyone will respond or not, but let's try. ---Trilok Soni
diff --git a/drivers/watchdog/qcom-wdt.c b/drivers/watchdog/qcom-wdt.c index 0d2209c..767e84a 100644 --- a/drivers/watchdog/qcom-wdt.c +++ b/drivers/watchdog/qcom-wdt.c @@ -12,6 +12,7 @@ #include <linux/platform_device.h> #include <linux/watchdog.h> #include <linux/of_device.h> +#include <linux/panic.h> enum wdt_reg { WDT_RST, @@ -114,12 +115,28 @@ static int qcom_wdt_set_pretimeout(struct watchdog_device *wdd, return qcom_wdt_start(wdd); } +static void qcom_wdt_bite_on_panic(struct qcom_wdt *wdt) +{ + writel(0, wdt_addr(wdt, WDT_EN)); + writel(1, wdt_addr(wdt, WDT_BITE_TIME)); + writel(1, wdt_addr(wdt, WDT_RST)); + writel(QCOM_WDT_ENABLE, wdt_addr(wdt, WDT_EN)); + + wmb(); + + while(1) + udelay(1); +} + static int qcom_wdt_restart(struct watchdog_device *wdd, unsigned long action, void *data) { struct qcom_wdt *wdt = to_qcom_wdt(wdd); u32 timeout; + if (in_panic) + qcom_wdt_bite_on_panic(wdt); + /* * Trigger watchdog bite: * Setup BITE_TIME to be 128ms, and enable WDT. diff --git a/include/linux/panic.h b/include/linux/panic.h index 979b776..f913629 100644 --- a/include/linux/panic.h +++ b/include/linux/panic.h @@ -22,6 +22,7 @@ extern int panic_on_oops; extern int panic_on_unrecovered_nmi; extern int panic_on_io_nmi; extern int panic_on_warn; +extern bool in_panic; extern unsigned long panic_on_taint; extern bool panic_on_taint_nousertaint; diff --git a/kernel/panic.c b/kernel/panic.c index 487f5b0..714f7f4 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -65,6 +65,8 @@ static unsigned int warn_limit __read_mostly; int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); +bool in_panic = false; +EXPORT_SYMBOL_GPL(in_panic); #define PANIC_PRINT_TASK_INFO 0x00000001 #define PANIC_PRINT_MEM_INFO 0x00000002 @@ -261,6 +263,7 @@ void panic(const char *fmt, ...) int old_cpu, this_cpu; bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers; + in_panic = true; if (panic_on_warn) { /* * This thread may hit another WARN() in the panic path.
Minidump is a best effort mechanism to collect useful and predefined data for first level of debugging on end user devices running on Qualcomm SoCs. It is built on the premise that System on Chip (SoC) or subsystem part of SoC crashes, due to a range of hardware and software bugs. Hence, the ability to collect accurate data is only a best-effort. The data collected could be invalid or corrupted, data collection itself could fail, and so on. Qualcomm devices in engineering mode provides a mechanism for generating full system ramdumps for post mortem debugging. But in some cases it's however not feasible to capture the entire content of RAM. The minidump mechanism provides the means for selecting which snippets should be included in the ramdump. Minidump kernel driver implementation is divided into two parts for simplicity, one is minidump core which can also be called minidump frontend(As API gets exported from this driver for registration with backend) and the other part is minidump backend i.e, where the underlying implementation of minidump will be there. There could be different way how the backend is implemented like Shared memory, Memory mapped IO or Resource manager(gunyah) based where the guest region information is passed to hypervisor via hypercalls. Minidump Client-1 Client-2 Client-5 Client-n | | | | | | ... | ... | | | | | | | | | | | | | | | | | | | | | | | | | | +---+--------------+----+ | +-----------+ qcom_minidump(core) +--------+ | | +------+-----+------+---+ | | | | | | +---------------+ | +--------------------+ | | | | | | | | | v v v +-------------------+ +-------------------+ +------------------+ |qcom_minidump_smem | |qcom_minidump_mmio | | qcom_minidump_rm | | | | | | | +-------------------+ +-------------------+ +------------------+ Shared memory Memory mapped IO Resource manager (backend) (backend) (backend) Here, we will be giving all analogy of backend with SMEM as it is the only implemented backend at present but general idea remains the same. The core of SMEM based minidump feature is part of Qualcomm's boot firmware code. It initializes shared memory (SMEM), which is a part of DDR and allocates a small section of SMEM to minidump table i.e also called global table of content (G-ToC). Each subsystem (APSS, ADSP, ...) has their own table of segments to be included in the minidump and all get their reference from G-ToC. Each segment/region has some details like name, physical address and it's size etc. and it could be anywhere scattered in the DDR. Existing upstream Qualcomm remoteproc driver[1] already supports SMEM based minidump feature for remoteproc