From d1c29465b8a52d8fc5a59aac92c6b206b69fe631 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Feb 2015 15:15:10 +1030 Subject: lguest: don't disable iospace. This no longer speeds up boot (IDE got better, I guess), but it does stop us probing for a PCI bus. Signed-off-by: Rusty Russell --- arch/x86/lguest/boot.c | 8 -------- 1 file changed, 8 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index c1c1544..47ec7f2 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1400,14 +1400,6 @@ __init void lguest_init(void) atomic_notifier_chain_register(&panic_notifier_list, &paniced); /* - * The IDE code spends about 3 seconds probing for disks: if we reserve - * all the I/O ports up front it can't get them and so doesn't probe. - * Other device drivers are similar (but less severe). This cuts the - * kernel boot time on my machine from 4.1 seconds to 0.45 seconds. - */ - paravirt_disable_iospace(); - - /* * This is messy CPU setup stuff which the native boot code does before * start_kernel, so we have to do, too: */ -- cgit v1.1 From ee72576c143d8e9081ae1fe8644122454dd323c5 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Feb 2015 15:15:10 +1030 Subject: lguest: disable ACPI explicitly. Once we add PCI, it starts trying to manage our interrupts. Signed-off-by: Rusty Russell --- arch/x86/lguest/boot.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 47ec7f2..aa6e3b4 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -56,6 +56,7 @@ #include #include #include +#include #include #include #include @@ -1428,6 +1429,9 @@ __init void lguest_init(void) /* Register our very early console. */ virtio_cons_early_init(early_put_chars); + /* Don't let ACPI try to control our PCI interrupts. */ + disable_acpi(); + /* * Last of all, we set the power management poweroff hook to point to * the Guest routine to power off, and the reboot hook to our restart -- cgit v1.1 From e1b83e27881cf3153ce420aea853797fed29a9ea Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Feb 2015 15:15:10 +1030 Subject: lguest: Override pcibios_enable_irq/pcibios_disable_irq to our stupid PIC This lets us deliver interrupts for our emulated PCI devices using our dumb PIC, and not emulate an 8259 and PCI irq mapping tables or whatever. Signed-off-by: Rusty Russell --- arch/x86/lguest/boot.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index aa6e3b4..2943ab9 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -56,6 +56,7 @@ #include #include #include +#include #include #include #include @@ -72,6 +73,7 @@ #include #include /* for struct machine_ops */ #include +#include /*G:010 * Welcome to the Guest! @@ -832,6 +834,24 @@ static struct irq_chip lguest_irq_controller = { .irq_unmask = enable_lguest_irq, }; +static int lguest_enable_irq(struct pci_dev *dev) +{ + u8 line = 0; + + /* We literally use the PCI interrupt line as the irq number. */ + pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &line); + irq_set_chip_and_handler_name(line, &lguest_irq_controller, + handle_level_irq, "level"); + dev->irq = line; + return 0; +} + +/* We don't do hotplug PCI, so this shouldn't be called. */ +static void lguest_disable_irq(struct pci_dev *dev) +{ + WARN_ON(1); +} + /* * This sets up the Interrupt Descriptor Table (IDT) entry for each hardware * interrupt (except 128, which is used for system calls), and then tells the @@ -1432,6 +1452,10 @@ __init void lguest_init(void) /* Don't let ACPI try to control our PCI interrupts. */ disable_acpi(); + /* We control them ourselves, by overriding these two hooks. */ + pcibios_enable_irq = lguest_enable_irq; + pcibios_disable_irq = lguest_disable_irq; + /* * Last of all, we set the power management poweroff hook to point to * the Guest routine to power off, and the reboot hook to our restart -- cgit v1.1 From a561adfaecc9eb6fb66941b450458801f3f60ca0 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Feb 2015 15:26:01 +1030 Subject: lguest: use the PCI console device's emerg_wr for early boot messages. This involves manually checking the console device (which is always in slot 1 of bus 0) and using the window in VIRTIO_PCI_CAP_PCI_CFG to program it (as we can't map the BAR yet). We could in fact do this much earlier, but we wait for the first write from the virtio_cons_early_init() facility. Signed-off-by: Rusty Russell --- arch/x86/lguest/boot.c | 146 +++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 134 insertions(+), 12 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 2943ab9..531b844 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -57,6 +57,7 @@ #include #include #include +#include #include #include #include @@ -74,6 +75,7 @@ #include /* for struct machine_ops */ #include #include +#include /*G:010 * Welcome to the Guest! @@ -1202,25 +1204,145 @@ static __init char *lguest_memory_setup(void) return "LGUEST"; } +/* Offset within PCI config space of BAR access capability. */ +static int console_cfg_offset = 0; +static int console_access_cap; + +/* Set up so that we access off in bar0 (on bus 0, device 1, function 0) */ +static void set_cfg_window(u32 cfg_offset, u32 off) +{ + write_pci_config_byte(0, 1, 0, + cfg_offset + offsetof(struct virtio_pci_cap, bar), + 0); + write_pci_config(0, 1, 0, + cfg_offset + offsetof(struct virtio_pci_cap, length), + 4); + write_pci_config(0, 1, 0, + cfg_offset + offsetof(struct virtio_pci_cap, offset), + off); +} + +static u32 read_bar_via_cfg(u32 cfg_offset, u32 off) +{ + set_cfg_window(cfg_offset, off); + return read_pci_config(0, 1, 0, + cfg_offset + sizeof(struct virtio_pci_cap)); +} + +static void write_bar_via_cfg(u32 cfg_offset, u32 off, u32 val) +{ + set_cfg_window(cfg_offset, off); + write_pci_config(0, 1, 0, + cfg_offset + sizeof(struct virtio_pci_cap), val); +} + +static void probe_pci_console(void) +{ + u8 cap, common_cap = 0, device_cap = 0; + /* Offsets within BAR0 */ + u32 common_offset, device_offset; + + /* Avoid recursive printk into here. */ + console_cfg_offset = -1; + + if (!early_pci_allowed()) { + printk(KERN_ERR "lguest: early PCI access not allowed!\n"); + return; + } + + /* We expect a console PCI device at BUS0, slot 1. */ + if (read_pci_config(0, 1, 0, 0) != 0x10431AF4) { + printk(KERN_ERR "lguest: PCI device is %#x!\n", + read_pci_config(0, 1, 0, 0)); + return; + } + + /* Find the capabilities we need (must be in bar0) */ + cap = read_pci_config_byte(0, 1, 0, PCI_CAPABILITY_LIST); + while (cap) { + u8 vndr = read_pci_config_byte(0, 1, 0, cap); + if (vndr == PCI_CAP_ID_VNDR) { + u8 type, bar; + u32 offset; + + type = read_pci_config_byte(0, 1, 0, + cap + offsetof(struct virtio_pci_cap, cfg_type)); + bar = read_pci_config_byte(0, 1, 0, + cap + offsetof(struct virtio_pci_cap, bar)); + offset = read_pci_config(0, 1, 0, + cap + offsetof(struct virtio_pci_cap, offset)); + + switch (type) { + case VIRTIO_PCI_CAP_COMMON_CFG: + if (bar == 0) { + common_cap = cap; + common_offset = offset; + } + break; + case VIRTIO_PCI_CAP_DEVICE_CFG: + if (bar == 0) { + device_cap = cap; + device_offset = offset; + } + break; + case VIRTIO_PCI_CAP_PCI_CFG: + console_access_cap = cap; + break; + } + } + cap = read_pci_config_byte(0, 1, 0, cap + PCI_CAP_LIST_NEXT); + } + if (!common_cap || !device_cap || !console_access_cap) { + printk(KERN_ERR "lguest: No caps (%u/%u/%u) in console!