From: Leon Romanovsky leonro@nvidia.com
Some ports, such as Zhaoxin Switch Downstream Ports, redirect peer-to-peer traffic without an ACS capability, as their device-specific ACS quirks report. P2PDMA reads only ACS Control, so below such a port it hands out bus addresses for traffic that goes to the host bridge.
Take Request and Completion Redirect from a bridge's quirk too. Ignore endpoint quirks, which only describe traffic between an endpoint's own functions. Skip bridges on a root bus: they never sit between two peers, and the AMD southbridge quirk may sleep there during DMA mapping.
pci=disable_acs_redir= cannot override a quirk, so name such ports separately.
Fixes: 52916982af48 ("PCI/P2PDMA: Support peer-to-peer memory") Signed-off-by: Leon Romanovsky leonro@nvidia.com --- drivers/pci/p2pdma.c | 114 +++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 96 insertions(+), 18 deletions(-)
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 45260423dfb09..ba94b0f339285 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -21,6 +21,8 @@ #include <linux/seq_buf.h> #include <linux/xarray.h>
+#include "pci.h" + struct pci_p2pdma { struct gen_pool *pool; bool p2pmem_published; @@ -490,6 +492,44 @@ static struct pci_dev *find_parent_pci_dev(struct device *dev) return NULL; }
+/* + * Some ports send peer-to-peer traffic upstream without a standard ACS + * capability, such as Zhaoxin Root and Switch Downstream Ports. Their + * device-specific ACS quirks say so. Report whether @pdev's quirk says that + * @flag is in effect. + * + * Only ask bridges. The quirks for multi-function endpoints only say that + * their functions do not talk to each other directly, which says nothing + * about their traffic to other devices. Skip bridges on a root bus too. They + * never decide whether two peers connect directly, and for them the AMD + * southbridge quirk calls acpi_get_table(), which may sleep. DMA mapping may + * call this code where sleeping is not allowed. + */ +static bool pci_acs_p2pdma_quirk(struct pci_dev *pdev, u16 flag) +{ + if (!pci_is_bridge(pdev) || pci_is_root_bus(pdev->bus)) + return false; + + return pci_dev_specific_acs_enabled(pdev, flag) > 0; +} + +/* + * Add the Request and Completion Redirect that @pdev's quirk reports to its + * ACS Control value. Only ever add them: a quirk that covers every device of + * a vendor says "no" for the ones it does not know, and that must not hide + * their own ACS controls. What a quirk says about other controls only means + * that the control does not apply, so ignore it. + */ +static u16 pci_acs_p2pdma_quirk_redirect(struct pci_dev *pdev, u16 ctrl) +{ + if (pci_acs_p2pdma_quirk(pdev, PCI_ACS_RR)) + ctrl |= PCI_ACS_RR; + if (pci_acs_p2pdma_quirk(pdev, PCI_ACS_CR)) + ctrl |= PCI_ACS_CR; + + return ctrl; +} + /* * Check if a PCI bridge has its ACS redirection bits set to redirect P2P * TLPs upstream via ACS. Returns 1 if the packets will be redirected @@ -498,14 +538,13 @@ static struct pci_dev *find_parent_pci_dev(struct device *dev) static int pci_bridge_has_acs_redir(struct pci_dev *pdev) { int pos; - u16 ctrl; + u16 ctrl = 0;
pos = pdev->acs_cap; - if (!pos) - return 0; - - pci_read_config_word(pdev, pos + PCI_ACS_CTRL, &ctrl); + if (pos) + pci_read_config_word(pdev, pos + PCI_ACS_CTRL, &ctrl);
+ ctrl = pci_acs_p2pdma_quirk_redirect(pdev, ctrl); if (ctrl & (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC)) return 1;