instances like ADSP, MODEM, ... where predefined selective segments of subsystem region can be dumped as part of coredump collection which generates smaller size artifacts compared to complete coredump of subsystem on crash. [1] https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/tree/drivers/remoteproc/qcom_common.c#n142 In addition to managing and querying the APSS minidump description, the Linux driver maintains a ELF header in a segment. This segment gets updated with section/program header whenever a new entry gets registered. docs: qcom: Add qualcomm minidump guide kallsyms: Export kallsyms_lookup_name soc: qcom: Add qcom_minidump_smem module soc: qcom: Add Qualcomm APSS minidump (frontend) feature support soc: qcom: Add linux minidump smem backend driver support soc: qcom: minidump: Add pending region registration support soc: qcom: minidump: Add update region support dt-bindings: reserved-memory: Add qcom,ramoops binding pstore/ram : Export ramoops_parse_dt() symbol soc: qcom: Add qcom's pstore minidump driver support soc: qcom: Register pstore frontend region with minidump remoteproc: qcom: Expand MD_* as MINIDUMP_* remoterproc: qcom: refactor to leverage exported minidump symbol MAINTAINERS: Add entry for minidump driver related support arm64: defconfig: Enable Qualcomm Minidump related drivers arm64: dts: qcom: sm8450: Add Qualcomm ramoops minidump node firmware: qcom_scm: provide a read-modify-write function pinctrl: qcom: Use qcom_scm_io_update_field() firmware: scm: Modify only the download bits in TCSR register firmware: qcom_scm: Refactor code to support multiple download mode firmware: qcom_scm: Add multiple download mode support Patch 1/21 is qualcomm minidump document Patch 2/21 will export kallsyms_lookup_name will be needed for minidump module Patch 3/21 moves the minidump specific data structure and macro to qcom_minidump_smem.c and later 13/21 will use the API and remove minidump specific code to qcom_minidump_smem file. Patch 4/21 is qualcomm minidump core(frontend) driver Patch 5/21 implements qualcomm smem backend kernel driver Patch 6/21 add pending region support for the clients who came for registration before minidump. Patch 7/21 add update region support for registered clients. Patch 8/21 Add dt-binding for qualcomm ramoops driver which is also a minidump client driver Patch 9/21 exported symbol from ramoops driver to avoid copy of the code. Patch 10/21 Add qcom's pstore minidump driver support which adds ramoops platform device and 11/21 register existing pstore frontend regions. Patch 12/21 and 13/21 does some clean up and code reuse. Patch 16/21 enable qcom_ramoops driver for sm8450 Patch 17-21 are not new and has already been through 6 versions and reason of adding here is for minidump testing purpose and it will be rebased automatically along with new version of minidump series. Testing of the patches has been done on sm8450 target after enabling config like CONFIG_PSTORE_RAM and CONFIG_PSTORE_CONSOLE and once the device boots up. Try crashing it via devmem2 0xf11c000(this is known to create xpu violation and and put the device in download mode) on command prompt. I have added download patch here numbered from 14/18 to 18/18 Earlier download mode setting patches were sent separately https://lore.kernel.org/lkml/1680076012-10785-1-git-send-email-quic_mojha@quicinc.com/ Default storage type is set to via USB, so minidump would be downloaded with the help of x86_64 machine (running PCAT tool) attached to Qualcomm device which has backed minidump boot firmware support (more can be found patch 3/18) Below patch [1] is to warm reset Qualcomm device which has upstream qcom watchdog driver support. After applying all patches, we can boot the device and can execute following command. echo mini > /sys/module/qcom_scm/parameters/download_mode echo c > /proc/sysrq-trigger This will make the device go to download mode and collect the minidump on to the attached x86 machine running the Qualcomm PCAT tool(This comes as part Qualcomm package manager kit). After that we will see a bunch of predefined registered region as binary blobs files starts with md_* downloaded on the x86 machine on given location in PCAT tool from the target device. A sample client example to dump a linux region has been given in patch 3/18 and as well as can be seen in patch 12/18. [1] --------------------------->8------------------------------------- commit f1124ccebd47550b4c9627aa162d9cdceba2b76f Author: Mukesh Ojha <quic_mojha@quicinc.com> Date: Thu Mar 16 14:08:35 2023 +0530 do not merge: watchdog bite on panic Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> -------------------------------------------------------------------------- Changes