\n", + common_cap, device_cap, console_access_cap); + return; + } + + +#define write_common_config(reg, val) \ + write_bar_via_cfg(console_access_cap, \ + common_offset+offsetof(struct virtio_pci_common_cfg,reg),\ + val) + +#define read_common_config(reg) \ + read_bar_via_cfg(console_access_cap, \ + common_offset+offsetof(struct virtio_pci_common_cfg,reg)) + + /* Check features: they must offer EMERG_WRITE */ + write_common_config(device_feature_select, 0); + + if (!(read_common_config(device_feature) + & (1 << VIRTIO_CONSOLE_F_EMERG_WRITE))) { + printk(KERN_ERR "lguest: console missing EMERG_WRITE\n"); + return; + } + + console_cfg_offset = device_offset; +} + /* * We will eventually use the virtio console device to produce console output, - * but before that is set up we use LHCALL_NOTIFY on normal memory to produce - * console output. + * but before that is set up we use the virtio PCI console's backdoor mmio + * access and the "emergency" write facility (which is legal even before the + * device is configured). */ static __init int early_put_chars(u32 vtermno, const char *buf, int count) { - char scratch[17]; - unsigned int len = count; + /* If we couldn't find PCI console, forget it. */ + if (console_cfg_offset < 0) + return count; - /* We use a nul-terminated string, so we make a copy. Icky, huh? */ - if (len > sizeof(scratch) - 1) - len = sizeof(scratch) - 1; - scratch[len] = '\0'; - memcpy(scratch, buf, len); - hcall(LHCALL_NOTIFY, __pa(scratch), 0, 0, 0); + if (unlikely(!console_cfg_offset)) { + probe_pci_console(); + if (console_cfg_offset < 0) + return count; + } - /* This routine returns the number of bytes actually written. */ - return len; + write_bar_via_cfg(console_access_cap, + console_cfg_offset + + offsetof(struct virtio_console_config, emerg_wr), + buf[0]); + return 1; } /* -- cgit v1.1 From d9bab50aa46ce46dd4537d455eb13b200cdac516 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Feb 2015 15:28:01 +1030 Subject: lguest: remove NOTIFY call and eventfd facility. Disappointing, as this was kind of neat (especially getting to use RCU to manage the address -> eventfd mapping). But now the devices are PCI handled in userspace, we get rid of both the NOTIFY hypercall and the interface to connect an eventfd. Signed-off-by: Rusty Russell --- arch/x86/include/asm/lguest_hcall.h | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h index 879fd7d..ef01fef 100644 --- a/arch/x86/include/asm/lguest_hcall.h +++ b/arch/x86/include/asm/lguest_hcall.h @@ -16,7 +16,6 @@ #define LHCALL_SET_PTE 14 #define LHCALL_SET_PGD 15 #define LHCALL_LOAD_TLS 16 -#define LHCALL_NOTIFY 17 #define LHCALL_LOAD_GDT_ENTRY 18 #define LHCALL_SEND_INTERRUPTS 19 -- cgit v1.1 From 55c2d7884e9a97c2f2d46d5818f783bf3dcc5314 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 13 Feb 2015 17:13:43 +1030 Subject: lguest: don't look in console features to find emerg_wr. The 1.0 spec clearly states that you must set the ACKNOWLEDGE and DRIVER status bits before accessing the feature bits. This is a problem for the early console code, which doesn't really want to acknowledge the device (the spec specifically excepts writing to the console's emerg_wr from the usual ordering constrains). Instead, we check that the *size* of the device configuration is sufficient to hold emerg_wr: at worst (if the device doesn't support the VIRTIO_CONSOLE_F_EMERG_WRITE feature), it will ignore