From: Bjorn Helgaas <bhelgaas@google.com>
To: Wei Yang <weiyang@linux.vnet.ibm.com>,
benh@au1.ibm.com, gwshan@linux.vnet.ibm.com
Cc: linux-pci@vger.kernel.org, linuxppc-dev@lists.ozlabs.org
Subject: [PATCH v12 19/21] powerpc/powernv: Group VF PE when IOV BAR is big on PHB3
Date: Tue, 24 Feb 2015 02:35:12 -0600 [thread overview]
Message-ID: <20150224083512.32124.68785.stgit@bhelgaas-glaptop2.roam.corp.google.com> (raw)
In-Reply-To: <20150224082939.32124.45744.stgit@bhelgaas-glaptop2.roam.corp.google.com>
From: Wei Yang <weiyang@linux.vnet.ibm.com>
When IOV BAR is big, each is covered by 4 M64 windows. This leads to
several VF PE sits in one PE in terms of M64.
Group VF PEs according to the M64 allocation.
[bhelgaas: use dev_printk() when possible]
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
arch/powerpc/include/asm/pci-bridge.h | 2
arch/powerpc/platforms/powernv/pci-ioda.c | 197 +++++++++++++++++++++++------
2 files changed, 154 insertions(+), 45 deletions(-)
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index d824bb184ab8..958ea8675691 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -182,7 +182,7 @@ struct pci_dn {
#define M64_PER_IOV 4
int m64_per_iov;
#define IODA_INVALID_M64 (-1)
- int m64_wins[PCI_SRIOV_NUM_BARS];
+ int m64_wins[PCI_SRIOV_NUM_BARS][M64_PER_IOV];
#endif /* CONFIG_PCI_IOV */
#endif
struct list_head child_list;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 30b7c3909746..b265d5da601b 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1152,26 +1152,27 @@ static int pnv_pci_vf_release_m64(struct pci_dev *pdev)
struct pci_controller *hose;
struct pnv_phb *phb;
struct pci_dn *pdn;
- int i;
+ int i, j;
bus = pdev->bus;
hose = pci_bus_to_host(bus);
phb = hose->private_data;
pdn = pci_get_pdn(pdev);
- for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
- if (pdn->m64_wins[i] == IODA_INVALID_M64)
- continue;
- opal_pci_phb_mmio_enable(phb->opal_id,
- OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i], 0);
- clear_bit(pdn->m64_wins[i], &phb->ioda.m64_bar_alloc);
- pdn->m64_wins[i] = IODA_INVALID_M64;
- }
+ for (i = 0; i < PCI_SRIOV_NUM_BARS; i++)
+ for (j = 0; j < M64_PER_IOV; j++) {
+ if (pdn->m64_wins[i][j] == IODA_INVALID_M64)
+ continue;
+ opal_pci_phb_mmio_enable(phb->opal_id,
+ OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 0);
+ clear_bit(pdn->m64_wins[i][j], &phb->ioda.m64_bar_alloc);
+ pdn->m64_wins[i][j] = IODA_INVALID_M64;
+ }
return 0;
}
-static int pnv_pci_vf_assign_m64(struct pci_dev *pdev)
+static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 vf_num)
{
struct pci_bus *bus;
struct pci_controller *hose;
@@ -1179,17 +1180,33 @@ static int pnv_pci_vf_assign_m64(struct pci_dev *pdev)
struct pci_dn *pdn;
unsigned int win;
struct resource *res;
- int i;
+ int i, j;
int64_t rc;
+ int total_vfs;
+ resource_size_t size, start;
+ int pe_num;
+ int vf_groups;
+ int vf_per_group;
bus = pdev->bus;
hose = pci_bus_to_host(bus);
phb = hose->private_data;
pdn = pci_get_pdn(pdev);
+ total_vfs = pci_sriov_get_totalvfs(pdev);
/* Initialize the m64_wins to IODA_INVALID_M64 */
for (i = 0; i < PCI_SRIOV_NUM_BARS; i++)
- pdn->m64_wins[i] = IODA_INVALID_M64;
+ for (j = 0; j < M64_PER_IOV; j++)
+ pdn->m64_wins[i][j] = IODA_INVALID_M64;
+
