From c3df83e01a96ca569d261bcdffa2fb858b1012fa Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Tue, 28 Jun 2022 16:30:56 +0200 Subject: PCI: Clean up pci_scan_slot() While determining the next PCI function is factored out of pci_scan_slot() into next_fn(), the former still handles the first function as a special case, which duplicates the code from the scan loop. Furthermore the non-ARI branch of next_fn() is generally hard to understand and especially the check for multifunction devices is hidden in the handling of NULL devices for non-contiguous multifunction. It also signals that no further functions need to be scanned by returning 0 via wraparound and this is a valid function number. Improve upon this by transforming the conditions in next_fn() to be easier to understand. By changing next_fn() to return -ENODEV instead of 0 when there is no next function we can then handle the initial function inside the loop and deduplicate the shared handling. This also makes it more explicit that only function 0 must exist. No functional change is intended. Link: https://lore.kernel.org/r/20220628143100.3228092-2-schnelle@linux.ibm.com Signed-off-by: Niklas Schnelle Signed-off-by: Bjorn Helgaas Cc: Jan Kiszka --- drivers/pci/probe.c | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 17a969942d37..b05d0ed83a24 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2579,8 +2579,7 @@ struct pci_dev *pci_scan_single_device(struct pci_bus *bus, int devfn) } EXPORT_SYMBOL(pci_scan_single_device); -static unsigned int next_fn(struct pci_bus *bus, struct pci_dev *dev, - unsigned int fn) +static int next_fn(struct pci_bus *bus, struct pci_dev *dev, int fn) { int pos; u16 cap = 0; @@ -2588,24 +2587,26 @@ static unsigned int next_fn(struct pci_bus *bus, struct pci_dev *dev, if (pci_ari_enabled(bus)) { if (!dev) - return 0; + return -ENODEV; pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ARI); if (!pos) - return 0; + return -ENODEV; pci_read_config_word(dev, pos + PCI_ARI_CAP, &cap); next_fn = PCI_ARI_CAP_NFN(cap); if (next_fn <= fn) - return 0; /* protect against malformed list */ + return -ENODEV; /* protect against malformed list */ return next_fn; } - /* dev may be NULL for non-contiguous multifunction devices */ - if (!dev || dev->multifunction) - return (fn + 1) % 8; + if (fn >= 7) + return -ENODEV; + /* only multifunction devices may have more functions */ + if (dev && !dev->multifunction) + return -ENODEV; - return 0; + return fn + 1; } static int only_one_child(struct pci_bus *bus) @@ -2643,26 +2644,25 @@ static int only_one_child(struct pci_bus *bus) */ int pci_scan_slot(struct pci_bus *bus, int devfn) { - unsigned int fn, nr = 0; struct pci_dev *dev; + int fn = 0, nr = 0; if (only_one_child(bus) && (devfn > 0)) return 0; /* Already scanned the entire slot */ - dev = pci_scan_single_device(bus, devfn); - if (!dev) - return 0; - if (!pci_dev_is_added(dev)) - nr++; - - for (fn = next_fn(bus, dev, 0); fn > 0; fn = next_fn(bus, dev, fn)) { + do { dev = pci_scan_single_device(bus, devfn + fn); if (dev) { if (!pci_dev_is_added(dev)) nr++; - dev->multifunction = 1; + if (fn > 0) + dev->multifunction = 1; + } else if (fn == 0) { + /* function 0 is required */ + break; } - } + fn = next_fn(bus, dev, fn); + } while (fn >= 0); /* Only one slot has PCIe device */ if (bus->self && nr) -- cgit From fbed59ed8781d7eecd7f45cde0188cf24eeb5c38 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Tue, 28 Jun 2022 16:30:57 +0200 Subject: PCI: Split out next_ari_fn() from next_fn() In commit b1bd58e448f2 ("PCI: Consolidate "next-function" functions") the next_fn() function subsumed the traditional and ARI-based next function determination. This got rid of some needlessly complex function pointer handling but also reduced the separation between these very different methods of finding the next function. With the next_fn() cleaned up a bit we can re-introduce