From: Logan Gunthorpe <logang@deltatee.com>
To: linux-kernel@vger.kernel.org, linux-ntb@googlegroups.com,
linux-pci@vger.kernel.org, iommu@lists.linux-foundation.org,
linux-kselftest@vger.kernel.org, Jon Mason <jdmason@kudzu.us>,
Bjorn Helgaas <bhelgaas@google.com>,
Joerg Roedel <joro@8bytes.org>
Cc: Allen Hubbe <allenbh@gmail.com>,
Dave Jiang <dave.jiang@intel.com>,
Serge Semin <fancer.lancer@gmail.com>,
Eric Pilmore <epilmore@gigaio.com>,
Logan Gunthorpe <logang@deltatee.com>
Subject: [PATCH v2 05/12] PCI/MSI: Support allocating virtual MSI interrupts
Date: Wed, 13 Feb 2019 10:54:47 -0700 [thread overview]
Message-ID: <20190213175454.7506-6-logang@deltatee.com> (raw)
In-Reply-To: <20190213175454.7506-1-logang@deltatee.com>
For NTB devices, we want to be able to trigger MSI interrupts
through a memory window. In these cases we may want to use
more interrupts than the NTB PCI device has available in its MSI-X
table.
We allow for this by creating a new 'virtual' interrupt. These
interrupts are allocated as usual but are not programmed into the
MSI-X table (as there may not be space for them).
The MSI address and data will then handled through an NTB MSI library
introduced later in this series.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
---
drivers/pci/msi.c | 55 +++++++++++++++++++++++++++++++++++++--------
include/linux/msi.h | 8 +++++++
include/linux/pci.h | 9 ++++++++
3 files changed, 63 insertions(+), 9 deletions(-)
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 4c0b47867258..e7810ec45c9d 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -192,6 +192,9 @@ static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
static void __iomem *pci_msix_desc_addr(struct msi_desc *desc)
{
+ if (desc->msi_attrib.is_virtual)
+ return NULL;
+
return desc->mask_base +
desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
}
@@ -206,14 +209,19 @@ static void __iomem *pci_msix_desc_addr(struct msi_desc *desc)
u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag)
{
u32 mask_bits = desc->masked;
+ void __iomem *desc_addr;
if (pci_msi_ignore_mask)
return 0;
+ desc_addr = pci_msix_desc_addr(desc);
+ if (!desc_addr)
+ return 0;
mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
if (flag)
mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
- writel(mask_bits, pci_msix_desc_addr(desc) + PCI_MSIX_ENTRY_VECTOR_CTRL);
+
+ writel(mask_bits, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
return mask_bits;
}
@@ -273,6 +281,11 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
if (entry->msi_attrib.is_msix) {
void __iomem *base = pci_msix_desc_addr(entry);
+ if (!base) {
+ WARN_ON(1);
+ return;
+ }
+
msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR);
msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR);
msg->data = readl(base + PCI_MSIX_ENTRY_DATA);
@@ -303,6 +316,9 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
} else if (entry->msi_attrib.is_msix) {
void __iomem *base = pci_msix_desc_addr(entry);
+ if (!base)
+ goto skip;
+
writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR);
writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR);
writel(msg->data, base + PCI_MSIX_ENTRY_DATA);
@@ -327,7 +343,13 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
msg->data);
}
}
+
+skip:
entry->msg = *msg;
+
+ if (entry->write_msi_msg)
+ entry->write_msi_msg(entry, entry->write_msi_msg_data);
+
}
void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg)
@@ -550,6 +572,7 @@ msi_setup_entry(struct pci_dev *dev, int nvec, const struct irq_affinity *affd)
