public inbox for linux-pci@vger.kernel.org
 help / color / mirror / Atom feed
From: Jonathan Cameron <jonathan.cameron@huawei.com>
To: <smadhavan@nvidia.com>
Cc: <dave@stgolabs.net>, <dave.jiang@intel.com>,
	<alison.schofield@intel.com>, <vishal.l.verma@intel.com>,
	<ira.weiny@intel.com>, <dan.j.williams@intel.com>,
	<bhelgaas@google.com>, <ming.li@zohomail.com>, <rrichter@amd.com>,
	<Smita.KoralahalliChannabasappa@amd.com>,
	<huaisheng.ye@intel.com>, <linux-cxl@vger.kernel.org>,
	<linux-pci@vger.kernel.org>, <vaslot@nvidia.com>,
	<vsethi@nvidia.com>, <sdonthineni@nvidia.com>,
	<vidyas@nvidia.com>, <mochs@nvidia.com>, <jsequeira@nvidia.com>
Subject: Re: [PATCH v4 07/10] cxl: add host cache flush and multi-function reset
Date: Wed, 21 Jan 2026 11:20:05 +0000	[thread overview]
Message-ID: <20260121112005.00001e80@huawei.com> (raw)
In-Reply-To: <20260120222610.2227109-8-smadhavan@nvidia.com>

On Tue, 20 Jan 2026 22:26:07 +0000
smadhavan@nvidia.com wrote:

> From: Srirangan Madhavan <smadhavan@nvidia.com>
> 
> Flush host CPU caches for mapped HDM ranges after teardown and prepare
> sibling Type 2 functions on multi-function devices. The host cache
> maintenance uses wbinvd_on_all_cpus() on x86 and VA-based PoC clean+

That's not sufficient in general on arm64.  It might flush far enough
or there might be buffers beyond the point of coherence that are not
flushed.

Until there are clarifications from Arm we need something like the
agents in drivers/cache to do equivalent of wbinvd_on_all_cpus()
(be it on a PA range to making a tiny bit less horrible)

Or we need an opt in list for platforms where a flush to PoC is enough.

Needs to some sort of arch_ call as well, not hidden in the cxl driver.

I'd suggest a separate patch to add the necessary infrastructure for arm64
with the relevant maintainers and lists included.

It needs enough work to be something they'd consider that I haven't +CC them
on this version.

With that in mind I'll skip reviewing this patch for now.

