| Message ID | 20240508112658.3555882-1-vidyas@nvidia.com (mailing list archive) |
|---|---|
| State | Changes Requested |
| Headers | show |
| Series | [V1] PCI: Extend ACS configurability | expand |
On Wed, May 08, 2024 at 04:56:58PM +0530, Vidya Sagar wrote: > diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt > index 41644336e..b4a8207eb 100644 > --- a/Documentation/admin-guide/kernel-parameters.txt > +++ b/Documentation/admin-guide/kernel-parameters.txt > @@ -4456,6 +4456,28 @@ > bridges without forcing it upstream. Note: > this removes isolation between devices and > may put more devices in an IOMMU group. > + config_acs= > + Format: > + =<ACS flags>@<pci_dev>[; ...] > + Specify one or more PCI devices (in the format > + specified above) optionally prepended with flags > + and separated by semicolons. The respective > + capabilities will be enabled, disabled or unchanged > + based on what is specified in flags. > + ACS Flags is defined as follows > + bit-0 : ACS Source Validation > + bit-1 : ACS Translation Blocking > + bit-2 : ACS P2P Request Redirect > + bit-3 : ACS P2P Completion Redirect > + bit-4 : ACS Upstream Forwarding > + bit-5 : ACS P2P Egress Control > + bit-6 : ACS Direct Translated P2P > + Each bit can be marked as > + ‘0‘ – force disabled > + ‘1’ – force enabled > + ‘x’ – unchanged. It looks like 'x' doesn't fully work? Or at least it doesn't do what I'd expect - preserve the FW setting of the bit. > @@ -1005,6 +1076,7 @@ static void pci_enable_acs(struct pci_dev *dev) > * preferences. > */ > pci_disable_acs_redir(dev); > + pci_config_acs(dev); Because this sequence starts with: pci_std_enable_acs(dev); disable_acs_redir: pci_disable_acs_redir(dev); pci_config_acs(dev); And pci_std_enable_acs() has already mangled the ACS flags: ctrl |= (cap & PCI_ACS_SV); ctrl |= (cap & PCI_ACS_RR); ctrl |= (cap & PCI_ACS_CR); ctrl |= (cap & PCI_ACS_UF); if (pci_ats_disabled() || dev->external_facing || dev->untrusted) ctrl |= (cap & PCI_ACS_TB); pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl); So any FW setting on those bits is toast at this point. It would be nicer if this code was structured a bit more robustly so that it only wrote the ACS bits once after evaluating all the three sources of configuration. But I like the idea, I think this is a nice improvement. Something sort of like this perhaps: diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 94313641bc63fa..64b852ec3d613c 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -948,12 +948,20 @@ void pci_request_acs(void) static const char *disable_acs_redir_param; static const char *config_acs_param; -static void __pci_config_acs(struct pci_dev *dev, const char *p, - u16 mask, u16 flags) +struct pci_acs { + u16 cap; + u16 ctrl; + u16 fw_ctrl; +}; + +static void __pci_config_acs(struct pci_dev *dev, struct pci_acs *caps, + const char *p, u16 mask, u16 flags) { char *delimit; int ret = 0; - u16 ctrl, pos; + + if (!p) + return; while (*p) { if (!mask) { @@ -1018,98 +1026,37 @@ static void __pci_config_acs(struct pci_dev *dev, const char *p, if (!pci_dev_specific_disable_acs_redir(dev)) return; - pos = dev->acs_cap; - if (!pos) { - pci_warn(dev, "cannot configure ACS for this hardware as it does not have ACS capabilities\n"); - return; - } - pci_dbg(dev, "ACS mask = 0x%X\n", mask); pci_dbg(dev, "ACS flags = 0x%X\n", flags); - pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl); - ctrl &= ~mask; - ctrl |= flags; - pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl); + /* If mask is 0 then we copy the bit from the firmware setting. */ + caps->ctrl = (caps->ctrl & ~mask) | (caps->fw_ctrl & mask); + /* FIXME: flags doesn't check for supported? */ + caps->ctrl |= flags; - pci_info(dev, "Configured ACS\n"); + pci_info(dev, "Configured ACS to 0x%x\n", caps->ctrl); } - -/** - * pci_disable_acs_redir - disable ACS redirect capabilities - * @dev: the PCI device - * - * For only devices specified in the disable_acs_redir parameter. - */ -static void pci_disable_acs_redir(struct pci_dev *dev) -{ - const char *p; - u16 mask = 0, flags = 0; - - if (!disable_acs_redir_param) - return; - - p = disable_acs_redir_param; - - mask = PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC; - flags = ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC); - - __pci_config_acs(dev, p, mask, flags); -} - -/** - * pci_config_acs - configure ACS capabilities - * @dev: the PCI device - * - * For only devices specified in the config_acs parameter. - */ -static void pci_config_acs(struct pci_dev *dev) -{ - const char *p; - u16 mask = 0, flags = 