entry->msi_attrib.is_msix = 0;
entry->msi_attrib.is_64 = !!(control & PCI_MSI_FLAGS_64BIT);
+ entry->msi_attrib.is_virtual = 0;
entry->msi_attrib.entry_nr = 0;
entry->msi_attrib.maskbit = !!(control & PCI_MSI_FLAGS_MASKBIT);
entry->msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */
@@ -674,6 +697,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
struct irq_affinity_desc *curmsk, *masks = NULL;
struct msi_desc *entry;
int ret, i;
+ int vec_count = pci_msix_vec_count(dev);
if (affd)
masks = irq_create_affinity_masks(nvec, affd);
@@ -696,6 +720,10 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
entry->msi_attrib.entry_nr = entries[i].entry;
else
entry->msi_attrib.entry_nr = i;
+
+ entry->msi_attrib.is_virtual =
+ entry->msi_attrib.entry_nr >= vec_count;
+
entry->msi_attrib.default_irq = dev->irq;
entry->mask_base = base;
@@ -714,12 +742,19 @@ static void msix_program_entries(struct pci_dev *dev,
{
struct msi_desc *entry;
int i = 0;
+ void __iomem *desc_addr;
for_each_pci_msi_entry(entry, dev) {
if (entries)
entries[i++].vector = entry->irq;
- entry->masked = readl(pci_msix_desc_addr(entry) +
- PCI_MSIX_ENTRY_VECTOR_CTRL);
+
+ desc_addr = pci_msix_desc_addr(entry);
+ if (desc_addr)
+ entry->masked = readl(desc_addr +
+ PCI_MSIX_ENTRY_VECTOR_CTRL);
+ else
+ entry->masked = 0;
+
msix_mask_irq(entry, 1);
}
}
@@ -932,7 +967,8 @@ int pci_msix_vec_count(struct pci_dev *dev)
EXPORT_SYMBOL(pci_msix_vec_count);
static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries,
- int nvec, const struct irq_affinity *affd)
+ int nvec, const struct irq_affinity *affd,
+ int flags)
{
int nr_entries;
int i, j;
@@ -943,7 +979,7 @@ static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries,
nr_entries = pci_msix_vec_count(dev);
if (nr_entries < 0)
return nr_entries;
- if (nvec > nr_entries)
+ if (nvec > nr_entries && !(flags & PCI_IRQ_VIRTUAL))
return nr_entries;
if (entries) {
@@ -1086,7 +1122,8 @@ EXPORT_SYMBOL(pci_enable_msi);
static int __pci_enable_msix_range(struct pci_dev *dev,
struct msix_entry *entries, int minvec,
- int maxvec, const struct irq_affinity *affd)
+ int maxvec, const struct irq_affinity *affd,
+ int flags)
{
int rc, nvec = maxvec;
@@ -1110,7 +1147,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev,
return -ENOSPC;
}
- rc = __pci_enable_msix(dev, entries, nvec, affd);
+ rc = __pci_enable_msix(dev, entries, nvec, affd, flags);
if (rc == 0)
return nvec;
@@ -1141,7 +1178,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev,
int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
int minvec, int maxvec)
{
- return __pci_enable_msix_range(dev, entries, minvec, maxvec, NULL);
+ return __pci_enable_msix_range(dev, entries, minvec, maxvec, NULL, 0);
}
EXPORT_SYMBOL(pci_enable_msix_range);
@@ -1181,7 +1218,7 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs,
if (flags & PCI_IRQ_MSIX) {
msix_vecs = __pci_enable_msix_range(dev, NULL, min_vecs,
- max_vecs, affd);
+ max_vecs, affd, flags);
if (msix_vecs > 0)
return msix_vecs;
}
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 784fb52b9900..5044b4906102 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -56,6 +56,10 @@ struct fsl_mc_msi_desc {
* @msg: The last set MSI message cached for reuse
* @affinity: Optional pointer to a cpu affinity mask for this descriptor
*
+ * @write_msi_msg: Callback that may be called when the MSI message
+ * address or data changes
+ * @write_msi_msg_data: Data parameter for the callback.