this separation by moving out the ARI handling while sticking with direct function calls. Link: https://lore.kernel.org/r/20220628143100.3228092-3-schnelle@linux.ibm.com Signed-off-by: Niklas Schnelle Signed-off-by: Bjorn Helgaas Reviewed-by: Pierre Morel --- drivers/pci/probe.c | 31 ++++++++++++++++++------------- 1 file changed, 18 insertions(+), 13 deletions(-) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index b05d0ed83a24..d62885519df3 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2579,26 +2579,31 @@ struct pci_dev *pci_scan_single_device(struct pci_bus *bus, int devfn) } EXPORT_SYMBOL(pci_scan_single_device); -static int next_fn(struct pci_bus *bus, struct pci_dev *dev, int fn) +static int next_ari_fn(struct pci_bus *bus, struct pci_dev *dev, int fn) { int pos; u16 cap = 0; unsigned int next_fn; - if (pci_ari_enabled(bus)) { - if (!dev) - return -ENODEV; - pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ARI); - if (!pos) - return -ENODEV; + if (!dev) + return -ENODEV; - pci_read_config_word(dev, pos + PCI_ARI_CAP, &cap); - next_fn = PCI_ARI_CAP_NFN(cap); - if (next_fn <= fn) - return -ENODEV; /* protect against malformed list */ + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ARI); + if (!pos) + return -ENODEV; - return next_fn; - } + pci_read_config_word(dev, pos + PCI_ARI_CAP, &cap); + next_fn = PCI_ARI_CAP_NFN(cap); + if (next_fn <= fn) + return -ENODEV; /* protect against malformed list */ + + return next_fn; +} + +static int next_fn(struct pci_bus *bus, struct pci_dev *dev, int fn) +{ + if (pci_ari_enabled(bus)) + return next_ari_fn(bus, dev, fn); if (fn >= 7) return -ENODEV; -- cgit From db360b1ea7faef290471bc1b2a7463b96fd20a07 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Tue, 28 Jun 2022 16:30:58 +0200 Subject: PCI: Move jailhouse's isolated function handling to pci_scan_slot() The special case of the jailhouse hypervisor passing through individual PCI functions handles scanning for PCI functions even if function 0 does not exist. Previously this was done with an extra loop duplicating the one in pci_scan_slot(). By incorporating the check for jailhouse_paravirt() into pci_scan_slot() we can instead do this as part of the normal slot scan. Note that with the assignment of dev->multifunction gated by fn > 0 we set dev->multifunction unconditionally for all functions if function 0 is missing just as in the existing jailhouse loop. The only functional change is that we now call pcie_aspm_init_link_state() for these functions, but this already happened if function 0 was passed through and should not be a problem. Link: https://lore.kernel.org/linux-pci/20220408224514.GA353445@bhelgaas/ Suggested-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20220628143100.3228092-4-schnelle@linux.ibm.com Signed-off-by: Niklas Schnelle Signed-off-by: Bjorn Helgaas Reviewed-by: Pierre Morel Cc: Jan Kiszka --- drivers/pci/probe.c | 30 ++++++++++-------------------- 1 file changed, 10 insertions(+), 20 deletions(-) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index d62885519df3..1f91ed67b5c5 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2663,8 +2663,13 @@ int pci_scan_slot(struct pci_bus *bus, int devfn) if (fn > 0) dev->multifunction = 1; } else if (fn == 0) { - /* function 0 is required */ - break; + /* + * Function 0 is required unless we are running on + * a hypervisor that passes through individual PCI + * functions. + */ + if (!jailhouse_paravirt()) + break; } fn = next_fn(bus, dev, fn); } while (fn >= 0); @@ -2863,29 +2868,14 @@ static unsigned int pci_scan_child_bus_extend(struct pci_bus *bus, { unsigned int used_buses, normal_bridges = 0, hotplug_bridges = 0; unsigned int start = bus->busn_res.start; - unsigned int devfn, fn, cmax, max = start; + unsigned int devfn, cmax, max = start; struct pci_dev *dev; - int nr_devs; dev_dbg(&bus->dev, "scanning bus\n"); /* Go find them, Rover! */ - for (devfn = 0; devfn < 256; devfn += 8) { - nr_devs = pci_scan_slot(bus, devfn); - - /* - * The Jailhouse hypervisor may pass individual functions of a - * multi-function device to a guest without passing function 0. - * Look for them as well. - */ - if (jailhouse_paravirt() && nr_devs == 0) { - for (fn = 1; fn < 8; fn++) { - dev = pci_scan_single_device(bus, devfn + fn); - if (dev) - dev->multifunction = 1; - } - } - } + for (devfn = 0; devfn < 256; devfn += 8) + pci_scan_slot(bus, devfn); /* Reserve buses for SR-IOV capability */ used_buses = pci_iov_bus_range(bus); -- cgit From 189c6c33ff421def040b904fb14ef76c5bf5af4c Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Tue, 28 Jun 2022 16:30:59 +0200 Subject: PCI: Extend isolated function probing to s390 Like the jailhouse hypervisor, s390's PCI architecture allows passing isolated PCI functions to a guest OS instance. As of now this is was not utilized even with multi-function support as the s390 PCI code makes sure that only virtual PCI busses including a function with devfn 0 are presented to the PCI subsystem. A subsequent change will remove this restriction. Allow probing such functions by replacing the existing check for jailhouse_paravirt() with a new hypervisor_isolated_pci_functions() helper. Link: https://lore.kernel.org/r/20220628143100.3228092-5-schnelle@linux.ibm.com Signed-off-by: Niklas Schnelle Signed-off-by: Bjorn Helgaas Reviewed-by: Pierre Morel Cc: Jan Kiszka --- drivers/pci/probe.c | 2 +- include/linux/hypervisor.h | 8 ++++++++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 1f91ed67b5c5..4948531481d1 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2668,7 +2668,7 @@ int pci_scan_slot(struct pci_bus *bus, int devfn) * a hypervisor that passes through individual PCI * functions. */ - if (!jailhouse_paravirt()) + if (!hypervisor_isolated_pci_functions()) break; } fn = next_fn(bus, dev, fn); diff --git a/include/linux/hypervisor.h b/include/linux/hypervisor.h index fc08b433c856..9efbc54e35e5 100644 --- a/include/linux/hypervisor.h +++ b/include/linux/hypervisor.h @@ -32,4 +32,12 @@ static inline bool jailhouse_paravirt(void) #endif /* !CONFIG_X86 */ +static inline bool hypervisor_isolated_pci_functions(void) +{ + if (IS_ENABLED(CONFIG_S390)) + return true; + + return jailhouse_paravirt(); +} + #endif /* __LINUX_HYPEVISOR_H */ -- cgit From 960ac362648780469b2f5584bb8cff540444d119 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Tue, 28 Jun 2022 16:31:00 +0200 Subject: s390/pci: allow zPCI zbus without a function zero Currently the zPCI code blocks PCI bus creation and probing of a zPCI zbus unless there is a PCI function with devfn 0. This is always the case for the PCI functions with hidden RID, but may keep PCI functions from a multi-function PCI device with RID information invisible until the function 0 becomes visible. Worse, as a PCI bus is necessary to even present a PCI hotplug slot, even that remains invisible. With the probing of these so-called isolated PCI functions enabled for s390 in common code, this restriction is no longer necessary. On network cards with multiple ports and a PF per port this also allows using each port on its own while still providing the physical PCI topology information in the devfn needed to associate VFs with their parent PF. Link: https://lore.kernel.org/r/20220628143100.3228092-6-schnelle@linux.ibm.com Signed-off-by: Niklas Schnelle Signed-off-by: Bjorn Helgaas Reviewed-by: Pierre Morel --- arch/s390/pci/pci_bus.c | 82 ++++++++++++------------------------------------- 1 file changed, 20 insertions(+), 62 deletions(-) diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 5d77acbd1c87..6a8da1b742ae 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -145,9 +145,6 @@ int zpci_bus_scan_bus(struct zpci_bus *zbus) struct zpci_dev *zdev; int devfn, rc, ret = 0; - if (!zbus->function[0]) - return 0; - for (devfn = 0; devfn < ZPCI_FUNCTIONS_PER_BUS; devfn++) { zdev = zbus->function[devfn]; if (zdev && zdev->state == ZPCI_FN_STATE_CONFIGURED) { @@ -184,26 +181,26 @@ void zpci_bus_scan_busses(void) /* zpci_bus_create_pci_bus - Create the PCI bus associated with this zbus * @zbus: the zbus holding the zdevices - * @f0: function 0 of the bus + * @fr: PCI root function that will determine the bus's domain, and bus speeed * @ops: the pci operations * - * Function zero is taken as a parameter as this is used to determine the - * domain, multifunction property and maximum bus speed of the entire bus. + * The PCI function @fr determines the domain (its UID), multifunction property + * and maximum bus speed of the entire bus. * * Return: 0 on success, an error code otherwise */ -static int zpci_bus_create_pci_bus(struct zpci_bus *zbus, struct zpci_dev *f0, struct pci_ops *ops) +static int zpci_bus_create_pci_bus(struct zpci_bus *zbus, struct zpci_dev *fr, struct pci_ops *ops) { struct pci_bus *bus; int domain; - domain = zpci_alloc_domain((u16)f0->uid); + domain = zpci_alloc_domain((u16)fr->uid); if (domain < 0) return domain; zbus->domain_nr = domain; - zbus->multifunction = f0->rid_available; - zbus->max_bus_speed = f0->max_bus_speed; + zbus->multifunction = fr->rid_available; + zbus->max_bus_speed = fr->max_bus_speed; /* * Note that the zbus->resources are taken over and zbus->resources @@ -303,47 +300,6 @@ void pcibios_bus_add_device(struct pci_dev *pdev) } } -/* zpci_bus_create_hotplug_slots - Add hotplug slot(s) for device added to bus - * @zdev: the zPCI device that was newly added - * - * Add the hotplug slot(s) for the newly added PCI function. Normally this is - * simply the slot for the function itself. If however we are adding the - * function 0 on a zbus, it might be that we already registered functions on - * that zbus but could not create their hotplug slots yet so add those now too. - * - * Return: 0 on success, an error code otherwise - */ -static int zpci_bus_create_hotplug_slots(struct zpci_dev *zdev) -{ - struct zpci_bus *zbus = zdev->zbus; - int devfn, rc = 0; - - rc = zpci_init_slot(zdev); - if (rc) - return rc; - zdev->has_hp_slot = 1; - - if (zdev->devfn == 0 && zbus->multifunction) { - /* Now that function 0 is there we can finally create the - * hotplug slots for those functions with devfn != 0 that have - * been parked in zbus->function[] waiting for us to be able to - * create the PCI bus. - */ - for (devfn = 1; devfn < ZPCI_FUNCTIONS_PER_BUS; devfn++) { - zdev = zbus->function[devfn]; - if (zdev && !zdev->has_hp_slot) { - rc = zpci_init_slot(zdev); - if (rc) - return rc; - zdev->has_hp_slot = 1; - } - } - - } - - return rc; -} - static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) { int rc = -EINVAL; @@ -352,21 +308,19 @@ static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) pr_err("devfn %04x is already assigned\n", zdev->devfn); return rc; } + zdev->zbus = zbus; zbus->function[zdev->devfn] = zdev; zpci_nb_devices++; - if (zbus->bus) { - if (zbus->multifunction && !zdev->rid_available) { - WARN_ONCE(1, "rid_available not set for multifunction\n"); - goto error; - } - - zpci_bus_create_hotplug_slots(zdev); - } else { - /* Hotplug slot will be created once function 0 appears */ - zbus->multifunction = 1; + if (zbus->multifunction && !zdev->rid_available) { + WARN_ONCE(1, "rid_available not set for multifunction\n"); + goto error; } + rc = zpci_init_slot(zdev); + if (rc) + goto error; + zdev->has_hp_slot = 1; return 0; @@ -400,7 +354,11 @@ int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops) return -ENOMEM; } - if (zdev->devfn == 0) { + if (!zbus->bus) { + /* The UID of the first PCI function registered with a zpci_bus + * is used as the domain number for that bus. Currently there + * is exactly one zpci_bus per domain. + */ rc = zpci_bus_create_pci_bus(zbus, zdev, ops); if (rc) goto error; -- cgit