+ if (pdn->m64_per_iov == M64_PER_IOV) {
+ vf_groups = (vf_num <= M64_PER_IOV) ? vf_num: M64_PER_IOV;
+ vf_per_group = (vf_num <= M64_PER_IOV)? 1:
+ __roundup_pow_of_two(vf_num) / pdn->m64_per_iov;
+ } else {
+ vf_groups = 1;
+ vf_per_group = 1;
+ }
for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
res = &pdev->resource[i + PCI_IOV_RESOURCES];
@@ -1199,35 +1216,61 @@ static int pnv_pci_vf_assign_m64(struct pci_dev *pdev)
if (!pnv_pci_is_mem_pref_64(res->flags))
continue;
- do {
- win = find_next_zero_bit(&phb->ioda.m64_bar_alloc,
- phb->ioda.m64_bar_idx + 1, 0);
-
- if (win >= phb->ioda.m64_bar_idx + 1)
- goto m64_failed;
- } while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc));
+ for (j = 0; j < vf_groups; j++) {
+ do {
+ win = find_next_zero_bit(&phb->ioda.m64_bar_alloc,
+ phb->ioda.m64_bar_idx + 1, 0);
+
+ if (win >= phb->ioda.m64_bar_idx + 1)
+ goto m64_failed;
+ } while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc));
+
+ pdn->m64_wins[i][j] = win;
+
+ if (pdn->m64_per_iov == M64_PER_IOV) {
+ size = pci_iov_resource_size(pdev,
+ PCI_IOV_RESOURCES + i);
+ size = size * vf_per_group;
+ start = res->start + size * j;
+ } else {
+ size = resource_size(res);
+ start = res->start;
+ }
- pdn->m64_wins[i] = win;
+ /* Map the M64 here */
+ if (pdn->m64_per_iov == M64_PER_IOV) {
+ pe_num = pdn->offset + j;
+ rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+ pe_num, OPAL_M64_WINDOW_TYPE,
+ pdn->m64_wins[i][j], 0);
+ }
- /* Map the M64 here */
- rc = opal_pci_set_phb_mem_window(phb->opal_id,
+ rc = opal_pci_set_phb_mem_window(phb->opal_id,
OPAL_M64_WINDOW_TYPE,
- pdn->m64_wins[i],
- res->start,
+ pdn->m64_wins[i][j],
+ start,
0, /* unused */
- resource_size(res));
- if (rc != OPAL_SUCCESS) {
- dev_err(&pdev->dev, "Failed to map M64 window #%d: %lld\n",
- win, rc);
- goto m64_failed;
- }
+ size);
- rc = opal_pci_phb_mmio_enable(phb->opal_id,
- OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i], 1);
- if (rc != OPAL_SUCCESS) {
- dev_err(&pdev->dev, "Failed to enable M64 window #%d: %llx\n",
- win, rc);
- goto m64_failed;
+
+ if (rc != OPAL_SUCCESS) {
+ dev_err(&pdev->dev, "Failed to map M64 window #%d: %lld\n",
+ win, rc);
+ goto m64_failed;
+ }
+
+ if (pdn->m64_per_iov == M64_PER_IOV)
+ rc = opal_pci_phb_mmio_enable(phb->opal_id,
+ OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 2);
+ else
+ rc = opal_pci_phb_mmio_enable(phb->opal_id,
+ OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 1);
+
+ if (rc != OPAL_SUCCESS) {
+ dev_err(&pdev->dev, "Failed to enable M64 window #%d: %llx\n",
+ win, rc);
+ goto m64_failed;
+ }
}
}
return 0;
@@ -1269,22 +1312,53 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe
pe->tce32_table = NULL;
}
-static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
+static void pnv_ioda_release_vf_PE(struct pci_dev *pdev, u16 vf_num)
{
struct pci_bus *bus;
struct pci_controller *hose;
struct pnv_phb *phb;
struct pnv_ioda_pe *pe, *pe_n;
struct pci_dn *pdn;
+ u16 vf_index;
+ int64_t rc;
bus = pdev->bus;
hose = pci_bus_to_host(bus);
phb = hose->private_data;
+ pdn = pci_get_pdn(pdev);
if (!pdev->is_physfn)
return;
- pdn = pci_get_pdn(pdev);
+ if (pdn->m64_per_iov == M64_PER_IOV && vf_num > M64_PER_IOV) {
+ int vf_group;
+ int vf_per_group;
+ int vf_index1;
+
+ vf_per_group = __roundup_pow_of_two(vf_num) / pdn->m64_per_iov;
+
+ for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++)
+ for (vf_index = vf_group * vf_per_group;
+ vf_index < (vf_group + 1) * vf_per_group &&
+ vf_index < vf_num;
+ vf_index++)
+ for (vf_index1 = vf_group * vf_per_group;
+ vf_index1 < (vf_group + 1) * vf_per_group &&
+ vf_index1 < vf_num;
+ vf_index1++){
+
+ rc = opal_pci_set_peltv(phb->opal_id,
+ pdn->offset + vf_index,
+ pdn->offset + vf_index1,
+ OPAL_REMOVE_PE_FROM_DOMAIN);
+
+ if (rc)
+ dev_warn(&pdev->dev, "%s: Failed to unlink same group PE#%d(%lld)\n",
+ __func__,
+ pdn->offset + vf_index1, rc);
+ }
+ }
+
list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) {
if (pe->parent_dev != pdev)
continue;
@@ -1319,10 +1393,11 @@ void pnv_pci_sriov_disable(struct pci_dev *pdev)
vf_num = pdn->vf_pes;
/* Release VF PEs */
- pnv_ioda_release_vf_PE(pdev);
+ pnv_ioda_release_vf_PE(pdev, vf_num);
if (phb->type == PNV_PHB_IODA2) {
- pnv_pci_vf_resource_shift(pdev, -pdn->offset);
+ if (pdn->m64_per_iov == 1)
+ pnv_pci_vf_resource_shift(pdev, -pdn->offset);
/* Release M64 windows */
pnv_pci_vf_release_m64(pdev);
@@ -1344,6 +1419,7 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 vf_num)
int pe_num;
u16 vf_index;
struct pci_dn *pdn;
+ int64_t rc;
bus = pdev->bus;
hose = pci_bus_to_host(bus);
@@ -1392,6 +1468,37 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 vf_num)
pnv_pci_ioda2_setup_dma_pe(phb, pe);
}
+
+ if (pdn->m64_per_iov == M64_PER_IOV && vf_num > M64_PER_IOV) {
+ int vf_group;
+ int vf_per_group;
+ int vf_index1;
+
+ vf_per_group = __roundup_pow_of_two(vf_num) / pdn->m64_per_iov;
+
+ for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++) {
+ for (vf_index = vf_group * vf_per_group;
+ vf_index < (vf_group + 1) * vf_per_group &&
+ vf_index < vf_num;
+ vf_index++) {
+ for (vf_index1 = vf_group * vf_per_group;
+ vf_index1 < (vf_group + 1) * vf_per_group &&
+ vf_index1 < vf_num;
+ vf_index1++) {
+
+ rc = opal_pci_set_peltv(phb->opal_id,
+ pdn->offset + vf_index,
+ pdn->offset + vf_index1,
+ OPAL_ADD_PE_TO_DOMAIN);
+
+ if (rc)
+ dev_warn(&pdev->dev, "%s: Failed to link same group PE#%d(%lld)\n",
+ __func__,
+ pdn->offset + vf_index1, rc);
+ }
+ }
+ }
+ }
}
int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 vf_num)
@@ -1424,16 +1531,18 @@ int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 vf_num)
mutex_unlock(&phb->ioda.pe_alloc_mutex);
/* Assign M64 window accordingly */
- ret = pnv_pci_vf_assign_m64(pdev);
+ ret = pnv_pci_vf_assign_m64(pdev, vf_num);
if (ret) {
dev_info(&pdev->dev, "Not enough M64 window resources\n");
goto m64_failed;
}
/* Do some magic shift */
- ret = pnv_pci_vf_resource_shift(pdev, pdn->offset);
- if (ret)
- goto m64_failed;
+ if (pdn->m64_per_iov == 1) {
+ ret = pnv_pci_vf_resource_shift(pdev, pdn->offset);
+ if (ret)
+ goto m64_failed;
+ }
}
/* Setup VF PEs */
next prev parent reply other threads:[~2015-02-24 8:35 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-02-24 8:32 [PATCH v12 00/21] Enable SRIOV on Power8 Bjorn Helgaas
2015-02-24 8:33 ` [PATCH v12 01/21] PCI: Print more info in sriov_enable() error message Bjorn Helgaas
2015-02-24 8:33 ` [PATCH v12 02/21] PCI: Print PF SR-IOV resource that contains all VF(n) BAR space Bjorn Helgaas
2015-02-24 8:33 ` [PATCH v12 03/21] PCI: Keep individual VF BAR size in struct pci_sriov Bjorn Helgaas
2015-02-24 8:33 ` [PATCH v12 04/21] PCI: Index IOV resources in the conventional style Bjorn Helgaas
2015-02-24 8:33 ` [PATCH v12 05/21] PCI: Refresh First VF Offset and VF Stride when updating NumVFs Bjorn Helgaas
2015-02-24 8:33 ` [PATCH v12 06/21] PCI: Calculate maximum number of buses required for VFs Bjorn Helgaas
2015-02-24 8:33 ` [PATCH v12 07/21] PCI: Export pci_iov_virtfn_bus() and pci_iov_virtfn_devfn() Bjorn Helgaas
2015-02-24 8:33 ` [PATCH v12 08/21] PCI: Add pcibios_sriov_enable() and pcibios_sriov_disable() Bjorn Helgaas
2015-02-24 8:39 ` Bjorn Helgaas
2015-03-02 6:53 ` Wei Yang
2015-02-24 8:33 ` [PATCH v12 09/21] PCI: Add pcibios_iov_resource_alignment() interface Bjorn Helgaas
2015-02-24 8:34 ` [PATCH v12 10/21] PCI: Consider additional PF's IOV BAR alignment in sizing and assigning Bjorn Helgaas
2015-02-24 8:41 ` Bjorn Helgaas
2015-03-02 7:32 ` Wei Yang
2015-03-11 2:36 ` Bjorn Helgaas
2015-03-11 9:17 ` Wei Yang
2015-02-24 8:34 ` [PATCH v12 11/21] powerpc/pci: Don't unset PCI resources for VFs Bjorn Helgaas
2015-02-24 8:44 ` Bjorn Helgaas
2015-03-02 7:34 ` Wei Yang
2015-02-24 8:34 ` [PATCH v12 12/21] powerpc/pci: Refactor pci_dn Bjorn Helgaas
2015-02-24 8:34 ` [PATCH v12 13/21] powerpc/powernv: Use pci_dn, not device_node, in PCI config accessor Bjorn Helgaas
2015-02-24 8:34 ` [PATCH v12 14/21] powerpc/powernv: Allocate struct pnv_ioda_pe iommu_table dynamically Bjorn Helgaas
2015-02-24 8:46 ` Bjorn Helgaas
2015-03-02 7:50 ` Wei Yang
2015-03-02 7:56 ` Benjamin Herrenschmidt
2015-03-02 8:02 ` Wei Yang
2015-03-11 2:47 ` Bjorn Helgaas
2015-03-11 6:13 ` Wei Yang
2015-02-24 8:34 ` [PATCH v12 15/21] powerpc/powernv: Reserve additional space for IOV BAR according to the number of total_pe Bjorn Helgaas
2015-02-24 8:52 ` Bjorn Helgaas
2015-03-02 7:41 ` Wei Yang
2015-03-11 2:51 ` Bjorn Helgaas
2015-03-11 6:22 ` Wei Yang
2015-03-11 13:40 ` Bjorn Helgaas
2015-02-24 8:34 ` [PATCH v12 16/21] powerpc/powernv: Implement pcibios_iov_resource_alignment() on powernv Bjorn Helgaas
2015-02-24 8:34 ` [PATCH v12 17/21] powerpc/powernv: Shift VF resource with an offset Bjorn Helgaas
2015-02-24 9:00 ` Bjorn Helgaas
2015-02-24 17:10 ` Bjorn Helgaas
2015-03-02 7:58 ` Wei Yang
2015-03-04 3:01 ` Wei Yang
2015-03-11 2:55 ` Bjorn Helgaas
2015-03-11 6:42 ` Wei Yang
2015-02-24 9:03 ` Bjorn Helgaas
2015-02-24 8:35 ` [PATCH v12 18/21] powerpc/powernv: Reserve additional space for IOV BAR, with m64_per_iov supported Bjorn Helgaas
2015-02-24 9:06 ` Bjorn Helgaas
2015-03-02 7:55 ` Wei Yang
2015-02-24 8:35 ` Bjorn Helgaas [this message]
2015-02-24 8:35 ` [PATCH v12 20/21] powerpc/pci: Remove unused struct pci_dn.pcidev field Bjorn Helgaas
2015-02-24 8:35 ` [PATCH v12 21/21] powerpc/pci: Add PCI resource alignment documentation Bjorn Helgaas
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=20150224083512.32124.68785.stgit@bhelgaas-glaptop2.roam.corp.google.com \
--to=bhelgaas@google.com \
--cc=benh@au1.ibm.com \
--cc=gwshan@linux.vnet.ibm.com \
--cc=linux-pci@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=weiyang@linux.vnet.ibm.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;
as well as URLs for NNTP newsgroup(s).