All of lore.kernel.org
 help / color / mirror / Atom feed
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
To: Niklas Cassel <cassel@kernel.org>
Cc: "Lorenzo Pieralisi" <lpieralisi@kernel.org>,
	"Krzysztof Wilczyński" <kw@linux.com>,
	"Kishon Vijay Abraham I" <kishon@kernel.org>,
	"Bjorn Helgaas" <bhelgaas@google.com>,
	"Shradha Todi" <shradha.t@samsung.com>,
	"Damien Le Moal" <dlemoal@kernel.org>,
	linux-pci@vger.kernel.org, arnd@arndb.de
Subject: Re: [PATCH v3 9/9] PCI: endpoint: Set prefetch when allocating memory for 64-bit BARs
Date: Fri, 15 Mar 2024 12:14:08 +0530	[thread overview]
Message-ID: <20240315064408.GI3375@thinkpad> (raw)
In-Reply-To: <20240313105804.100168-10-cassel@kernel.org>

+ Arnd

On Wed, Mar 13, 2024 at 11:58:01AM +0100, Niklas Cassel wrote:
> From the PCIe 6.0 base spec:

It'd be good to mention the section also.

> "Generally only 64-bit BARs are good candidates, since only Legacy
> Endpoints are permitted to set the Prefetchable bit in 32-bit BARs,
> and most scalable platforms map all 32-bit Memory BARs into
> non-prefetchable Memory Space regardless of the Prefetchable bit value."
> 
> "For a PCI Express Endpoint, 64-bit addressing must be supported for all
> BARs that have the Prefetchable bit Set. 32-bit addressing is permitted
> for all BARs that do not have the Prefetchable bit Set."
> 
> "Any device that has a range that behaves like normal memory should mark
> the range as prefetchable. A linear frame buffer in a graphics device is
> an example of a range that should be marked prefetchable."
> 
> The PCIe spec tells us that we should have the prefetchable bit set for
> 64-bit BARs backed by "normal memory". The backing memory that we allocate
> for a 64-bit BAR using pci_epf_alloc_space() (which calls
> dma_alloc_coherent()) is obviously "normal memory".
> 

I'm not sure this is correct. Memory returned by 'dma_alloc_coherent' is not the
'normal memory' but rather 'consistent/coherent memory'. Here the question is,
can the memory returned by dma_alloc_coherent() be prefetched or write-combined
on all architectures.

I hope Arnd can answer this question.

- Mani

> Thus, set the prefetchable bit when allocating backing memory for a 64-bit
> BAR.
> 
> Signed-off-by: Niklas Cassel <cassel@kernel.org>
> ---
>  drivers/pci/endpoint/pci-epf-core.c | 3 +++
>  1 file changed, 3 insertions(+)
> 
> diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c
> index e7dbbeb1f0de..20d2bde0747c 100644
> --- a/drivers/pci/endpoint/pci-epf-core.c
> +++ b/drivers/pci/endpoint/pci-epf-core.c
> @@ -309,6 +309,9 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar,
>  	else
>  		epf_bar[bar].flags |= PCI_BASE_ADDRESS_MEM_TYPE_32;
>  
> +	if (epf_bar[bar].flags & PCI_BASE_ADDRESS_MEM_TYPE_64)
> +		epf_bar[bar].flags |= PCI_BASE_ADDRESS_MEM_PREFETCH;
> +
>  	return space;
>  }
>  EXPORT_SYMBOL_GPL(pci_epf_alloc_space);
> -- 
> 2.44.0
> 