0; - - if (!config_acs_param) - return; - - p = config_acs_param; - - __pci_config_acs(dev, p, mask, flags); -} - /** * pci_std_enable_acs - enable ACS on devices using standard ACS capabilities * @dev: the PCI device */ -static void pci_std_enable_acs(struct pci_dev *dev) +static void pci_std_enable_acs(struct pci_dev *dev, struct pci_acs *caps) { - int pos; - u16 cap; - u16 ctrl; - - pos = dev->acs_cap; - if (!pos) - return; - - pci_read_config_word(dev, pos + PCI_ACS_CAP, &cap); - pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl); - /* Source Validation */ - ctrl |= (cap & PCI_ACS_SV); + caps->ctrl |= (caps->cap & PCI_ACS_SV); /* P2P Request Redirect */ - ctrl |= (cap & PCI_ACS_RR); + caps->ctrl |= (caps->cap & PCI_ACS_RR); /* P2P Completion Redirect */ - ctrl |= (cap & PCI_ACS_CR); + caps->ctrl |= (caps->cap & PCI_ACS_CR); /* Upstream Forwarding */ - ctrl |= (cap & PCI_ACS_UF); + caps->ctrl |= (caps->cap & PCI_ACS_UF); /* Enable Translation Blocking for external devices and noats */ if (pci_ats_disabled() || dev->external_facing || dev->untrusted) - ctrl |= (cap & PCI_ACS_TB); - - pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl); + caps->ctrl |= (caps->cap & PCI_ACS_TB); } /** @@ -1118,24 +1065,33 @@ static void pci_std_enable_acs(struct pci_dev *dev) */ static void pci_enable_acs(struct pci_dev *dev) { - if (!pci_acs_enable) - goto disable_acs_redir; + struct pci_acs caps; + int pos; - if (!pci_dev_specific_enable_acs(dev)) - goto disable_acs_redir; + pos = dev->acs_cap; + if (!pos) + return; - pci_std_enable_acs(dev); + pci_read_config_word(dev, pos + PCI_ACS_CAP, &caps.cap); + pci_read_config_word(dev, pos + PCI_ACS_CTRL, &caps.ctrl); + caps.fw_ctrl = caps.ctrl; + + /* If an iommu is present we start with kernel default caps */ + if (pci_acs_enable) { + if (pci_dev_specific_enable_acs(dev)) + pci_std_enable_acs(dev, &caps); + } -disable_acs_redir: /* - * Note: pci_disable_acs_redir() must be called even if ACS was not - * enabled by the kernel because it may have been enabled by - * platform firmware. So if we are told to disable it, we should - * always disable it after setting the kernel's default - * preferences. + * Always apply caps from the command line, even if there is no iommu. + * Trust that the admin has a reason to change the ACS settings. */ - pci_disable_acs_redir(dev); - pci_config_acs(dev); + __pci_config_acs(dev, &caps, disable_acs_redir_param, + PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC, + ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC)); + __pci_config_acs(dev, &caps, config_acs_param, 0, 0); + + pci_write_config_word(dev, pos + PCI_ACS_CTRL, caps.ctrl); } /**
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 41644336e..b4a8207eb 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4456,6 +4456,28 @@ bridges without forcing it upstream. Note: this removes isolation between devices and may put more devices in an IOMMU group. + config_acs= + Format: + =<ACS flags>@<pci_dev>[; ...] + Specify one or more PCI devices (in the format + specified above) optionally prepended with flags + and separated by semicolons. The respective + capabilities will be enabled, disabled or unchanged + based on what is specified in flags. + ACS Flags is defined as follows + bit-0 : ACS Source Validation + bit-1 : ACS Translation Blocking + bit-2 : ACS P2P Request Redirect + bit-3 : ACS P2P Completion Redirect + bit-4 : ACS Upstream Forwarding + bit-5 : ACS P2P Egress Control + bit-6 : ACS Direct Translated P2P + Each bit can be marked as + ‘0‘ – force disabled + ‘1’ – force enabled + ‘x’ – unchanged. + Note: this may remove isolation between devices + and may put more devices in an IOMMU group. force_floating [S390] Force usage of floating interrupts. nomio [S390] Do not use MIO instructions. norid [S390] ignore the RID field and force use of diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index a607f277c..0ad48ade9 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -887,30 +887,59 @@ void pci_request_acs(void) } static const char *disable_acs_redir_param; +static const char *config_acs_param; -/** - * pci_disable_acs_redir - disable ACS redirect capabilities - * @dev: the PCI device - * - * For only devices specified in the disable_acs_redir parameter. - */ -static void pci_disable_acs_redir(struct pci_dev *dev) +static void __pci_config_acs(struct pci_dev *dev, const char *p, + u16 mask, u16 flags) { + char *delimit; int ret = 0; - const char *p; - int pos; - u16 ctrl; + u16 ctrl, pos; - if (!disable_acs_redir_param) - return; - - p = disable_acs_redir_param; while (*p) { + if (!mask) { + /* Check for ACS flags */ + delimit = strstr(p, "@"); + if (delimit) { + int end; + u32 shift = 0; + + end = delimit - p - 1; + + while (end > -1) { + if (*(p + end) == '0') { + mask |= 1 << shift; + shift++; + end--; + } else if (*(p + end) == '1') { + mask |= 1 << shift; + flags |= 1 << shift; + shift++; + end--; + } else if ((*(p + end) == 'x') || (*(p + end) == 'X')) { + shift++; + end--; + } else { + pci_err(dev, "Invalid ACS flags... Ignoring\n"); + return; + } + } + p = delimit + 1; + } else { + pci_err(dev, "ACS Flags missing\n"); + return; + } + } + + if (mask & ~(PCI_ACS_SV | PCI_ACS_TB | PCI_ACS_RR | PCI_ACS_CR | + PCI_ACS_UF | PCI_ACS_EC | PCI_ACS_DT)) { + pci_err(dev, "Invalid ACS flags specified\n"); + return; + } + ret = pci_dev_str_match(dev, p, &p); if (ret < 0) { - pr_info_once("PCI: Can't parse disable_acs_redir parameter: %s\n", - disable_acs_redir_param); - + pr_info_once("PCI: Can't parse acs command line parameter\n"); break; } else if (ret == 1) { /* Found a match */ @@ -932,18 +961,60 @@ static void pci_disable_acs_redir(struct pci_dev *dev) pos = dev->acs_cap; if (!pos) { - pci_warn(dev, "cannot disable ACS redirect for this hardware as it does not have ACS capabilities\n"); + pci_warn(dev, "cannot configure ACS for this hardware as it does not have ACS capabilities\n"); return; } + pci_dbg(dev, "ACS mask = 0x%X\n", mask); + pci_dbg(dev, "ACS flags = 0x%X\n", flags); + pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl); + ctrl &= ~mask; + ctrl |= flags; + pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl); - /* P2P Request & Completion Redirect */ - ctrl &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC); + pci_info(dev, "Configured ACS\n"); +} - pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl); +/** + * pci_disable_acs_redir - disable ACS redirect capabilities + * @dev: the PCI device + * + * For only devices specified in the disable_acs_redir parameter. + */ +static void pci_disable_acs_redir(struct pci_dev *dev) +{ + const char *p; + u16 mask = 0, flags = 0; + + if (!disable_acs_redir_param) + return; + + p = disable_acs_redir_param; + + mask = PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC; + flags = ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC); + + __pci_config_acs(dev, p, mask, flags); +} + +/** + * pci_config_acs - configure ACS capabilities + * @dev: the PCI device + * + * For only devices specified in the config_acs parameter. + */ +static void pci_config_acs(struct pci_dev *dev) +{ + const char *p; + u16 mask = 0, flags = 0; + + if (!config_acs_param) + return; + + p = config_acs_param; - pci_info(dev, "disabled ACS redirect\n"); + __pci_config_acs(dev, p, mask, flags); } /** @@ -1005,6 +1076,7 @@ static void pci_enable_acs(struct pci_dev *dev) * preferences. */ pci_disable_acs_redir(dev); + pci_config_acs(dev); } /** @@ -7023,6 +7095,8 @@ static int __init pci_setup(char *str) pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS); } else if (!strncmp(str, "disable_acs_redir=", 18)) { disable_acs_redir_param = str + 18; + } else if (!strncmp(str, "config_acs=", 11)) { + config_acs_param = str + 11; } else { pr_err("PCI: Unknown option `%s'\n", str); } @@ -7047,6 +7121,7 @@ static int __init pci_realloc_setup_params(void) resource_alignment_param = kstrdup(resource_alignment_param, GFP_KERNEL); disable_acs_redir_param = kstrdup(disable_acs_redir_param, GFP_KERNEL); + config_acs_param = kstrdup(config_acs_param, GFP_KERNEL); return 0; }
For iommu_groups to form correctly, the ACS settings in the PCIe fabric need to be setup early in the boot process, either via the BIOS or via the kernel disable_acs_redir parameter. disable_acs_redir allows clearing the RR|CR|EC ACS flags, but the PCIe spec Rev3.0 already defines 7 different ACS related flags with many more useful combinations depending on the fabric design. For backward compatibility, leave the 'disable_acs_redir' as is and add a new parameter 'config_acs'so that the user can directly specify the ACS flags to set on a per-device basis. Use a similar syntax to the existing 'resource_alignment' parameter by using the @ character and have the user specify the ACS flags using a bit encoding. If both 'disable_acs_redir' and 'config_acs' are specified for a particular device, configuration specified through 'config_acs' takes precedence over the other. Signed-off-by: Vidya Sagar <vidyas@nvidia.com> --- .../admin-guide/kernel-parameters.txt | 22 ++++ drivers/pci/pci.c | 119 ++++++++++++++---- 2 files changed, 119 insertions(+), 22 deletions(-)