+ *
* @masked: [PCI MSI/X] Mask bits
* @is_msix: [PCI MSI/X] True if MSI-X
* @multiple: [PCI MSI/X] log2 num of messages allocated
@@ -78,6 +82,9 @@ struct msi_desc {
struct msi_msg msg;
struct irq_affinity_desc *affinity;
+ void (*write_msi_msg)(struct msi_desc *entry, void *data);
+ void *write_msi_msg_data;
+
union {
/* PCI MSI/X specific data */
struct {
@@ -88,6 +95,7 @@ struct msi_desc {
__u8 multi_cap : 3;
__u8 maskbit : 1;
__u8 is_64 : 1;
+ __u8 is_virtual : 1;
__u16 entry_nr;
unsigned default_irq;
} msi_attrib;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 65f1d8c2f082..f8df9637f3fc 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1352,6 +1352,15 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode,
#define PCI_IRQ_MSI (1 << 1) /* Allow MSI interrupts */
#define PCI_IRQ_MSIX (1 << 2) /* Allow MSI-X interrupts */
#define PCI_IRQ_AFFINITY (1 << 3) /* Auto-assign affinity */
+
+/*
+ * Virtual interrupts allow for more interrupts to be allocated
+ * than the device has interrupts for. These are not programmed
+ * into the device's MSI-X table and must be handled by some
+ * other driver means.
+ */
+#define PCI_IRQ_VIRTUAL (1 << 4)
+
#define PCI_IRQ_ALL_TYPES \
(PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX)
--
2.19.0
next prev parent reply other threads:[~2019-02-13 17:55 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-13 17:54 [PATCH v2 00/12] Support using MSI interrupts in ntb_transport Logan Gunthorpe
2019-02-13 17:54 ` [PATCH v2 01/12] iommu/vt-d: Implement dma_[un]map_resource() Logan Gunthorpe
2019-02-13 17:57 ` Logan Gunthorpe
2019-02-13 17:54 ` [PATCH v2 02/12] NTB: ntb_transport: Ensure the destination buffer is mapped for TX DMA Logan Gunthorpe
2019-02-13 17:54 ` [PATCH v2 03/12] iommu/vt-d: Add helper to set an IRTE to verify only the bus number Logan Gunthorpe
2019-02-13 17:54 ` [PATCH v2 04/12] iommu/vt-d: Allow interrupts from the entire bus for aliased devices Logan Gunthorpe
2019-02-13 17:54 ` Logan Gunthorpe [this message]
2019-02-13 17:54 ` [PATCH v2 06/12] PCI/switchtec: Add module parameter to request more interrupts Logan Gunthorpe
2019-02-13 17:54 ` [PATCH v2 07/12] NTB: Introduce functions to calculate multi-port resource index Logan Gunthorpe
2019-03-06 1:24 ` Serge Semin
2019-03-06 19:11 ` Logan Gunthorpe
2019-03-06 22:45 ` Serge Semin
2019-03-06 23:22 ` Logan Gunthorpe
2019-03-12 20:42 ` Serge Semin
2019-03-12 21:30 ` Logan Gunthorpe
2019-02-13 17:54 ` [PATCH v2 08/12] NTB: Rename ntb.c to support multiple source files in the module Logan Gunthorpe
2019-02-13 17:54 ` [PATCH v2 09/12] NTB: Introduce MSI library Logan Gunthorpe
2019-03-06 20:26 ` Serge Semin
2019-03-06 21:35 ` Logan Gunthorpe
2019-03-06 23:13 ` Serge Semin
2019-02-13 17:54 ` [PATCH v2 10/12] NTB: Introduce NTB MSI Test Client Logan Gunthorpe
2019-03-06 20:44 ` Serge Semin
2019-03-06 21:39 ` Logan Gunthorpe
2019-02-13 17:54 ` [PATCH v2 11/12] NTB: Add ntb_msi_test support to ntb_test Logan Gunthorpe
2019-02-13 17:54 ` [PATCH v2 12/12] NTB: Add MSI interrupt support to ntb_transport Logan Gunthorpe
2019-02-26 9:34 ` [PATCH v2 00/12] Support using MSI interrupts in ntb_transport Joerg Roedel
2019-02-26 16:18 ` Logan Gunthorpe
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=20190213175454.7506-6-logang@deltatee.com \
--to=logang@deltatee.com \
--cc=allenbh@gmail.com \
--cc=bhelgaas@google.com \
--cc=dave.jiang@intel.com \
--cc=epilmore@gigaio.com \
--cc=fancer.lancer@gmail.com \
--cc=iommu@lists.linux-foundation.org \
--cc=jdmason@kudzu.us \
--cc=joro@8bytes.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-ntb@googlegroups.com \
--cc=linux-pci@vger.kernel.org \
/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;
as well as URLs for NNTP newsgroup(s).