Jonathan

> invalidate on arm64 via memremap() and on_each_cpu(), matching the
> required ordering before reset.
> 
> Signed-off-by: Srirangan Madhavan <smadhavan@nvidia.com>
> ---
>  drivers/cxl/pci.c | 150 +++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 148 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
> index e4134162e82a..f9cc452ccb8a 100644
> --- a/drivers/cxl/pci.c
> +++ b/drivers/cxl/pci.c
> @@ -11,6 +11,10 @@
>  #include <linux/pci.h>
>  #include <linux/aer.h>
>  #include <linux/io.h>
> +#include <linux/align.h>
> +#include <linux/cache.h>
> +#include <linux/cacheflush.h>
> +#include <linux/smp.h>
>  #include <cxl/mailbox.h>
>  #include <cxl/pci.h>
>  #include "cxlmem.h"
> @@ -1085,6 +1089,71 @@ bool cxl_is_type2_device(struct pci_dev *pdev)
>  	return cxlds->type == CXL_DEVTYPE_DEVMEM;
>  }
> 
> +#ifdef CONFIG_ARM64
> +struct cxl_cache_flush_ctx {
> +	void *va;
> +	size_t len;
> +};
> +
> +static void cxl_flush_by_va_local(void *info)
> +{
> +	struct cxl_cache_flush_ctx *ctx = info;
> +
> +	dcache_clean_inval_poc((unsigned long)ctx->va,
> +			       (unsigned long)ctx->va + ctx->len);
> +	asm volatile("dsb ish" ::: "memory");
> +}
> +#endif
> +
> +static int cxl_region_flush_host_cpu_caches(struct device *dev, void *data)
> +{
> +	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);
> +	struct cxl_region *cxlr = cxled->cxld.region;
> +	struct resource *res;
> +
> +	if (!is_endpoint_decoder(dev))
> +		return 0;
> +
> +	if (!cxlr || !cxlr->params.res)
> +		return 0;
> +
> +	res = cxlr->params.res;
> +
> +#ifdef CONFIG_X86
> +	static bool flushed;
> +
> +	if (!flushed) {
> +		wbinvd_on_all_cpus();
> +		flushed = true;
> +	}
> +#elif defined(CONFIG_ARM64)
> +	void *va;
> +	size_t len, line_size = L1_CACHE_BYTES;
> +	phys_addr_t start, end, aligned_start, aligned_end;
> +	struct cxl_cache_flush_ctx flush_ctx;
> +
> +	start = res->start;
> +	end = res->end;
> +
> +	aligned_start = ALIGN_DOWN(start, line_size);
> +	aligned_end = ALIGN(end + 1, line_size);
> +	len = aligned_end - aligned_start;
> +
> +	va = memremap(aligned_start, len, MEMREMAP_WB);
> +	if (!va) {
> +		pr_warn("Failed to map region for cache flush\n");
> +		return 0;
> +	}
> +
> +	flush_ctx.va = va;
> +	flush_ctx.len = len;
> +	on_each_cpu(cxl_flush_by_va_local, &flush_ctx, 1);
> +
> +	memunmap(va);
> +#endif
> +	return 0;
> +}
> +
>  static int cxl_check_region_driver_bound(struct device *dev, void *data)
>  {
>  	struct cxl_decoder *cxld = to_cxl_decoder(dev);
> @@ -1245,6 +1314,9 @@ static int cxl_reset_prepare_memdev(struct pci_dev *pdev)
>  		return rc;
>  	}
> 
> +	device_for_each_child(&endpoint->dev, NULL,
> +			      cxl_region_flush_host_cpu_caches);
> +
>  	/* Keep cxl_region_rwsem held, released by cleanup function */
>  	return 0;
>  }
> @@ -1259,12 +1331,79 @@ static void cxl_reset_cleanup_memdev(struct pci_dev *pdev)
>  		up_write(&cxl_region_rwsem);
>  }
> 
> +static int cxl_reset_prepare_all_functions(struct pci_dev *pdev)
> +{
> +	struct pci_dev *func_dev;
> +	unsigned int devfn;
> +	int func, rc;
> +	struct pci_dev *prepared_funcs[8] = { NULL };
> +	int prepared_count = 0;
> +
> +	for (func = 0; func < 8; func++) {
> +		devfn = PCI_DEVFN(PCI_SLOT(pdev->devfn), func);
> +
> +		if (devfn == pdev->devfn)
> +			continue;
> +
> +		func_dev = pci_get_slot(pdev->bus, devfn);
> +		if (!func_dev)
> +			continue;
> +
> +		if (!cxl_is_type2_device(func_dev)) {
> +			pci_dev_put(func_dev);
> +			continue;
> +		}
> +
> +		rc = cxl_reset_prepare_memdev(func_dev);
> +		if (rc) {
> +			pci_dev_put(func_dev);
> +			goto cleanup_funcs;
> +		}
> +
> +		prepared_funcs[prepared_count++] = func_dev;
> +	}
> +
> +	return 0;
> +
> +cleanup_funcs:
> +	for (func = 0; func < prepared_count; func++) {
> +		if (prepared_funcs[func]) {
> +			cxl_reset_cleanup_memdev(prepared_funcs[func]);
> +			pci_dev_put(prepared_funcs[func]);
> +		}
> +	}
> +	return rc;
> +}
> +
> +static void cxl_reset_cleanup_all_functions(struct pci_dev *pdev)
> +{
> +	struct pci_dev *func_dev;
> +	unsigned int devfn;
> +	int func;
> +
> +	for (func = 0; func < 8; func++) {
> +		devfn = PCI_DEVFN(PCI_SLOT(pdev->devfn), func);
> +
> +		if (devfn == pdev->devfn)
> +			continue;
> +
> +		func_dev = pci_get_slot(pdev->bus, devfn);
> +		if (!func_dev)
> +			continue;
> +
> +		if (cxl_is_type2_device(func_dev))
> +			cxl_reset_cleanup_memdev(func_dev);
> +
> +		pci_dev_put(func_dev);
> +	}
> +}
> +
>  /**
>   * cxl_reset_prepare_device - Prepare CXL device for reset
>   * @pdev: PCI device being reset
>   *
>   * CXL-reset-specific preparation. Validates memory is offline, flushes
> - * device caches, and tears down regions.
> + * device caches, and tears down regions for device and siblings.
>   *
>   * Returns: 0 on success, -EBUSY if memory online, negative on error
>   */
> @@ -1283,6 +1422,12 @@ int cxl_reset_prepare_device(struct pci_dev *pdev)
>  		return rc;
>  	}
> 
> +	rc = cxl_reset_prepare_all_functions(pdev);
> +	if (rc) {
> +		cxl_reset_cleanup_memdev(pdev);
> +		return rc;
> +	}
> +
>  	return 0;
>  }
>  EXPORT_SYMBOL_NS_GPL(cxl_reset_prepare_device, "CXL");
> @@ -1291,10 +1436,11 @@ EXPORT_SYMBOL_NS_GPL(cxl_reset_prepare_device, "CXL");
>   * cxl_reset_cleanup_device - Cleanup after CXL reset
>   * @pdev: PCI device that was reset
>   *
> - * Releases region locks held during reset.
> + * Releases region locks for device and all sibling functions.
>   */
>  void cxl_reset_cleanup_device(struct pci_dev *pdev)
>  {
> +	cxl_reset_cleanup_all_functions(pdev);
>  	cxl_reset_cleanup_memdev(pdev);
>  }
>  EXPORT_SYMBOL_NS_GPL(cxl_reset_cleanup_device, "CXL");
> --
> 2.34.1
> 
> 