-- 
மணிவண்ணன் சதாசிவம்

  reply	other threads:[~2024-03-15  6:44 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-03-13 10:57 [PATCH v3 0/9] PCI: endpoint: set prefetchable bit for 64-bit BARs Niklas Cassel
2024-03-13 10:57 ` Niklas Cassel
2024-03-13 10:57 ` Niklas Cassel
2024-03-13 10:57 ` [PATCH v3 1/9] PCI: endpoint: pci-epf-test: Fix incorrect loop increment Niklas Cassel
2024-03-15  5:20   ` Manivannan Sadhasivam
2024-03-20 10:54     ` Niklas Cassel
2024-03-13 10:57 ` [PATCH v3 2/9] PCI: endpoint: Allocate a 64-bit BAR if that is the only option Niklas Cassel
2024-03-15  5:24   ` Manivannan Sadhasivam
2024-03-13 10:57 ` [PATCH v3 3/9] PCI: endpoint: pci-epf-test: Remove superfluous code Niklas Cassel
2024-03-15  5:25   ` Manivannan Sadhasivam
2024-03-13 10:57 ` [PATCH v3 4/9] PCI: endpoint: pci-epf-test: Simplify pci_epf_test_alloc_space() loop Niklas Cassel
2024-03-15  5:29   ` Manivannan Sadhasivam
2024-03-13 10:57 ` [PATCH v3 5/9] PCI: endpoint: pci-epf-test: Simplify pci_epf_test_set_bar() loop Niklas Cassel
2024-03-15  5:39   ` Manivannan Sadhasivam
2024-03-20 11:08     ` Niklas Cassel
2024-03-13 10:57 ` [PATCH v3 6/9] PCI: endpoint: pci-epf-test: Clean up pci_epf_test_unbind() Niklas Cassel
2024-03-15  5:42   ` Manivannan Sadhasivam
2024-03-20 11:11     ` Niklas Cassel
2024-03-13 10:57 ` [PATCH v3 7/9] PCI: cadence: Set a 64-bit BAR if requested Niklas Cassel
2024-03-15  5:46   ` Manivannan Sadhasivam
2024-03-20 11:14     ` Niklas Cassel
2024-03-13 10:58 ` [PATCH v3 8/9] PCI: rockchip-ep: " Niklas Cassel
2024-03-13 10:58   ` Niklas Cassel
2024-03-13 10:58   ` Niklas Cassel
2024-03-15  5:47   ` Manivannan Sadhasivam
2024-03-15  5:47     ` Manivannan Sadhasivam
2024-03-15  5:47     ` Manivannan Sadhasivam
2024-04-12 17:51   ` Bjorn Helgaas
2024-04-12 17:51     ` Bjorn Helgaas
2024-04-12 17:51     ` Bjorn Helgaas
2024-04-12 21:39     ` Niklas Cassel
2024-04-12 21:39       ` Niklas Cassel
2024-04-12 21:39       ` Niklas Cassel
2024-04-12 22:00       ` Bjorn Helgaas
2024-04-12 22:00         ` Bjorn Helgaas
2024-04-12 22:00         ` Bjorn Helgaas
2024-04-12 18:59   ` Bjorn Helgaas
2024-04-12 18:59     ` Bjorn Helgaas
2024-04-12 18:59     ` Bjorn Helgaas
2024-04-12 22:02     ` Niklas Cassel
2024-04-12 22:02       ` Niklas Cassel
2024-04-12 22:02       ` Niklas Cassel
2024-04-12 22:11       ` Bjorn Helgaas
2024-04-12 22:11         ` Bjorn Helgaas
2024-04-12 22:11         ` Bjorn Helgaas
2024-03-13 10:58 ` [PATCH v3 9/9] PCI: endpoint: Set prefetch when allocating memory for 64-bit BARs Niklas Cassel
2024-03-15  6:44   ` Manivannan Sadhasivam [this message]
2024-03-15 17:29     ` Arnd Bergmann
2024-03-17 11:54       ` Niklas Cassel
2024-03-18  3:53         ` Manivannan Sadhasivam
2024-03-18  7:25         ` Arnd Bergmann
2024-03-18 15:13           ` Niklas Cassel
2024-03-18 15:49             ` Arnd Bergmann
2024-03-19  6:22               ` Manivannan Sadhasivam
2024-03-18  4:30       ` Manivannan Sadhasivam
2024-03-18  6:44         ` Arnd Bergmann
2024-03-19  6:20           ` Manivannan Sadhasivam

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=20240315064408.GI3375@thinkpad \
    --to=manivannan.sadhasivam@linaro.org \
    --cc=arnd@arndb.de \
    --cc=bhelgaas@google.com \
    --cc=cassel@kernel.org \
    --cc=dlemoal@kernel.org \
    --cc=kishon@kernel.org \
    --cc=kw@linux.com \
    --cc=linux-pci@vger.kernel.org \
    --cc=lpieralisi@kernel.org \
    --cc=shradha.t@samsung.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.