@@ -520,6 +559,51 @@ static void seq_buf_print_bus_devfn(struct seq_buf *buf, struct pci_dev *pdev) seq_buf_printf(buf, "%s;", pci_name(pdev)); }
+/* + * Sort a port that redirects into @acs_list, the ports to suggest for + * pci=disable_acs_redir=, or @quirk_list. That parameter only clears the ACS + * Control register, so it cannot undo a redirect that a device quirk reports. + */ +static void pci_p2pdma_list_redir(struct seq_buf *acs_list, + struct seq_buf *quirk_list, + struct pci_dev *pdev) +{ + if (pci_acs_p2pdma_quirk(pdev, PCI_ACS_RR) || + pci_acs_p2pdma_quirk(pdev, PCI_ACS_CR)) + seq_buf_print_bus_devfn(quirk_list, pdev); + else + seq_buf_print_bus_devfn(acs_list, pdev); +} + +/* Drop the final semicolon. Returns false if no port was listed. */ +static bool pci_p2pdma_end_list(struct seq_buf *list) +{ + if (!seq_buf_used(list)) + return false; + + if (!seq_buf_has_overflowed(list)) + list->buffer[list->len - 1] = '\0'; + return true; +} + +static void pci_p2pdma_warn_redir(struct pci_dev *client, + struct pci_dev *provider, + struct seq_buf *acs_list, + struct seq_buf *quirk_list) +{ + pci_warn(client, + "ACS redirect is set between the client and provider (%s)\n", + pci_name(provider)); + if (pci_p2pdma_end_list(quirk_list)) + pci_warn(client, + "hardware redirects peer-to-peer traffic at %s, which no kernel parameter changes\n", + seq_buf_str(quirk_list)); + if (pci_p2pdma_end_list(acs_list)) + pci_warn(client, + "to disable ACS redirect for this path, add the kernel parameter: pci=disable_acs_redir=%s\n", + seq_buf_str(acs_list)); +} + static bool cpu_supports_p2pdma(void) { #ifdef CONFIG_X86 @@ -722,13 +806,14 @@ calc_map_type_and_dist(struct pci_dev *provider, struct pci_dev *client, enum pci_p2pdma_map_type map_type = PCI_P2PDMA_MAP_THRU_HOST_BRIDGE; struct pci_dev *a = provider, *b = client, *bb; struct pci_p2pdma *p2pdma; - struct seq_buf acs_list; + struct seq_buf acs_list, quirk_list; int acs_cnt = 0; int dist_a = 0; int dist_b = 0; - char buf[128]; + char buf[128], quirk_buf[64];
seq_buf_init(&acs_list, buf, sizeof(buf)); + seq_buf_init(&quirk_list, quirk_buf, sizeof(quirk_buf));
/* * Note, we don't need to take references to devices returned by @@ -739,7 +824,7 @@ calc_map_type_and_dist(struct pci_dev *provider, struct pci_dev *client, dist_b = 0;
if (pci_bridge_has_acs_redir(a)) { - seq_buf_print_bus_devfn(&acs_list, a); + pci_p2pdma_list_redir(&acs_list, &quirk_list, a); acs_cnt++; }
@@ -768,7 +853,7 @@ calc_map_type_and_dist(struct pci_dev *provider, struct pci_dev *client, break;
if (pci_bridge_has_acs_redir(bb)) { - seq_buf_print_bus_devfn(&acs_list, bb); + pci_p2pdma_list_redir(&acs_list, &quirk_list, bb); acs_cnt++; }
@@ -782,15 +867,8 @@ calc_map_type_and_dist(struct pci_dev *provider, struct pci_dev *client, goto done; }
- if (verbose) { - /* Drop the final semicolon; the list is not empty here */ - if (!seq_buf_has_overflowed(&acs_list)) - acs_list.buffer[acs_list.len - 1] = '\0'; - pci_warn(client, "ACS redirect is set between the client and provider (%s)\n", - pci_name(provider)); - pci_warn(client, "to disable ACS redirect for this path, add the kernel parameter: pci=disable_acs_redir=%s\n", - seq_buf_str(&acs_list)); - } + if (verbose) + pci_p2pdma_warn_redir(client, provider, &acs_list, &quirk_list);
map_through_host_bridge: if (!cpu_supports_p2pdma() &&