in v4: - Redesigned the driver and divided the driver into front end and backend (smem) so that any new backend can be attached easily to avoid code duplication. - Patch reordering as per the driver and subsystem to easier review of the code. - Removed minidump specific code from remoteproc to minidump smem based driver. - Enabled the all the driver as modules. - Address comments made on documentation and yaml and Device tree file [Krzysztof/Konrad] - Address comments made qcom_pstore_minidump driver and given its Device tree same set of properties as ramoops. [Luca/Kees] - Added patch for MAINTAINER file. - Include defconfig change as one patch as per [Krzysztof] suggestion. - Tried to remove the redundant file scope variables from the module as per [Krzysztof] suggestion. - Addressed comments made on dload mode patch v6 version https://lore.kernel.org/lkml/1680076012-10785-1-git-send-email-quic_mojha@quicinc.com/ Changes in v3: https://lore.kernel.org/lkml/1683133352-10046-1-git-send-email-quic_mojha@quicinc.com/ - Addressed most of the comments by Srini on v2 and refactored the minidump driver. - Added platform device support - Unregister region support. - Added update region for clients. - Added pending region support. - Modified the documentation guide accordingly. - Added qcom_pstore_ramdump client driver which happen to add ramoops platform device and also registers ramoops region with minidump. - Added download mode patch series with this minidump series. https://lore.kernel.org/lkml/1680076012-10785-1-git-send-email-quic_mojha@quicinc.com/ Changes in v2: https://lore.kernel.org/lkml/1679491817-2498-1-git-send-email-quic_mojha@quicinc.com/ - Addressed review comment made by [quic_tsoni/bmasney] to add documentation. - Addressed comments made by [srinivas.kandagatla] - Dropped pstore 6/6 from the last series, till i get conclusion to get pstore region in minidump. - Fixed issue reported by kernel test robot. Changes in v1: https://lore.kernel.org/lkml/1676978713-7394-1-git-send-email-quic_mojha@quicinc.com/ Mukesh Ojha (21): docs: qcom: Add qualcomm minidump guide kallsyms: Export kallsyms_lookup_name soc: qcom: Add qcom_minidump_smem module soc: qcom: Add Qualcomm APSS minidump (frontend) feature support soc: qcom: Add linux minidump smem backend driver support soc: qcom: minidump: Add pending region registration support soc: qcom: minidump: Add update region support dt-bindings: reserved-memory: Add qcom,ramoops binding pstore/ram : Export ramoops_parse_dt() symbol soc: qcom: Add qcom's pstore minidump driver support soc: qcom: Register pstore frontend region with minidump remoteproc: qcom: Expand MD_* as MINIDUMP_* remoterproc: qcom: refactor to leverage exported minidump symbol MAINTAINERS: Add entry for minidump driver related support arm64: defconfig: Enable Qualcomm Minidump related drivers arm64: dts: qcom: sm8450: Add Qualcomm ramoops minidump node firmware: qcom_scm: provide a read-modify-write function pinctrl: qcom: Use qcom_scm_io_update_field() firmware: scm: Modify only the download bits in TCSR register firmware: qcom_scm: Refactor code to support multiple download mode firmware: qcom_scm: Add multiple download mode support Documentation/admin-guide/index.rst | 1 + Documentation/admin-guide/qcom_minidump.rst | 293 +++++++++++ .../devicetree/bindings/soc/qcom/qcom,ramoops.yaml | 126 +++++ MAINTAINERS | 15 + arch/arm64/boot/dts/qcom/sm8450.dtsi | 12 + arch/arm64/configs/defconfig | 4 + drivers/firmware/Kconfig | 11 - drivers/firmware/qcom_scm.c | 85 ++- drivers/pinctrl/qcom/pinctrl-msm.c | 12 +- drivers/remoteproc/qcom_common.c | 142 +---- drivers/soc/qcom/Kconfig | 39 ++ drivers/soc/qcom/Makefile | 3 + drivers/soc/qcom/qcom_minidump.c | 582 +++++++++++++++++++++ drivers/soc/qcom/qcom_minidump_internal.h | 98 ++++ drivers/soc/qcom/qcom_minidump_smem.c | 387 ++++++++++++++ drivers/soc/qcom/qcom_pstore_minidump.c | 210 ++++++++ drivers/soc/qcom/smem.c | 9 + fs/pstore/ram.c | 26 +- include/linux/firmware/qcom/qcom_scm.h | 2 + include/linux/pstore_ram.h | 2 + include/soc/qcom/qcom_minidump.h | 64 +++ kernel/kallsyms.c | 2 +- 22 files changed, 1973 insertions(+), 152 deletions(-) create mode 100644 Documentation/admin-guide/qcom_minidump.rst create mode 100644 Documentation/devicetree/bindings/soc/qcom/qcom,ramoops.yaml create mode 100644 drivers/soc/qcom/qcom_minidump.c create mode 100644 drivers/soc/qcom/qcom_minidump_internal.h create mode 100644 drivers/soc/qcom/qcom_minidump_smem.c create mode 100644 drivers/soc/qcom/qcom_pstore_minidump.c create mode 100644 include/soc/qcom/qcom_minidump.h