the writes. Signed-off-by: Rusty Russell --- arch/x86/lguest/boot.c | 57 +++++++++++++++++++++----------------------------- 1 file changed, 24 insertions(+), 33 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 531b844..ac4453d 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1222,15 +1222,13 @@ static void set_cfg_window(u32 cfg_offset, u32 off) off); } -static u32 read_bar_via_cfg(u32 cfg_offset, u32 off) -{ - set_cfg_window(cfg_offset, off); - return read_pci_config(0, 1, 0, - cfg_offset + sizeof(struct virtio_pci_cap)); -} - static void write_bar_via_cfg(u32 cfg_offset, u32 off, u32 val) { + /* + * We could set this up once, then leave it; nothing else in the * + * kernel should touch these registers. But if it went wrong, that + * would be a horrible bug to find. + */ set_cfg_window(cfg_offset, off); write_pci_config(0, 1, 0, cfg_offset + sizeof(struct virtio_pci_cap), val); @@ -1239,8 +1237,9 @@ static void write_bar_via_cfg(u32 cfg_offset, u32 off, u32 val) static void probe_pci_console(void) { u8 cap, common_cap = 0, device_cap = 0; - /* Offsets within BAR0 */ - u32 common_offset, device_offset; + /* Offset within BAR0 */ + u32 device_offset; + u32 device_len; /* Avoid recursive printk into here. */ console_cfg_offset = -1; @@ -1263,7 +1262,7 @@ static void probe_pci_console(void) u8 vndr = read_pci_config_byte(0, 1, 0, cap); if (vndr == PCI_CAP_ID_VNDR) { u8 type, bar; - u32 offset; + u32 offset, length; type = read_pci_config_byte(0, 1, 0, cap + offsetof(struct virtio_pci_cap, cfg_type)); @@ -1271,18 +1270,15 @@ static void probe_pci_console(void) cap + offsetof(struct virtio_pci_cap, bar)); offset = read_pci_config(0, 1, 0, cap + offsetof(struct virtio_pci_cap, offset)); + length = read_pci_config(0, 1, 0, + cap + offsetof(struct virtio_pci_cap, length)); switch (type) { - case VIRTIO_PCI_CAP_COMMON_CFG: - if (bar == 0) { - common_cap = cap; - common_offset = offset; - } - break; case VIRTIO_PCI_CAP_DEVICE_CFG: if (bar == 0) { device_cap = cap; device_offset = offset; + device_len = length; } break; case VIRTIO_PCI_CAP_PCI_CFG: @@ -1292,32 +1288,27 @@ static void probe_pci_console(void) } cap = read_pci_config_byte(0, 1, 0, cap + PCI_CAP_LIST_NEXT); } - if (!common_cap || !device_cap || !console_access_cap) { + if (!device_cap || !console_access_cap) { printk(KERN_ERR "lguest: No caps (%u/%u/%u) in console!\n", common_cap, device_cap, console_access_cap); return; } - -#define write_common_config(reg, val) \ - write_bar_via_cfg(console_access_cap, \ - common_offset+offsetof(struct virtio_pci_common_cfg,reg),\ - val) - -#define read_common_config(reg) \ - read_bar_via_cfg(console_access_cap, \ - common_offset+offsetof(struct virtio_pci_common_cfg,reg)) - - /* Check features: they must offer EMERG_WRITE */ - write_common_config(device_feature_select, 0); - - if (!(read_common_config(device_feature) - & (1 << VIRTIO_CONSOLE_F_EMERG_WRITE))) { - printk(KERN_ERR "lguest: console missing EMERG_WRITE\n"); + /* + * Note that we can't check features, until we've set the DRIVER + * status bit. We don't want to do that until we have a real driver, + * so we just check that the device-specific config has room for + * emerg_wr. If it doesn't support VIRTIO_CONSOLE_F_EMERG_WRITE + * it should ignore the access. + */ + if (device_len < (offsetof(struct virtio_console_config, emerg_wr) + + sizeof(u32))) { + printk(KERN_ERR "lguest: console missing emerg_wr field\n"); return; } console_cfg_offset = device_offset; + printk(KERN_INFO "lguest: Console via virtio-pci emerg_wr\n"); } /* -- cgit v1.1