  reply	other threads:[~2026-01-21 11:20 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-20 22:26 [PATCH v4 0/10] CXL Reset support for Type 2 devices smadhavan
2026-01-20 22:26 ` [PATCH v4 01/10] cxl: move DVSEC defines to cxl pci header smadhavan
2026-01-21 10:31   ` Jonathan Cameron
2026-01-20 22:26 ` [PATCH v4 02/10] PCI: switch CXL port DVSEC defines smadhavan
2026-01-21 10:34   ` Jonathan Cameron
2026-01-20 22:26 ` [PATCH v4 03/10] cxl: add type 2 helper and reset DVSEC bits smadhavan
2026-01-20 23:27   ` Dave Jiang
2026-01-21 10:45     ` Jonathan Cameron
2026-01-20 22:26 ` [PATCH v4 04/10] PCI: add CXL reset method smadhavan
2026-01-21  0:08   ` Dave Jiang
2026-01-21 10:57   ` Jonathan Cameron
2026-01-23 13:54   ` kernel test robot
2026-01-20 22:26 ` [PATCH v4 05/10] cxl: add reset prepare and region teardown smadhavan
2026-01-21 11:09   ` Jonathan Cameron
2026-01-21 21:25   ` Dave Jiang
2026-01-20 22:26 ` [PATCH v4 06/10] PCI: wire CXL reset prepare/cleanup smadhavan
2026-01-21 22:13   ` Dave Jiang
2026-01-22  2:17     ` Srirangan Madhavan
2026-01-22 15:11       ` Dave Jiang
2026-01-24  7:54   ` kernel test robot
2026-01-20 22:26 ` [PATCH v4 07/10] cxl: add host cache flush and multi-function reset smadhavan
2026-01-21 11:20   ` Jonathan Cameron [this message]
2026-01-21 20:27     ` Davidlohr Bueso
2026-01-22  9:53       ` Jonathan Cameron
2026-01-21 22:19     ` Vikram Sethi
2026-01-22  9:40       ` Souvik Chakravarty
     [not found]     ` <PH7PR12MB9175CDFC163843BB497073CEBD96A@PH7PR12MB9175.namprd12.prod.outlook.com>
2026-01-22 10:31       ` Jonathan Cameron
2026-01-22 19:24         ` Vikram Sethi
2026-01-23 13:13           ` Jonathan Cameron
2026-01-21 23:59   ` Dave Jiang
2026-01-20 22:26 ` [PATCH v4 08/10] cxl: add DVSEC config save/restore smadhavan
2026-01-21 11:31   ` Jonathan Cameron
2026-01-20 22:26 ` [PATCH v4 09/10] PCI: save/restore CXL config around reset smadhavan
2026-01-21 22:32   ` Dave Jiang
2026-01-22 10:01   ` Lukas Wunner
2026-01-22 10:47     ` Jonathan Cameron
2026-01-26 22:34       ` Alex Williamson
2026-03-12 18:24         ` Jonathan Cameron
2026-01-20 22:26 ` [PATCH v4 10/10] cxl: add HDM decoder and IDE save/restore smadhavan
2026-01-21 11:42   ` Jonathan Cameron
2026-01-22 15:09   ` Dave Jiang
2026-01-21  1:19 ` [PATCH v4 0/10] CXL Reset support for Type 2 devices Alison Schofield
2026-01-22  0:00 ` Bjorn Helgaas
2026-01-27 16:33 ` Alex Williamson
2026-01-27 17:02   ` dan.j.williams
2026-01-27 18:07     ` Vikram Sethi
2026-01-28  3:42       ` dan.j.williams
2026-01-28 12:36         ` Jonathan Cameron

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260121112005.00001e80@huawei.com \
    --to=jonathan.cameron@huawei.com \
    --cc=Smita.KoralahalliChannabasappa@amd.com \
    --cc=alison.schofield@intel.com \
    --cc=bhelgaas@google.com \
    --cc=dan.j.williams@intel.com \
    --cc=dave.jiang@intel.com \
    --cc=dave@stgolabs.net \
    --cc=huaisheng.ye@intel.com \
    --cc=ira.weiny@intel.com \
    --cc=jsequeira@nvidia.com \
    --cc=linux-cxl@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=ming.li@zohomail.com \
    --cc=mochs@nvidia.com \
    --cc=rrichter@amd.com \
    --cc=sdonthineni@nvidia.com \
    --cc=smadhavan@nvidia.com \
    --cc=vaslot@nvidia.com \
    --cc=vidyas@nvidia.com \
    --cc=vishal.l.verma@intel.com \
    --cc=vsethi@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox