linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Alexey Kardashevskiy <aik@ozlabs.ru>
To: linuxppc-dev@lists.ozlabs.org
Cc: "Jose Ricardo Ziviani" <joserz@linux.ibm.com>,
	"Alexey Kardashevskiy" <aik@ozlabs.ru>,
	"Alistair Popple" <alistair@popple.id.au>,
	"Daniel Henrique Barboza" <danielhb413@gmail.com>,
	"Alex Williamson" <alex.williamson@redhat.com>,
	kvm-ppc@vger.kernel.org, "Sam Bobroff" <sbobroff@linux.ibm.com>,
	"Piotr Jaroszynski" <pjaroszynski@nvidia.com>,
	"Leonardo Augusto Guimarães Garcia" <lagarcia@br.ibm.com>,
	"Reza Arbab" <arbab@linux.ibm.com>,
	"David Gibson" <david@gibson.dropbear.id.au>
Subject: [PATCH kernel v5 10/20] powerpc/iommu_api: Move IOMMU groups setup to a single place
Date: Thu, 13 Dec 2018 17:17:24 +1100	[thread overview]
Message-ID: <20181213061734.16651-11-aik@ozlabs.ru> (raw)
In-Reply-To: <20181213061734.16651-1-aik@ozlabs.ru>

Registering new IOMMU groups and adding devices to them are separated in
code and the latter is dug in the DMA setup code which it does not
really belong to.

This moved IOMMU groups setup to a separate helper which registers a group
and adds devices as before. This does not make a difference as IOMMU
groups are not used anyway; the only dependency here is that
iommu_add_device() requires a valid pointer to an iommu_table
(set by set_iommu_table_base()).

To keep the old behaviour, this does not add new IOMMU groups for PEs
with no DMA weigth and also skips NVLink bridges which do not have
pci_controller_ops::setup_bridge (the normal way of adding PEs).

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
 arch/powerpc/platforms/powernv/pci-ioda.c | 80 +++++++++++++++++++----
 1 file changed, 66 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index b86a6e0..1168b185 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1269,6 +1269,8 @@ static void pnv_ioda_setup_npu_PEs(struct pci_bus *bus)
 		pnv_ioda_setup_npu_PE(pdev);
 }
 
+static void pnv_ioda_setup_bus_iommu_group(struct pnv_ioda_pe *pe);
+
 static void pnv_pci_ioda_setup_PEs(void)
 {
 	struct pci_controller *hose;
@@ -1591,6 +1593,7 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 		mutex_unlock(&phb->ioda.pe_list_mutex);
 
 		pnv_pci_ioda2_setup_dma_pe(phb, pe);
+		pnv_ioda_setup_bus_iommu_group(pe);
 	}
 }
 
@@ -1930,21 +1933,16 @@ static u64 pnv_pci_ioda_dma_get_required_mask(struct pci_dev *pdev)
 	return mask;
 }
 
-static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
-				   struct pci_bus *bus,
-				   bool add_to_group)
+static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
 {
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
 		set_dma_offset(&dev->dev, pe->tce_bypass_base);
-		if (add_to_group)
-			iommu_add_device(&pe->table_group, &dev->dev);
 
 		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
-			pnv_ioda_setup_bus_dma(pe, dev->subordinate,
-					add_to_group);
+			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
 	}
 }
 
@@ -2374,7 +2372,7 @@ static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
 	iommu_init_table(tbl, phb->hose->node);
 
 	if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
-		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
 	return;
  fail:
@@ -2607,7 +2605,7 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
 	pnv_pci_ioda2_set_bypass(pe, false);
 	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
 	if (pe->pbus)
-		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 	iommu_tce_table_put(tbl);
 }
 
@@ -2618,7 +2616,7 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
 
 	pnv_pci_ioda2_setup_default_config(pe);
 	if (pe->pbus)
-		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 }
 
 static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
@@ -2735,12 +2733,68 @@ static struct iommu_table_group_ops pnv_pci_ioda2_npu_ops = {
 	.release_ownership = pnv_ioda2_release_ownership,
 };
 
+static void pnv_ioda_setup_bus_iommu_group_add_devices(struct pnv_ioda_pe *pe,
+		struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		iommu_add_device(&pe->table_group, &dev->dev);
+
+		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
+			pnv_ioda_setup_bus_iommu_group_add_devices(pe,
+					dev->subordinate);
+	}
+}
+
+static void pnv_ioda_setup_bus_iommu_group(struct pnv_ioda_pe *pe)
+{
+	if (!pnv_pci_ioda_pe_dma_weight(pe))
+		return;
+
+	iommu_register_group(&pe->table_group, pe->phb->hose->global_number,
+			pe->pe_number);
+
+	/*
+	 * set_iommu_table_base(&pe->pdev->dev, tbl) should have been called
+	 * by now
+	 */
+	if (pe->flags & PNV_IODA_PE_DEV)
+		iommu_add_device(&pe->table_group, &pe->pdev->dev);
+	else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
+		pnv_ioda_setup_bus_iommu_group_add_devices(pe, pe->pbus);
+}
+
 static void pnv_pci_ioda_setup_iommu_api(void)
 {
 	struct pci_controller *hose, *tmp;
 	struct pnv_phb *phb;
 	struct pnv_ioda_pe *pe, *gpe;
 
+	/*
+	 * There are 4 types of PEs:
+	 * - PNV_IODA_PE_BUS: a downstream port with an adapter,
+	 *   created from pnv_pci_setup_bridge();
+	 * - PNV_IODA_PE_BUS_ALL: a PCI-PCIX bridge with devices behind it,
+	 *   created from pnv_pci_setup_bridge();
+	 * - PNV_IODA_PE_VF: a SRIOV virtual function,
+	 *   created from pnv_pcibios_sriov_enable();
+	 * - PNV_IODA_PE_DEV: an NPU or OCAPI device,
+	 *   created from pnv_pci_ioda_fixup().
+	 *
+	 * Normally a PE is represented by an IOMMU group, however for
+	 * devices with side channels the groups need to be more strict.
+	 */
+	list_for_each_entry(hose, &hose_list, list_node) {
+		phb = hose->private_data;
+
+		if (phb->type == PNV_PHB_NPU_NVLINK)
+			continue;
+
+		list_for_each_entry(pe, &phb->ioda.pe_list, list)
+			pnv_ioda_setup_bus_iommu_group(pe);
+	}
+
 	/*
 	 * Now we have all PHBs discovered, time to add NPU devices to
 	 * the corresponding IOMMU groups.
@@ -2759,6 +2813,7 @@ static void pnv_pci_ioda_setup_iommu_api(void)
 	}
 }
 #else /* !CONFIG_IOMMU_API */
+static void pnv_ioda_setup_bus_iommu_group(struct pnv_ioda_pe *pe) { }
 static void pnv_pci_ioda_setup_iommu_api(void) { };
 #endif
 
@@ -2801,9 +2856,6 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	/* TVE #1 is selected by PCI address bit 59 */
 	pe->tce_bypass_base = 1ull << 59;
 
-	iommu_register_group(&pe->table_group, phb->hose->global_number,
-			pe->pe_number);
-
 	/* The PE will reserve all possible 32-bits space */
 	pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n",
 		phb->ioda.m32_pci_base);
@@ -2824,7 +2876,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 		return;
 
 	if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
-		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 }
 
 #ifdef CONFIG_PCI_MSI
-- 
2.17.1


  parent reply	other threads:[~2018-12-13  6:55 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-12-13  6:17 [PATCH kernel v5 00/20] powerpc/powernv/npu, vfio: NVIDIA V100 + P9 passthrough Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 01/20] powerpc/ioda/npu: Call skiboot's hot reset hook when disabling NPU2 Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 02/20] powerpc/mm/iommu/vfio_spapr_tce: Change mm_iommu_get to reference a region Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 03/20] powerpc/vfio/iommu/kvm: Do not pin device memory Alexey Kardashevskiy
2018-12-14  3:18   ` Paul Mackerras
2018-12-18 23:33   ` Michael Ellerman
2018-12-13  6:17 ` [PATCH kernel v5 04/20] powerpc/powernv: Move npu struct from pnv_phb to pci_controller Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 05/20] powerpc/powernv/npu: Move OPAL calls away from context manipulation Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 06/20] powerpc/pseries/iommu: Use memory@ nodes in max RAM address calculation Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 07/20] powerpc/pseries/npu: Enable platform support Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 08/20] powerpc/pseries: Remove IOMMU API support for non-LPAR systems Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 09/20] powerpc/powernv/pseries: Rework device adding to IOMMU groups Alexey Kardashevskiy
2018-12-13  6:17 ` Alexey Kardashevskiy [this message]
2018-12-18 23:35   ` [PATCH kernel v5 10/20] powerpc/iommu_api: Move IOMMU groups setup to a single place Michael Ellerman
2018-12-19  6:17     ` Alexey Kardashevskiy
2018-12-19  9:51       ` Michael Ellerman
2018-12-13  6:17 ` [PATCH kernel v5 11/20] powerpc/powernv: Reference iommu_table while it is linked to a group Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 12/20] powerpc/powernv/npu: Move single TVE handling to NPU PE Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 13/20] powerpc/powernv/npu: Convert NPU IOMMU helpers to iommu_table_group_ops Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 14/20] powerpc/powernv/npu: Add compound IOMMU groups Alexey Kardashevskiy
2018-12-19  0:17   ` Michael Ellerman
2018-12-19  6:54     ` Alexey Kardashevskiy
2018-12-19 10:00       ` Michael Ellerman
2018-12-20  2:18         ` Alexey Kardashevskiy
2018-12-20  5:33           ` Michael Ellerman
2018-12-13  6:17 ` [PATCH kernel v5 15/20] powerpc/powernv/npu: Add release_ownership hook Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 16/20] powerpc/powernv/npu: Check mmio_atsd array bounds when populating Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 17/20] powerpc/powernv/npu: Fault user page into the hypervisor's pagetable Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 18/20] vfio_pci: Allow mapping extra regions Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 19/20] vfio_pci: Allow regions to add own capabilities Alexey Kardashevskiy
2018-12-13  6:17 ` [PATCH kernel v5 20/20] vfio_pci: Add NVIDIA GV100GL [Tesla V100 SXM2] subdriver Alexey Kardashevskiy
2018-12-18 22:37   ` Alex Williamson
2018-12-19  4:36     ` Alexey Kardashevskiy

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=20181213061734.16651-11-aik@ozlabs.ru \
    --to=aik@ozlabs.ru \
    --cc=alex.williamson@redhat.com \
    --cc=alistair@popple.id.au \
    --cc=arbab@linux.ibm.com \
    --cc=danielhb413@gmail.com \
    --cc=david@gibson.dropbear.id.au \
    --cc=joserz@linux.ibm.com \
    --cc=kvm-ppc@vger.kernel.org \
    --cc=lagarcia@br.ibm.com \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=pjaroszynski@nvidia.com \
    --cc=sbobroff@linux.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).