From 9b6934a3b449266850149b717597408354039e95 Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Fri, 21 Sep 2012 17:04:24 +0100 Subject: xen/hvc: handle backend CLOSED without CLOSING Backend drivers shouldn't transistion to CLOSED unless the frontend is CLOSED. If a backend does transition to CLOSED too soon then the frontend may not see the CLOSING state and will not properly shutdown. So, treat an unexpected backend CLOSED state the same as CLOSING. Signed-off-by: David Vrabel Signed-off-by: Konrad Rzeszutek Wilk diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c index 2944ff8..f4abfe2 100644 --- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -478,7 +478,6 @@ static void xencons_backend_changed(struct xenbus_device *dev, case XenbusStateInitialising: case XenbusStateInitialised: case XenbusStateUnknown: - case XenbusStateClosed: break; case XenbusStateInitWait: @@ -488,6 +487,10 @@ static void xencons_backend_changed(struct xenbus_device *dev, xenbus_switch_state(dev, XenbusStateConnected); break; + case XenbusStateClosed: + if (dev->state == XenbusStateClosed) + break; + /* Missed the backend's CLOSING state -- fallthrough */ case XenbusStateClosing: xenbus_frontend_closed(dev); break; -- cgit v0.10.2 From 34b6f01a79bd65fbd06511d2cb7b28e33a506246 Mon Sep 17 00:00:00 2001 From: Olaf Hering Date: Mon, 1 Oct 2012 21:18:01 +0200 Subject: xen pv-on-hvm: add pfn_is_ram helper for kdump Register pfn_is_ram helper speed up reading /proc/vmcore in the kdump kernel. See commit message of 997c136f518c ("fs/proc/vmcore.c: add hook to read_from_oldmem() to check for non-ram pages") for details. It makes use of a new hvmop HVMOP_get_mem_type which was introduced in xen 4.2 (23298:26413986e6e0) and backported to 4.1.1. The new function is currently only enabled for reading /proc/vmcore. Later it will be used also for the kexec kernel. Since that requires more changes in the generic kernel make it static for the time being. Signed-off-by: Olaf Hering Signed-off-by: Konrad Rzeszutek Wilk diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 5a16824..963cb2d 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -47,6 +47,7 @@ #include #include #include +#include #include @@ -2381,6 +2382,43 @@ void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order) EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region); #ifdef CONFIG_XEN_PVHVM +#ifdef CONFIG_PROC_VMCORE +/* + * This function is used in two contexts: + * - the kdump kernel has to check whether a pfn of the crashed kernel + * was a ballooned page. vmcore is using this function to decide + * whether to access a pfn of the crashed kernel. + * - the kexec kernel has to check whether a pfn was ballooned by the + * previous kernel. If the pfn is ballooned, handle it properly. + * Returns 0 if the pfn is not backed by a RAM page, the caller may + * handle the pfn special in this case. + */ +static int xen_oldmem_pfn_is_ram(unsigned long pfn) +{ + struct xen_hvm_get_mem_type a = { + .domid = DOMID_SELF, + .pfn = pfn, + }; + int ram; + + if (HYPERVISOR_hvm_op(HVMOP_get_mem_type, &a)) + return -ENXIO; + + switch (a.mem_type) { + case HVMMEM_mmio_dm: + ram = 0; + break; + case HVMMEM_ram_rw: + case HVMMEM_ram_ro: + default: + ram = 1; + break; + } + + return ram; +} +#endif + static void xen_hvm_exit_mmap(struct mm_struct *mm) { struct xen_hvm_pagetable_dying a; @@ -2411,6 +2449,9 @@ void __init xen_hvm_init_mmu_ops(void) { if (is_pagetable_dying_supported()) pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap; +#ifdef CONFIG_PROC_VMCORE + register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram); +#endif } #endif diff --git a/include/xen/interface/hvm/hvm_op.h b/include/xen/interface/hvm/hvm_op.h index a4827f4..956a046 100644 --- a/include/xen/interface/hvm/hvm_op.h +++ b/include/xen/interface/hvm/hvm_op.h @@ -43,4 +43,23 @@ struct xen_hvm_pagetable_dying { typedef struct xen_hvm_pagetable_dying xen_hvm_pagetable_dying_t; DEFINE_GUEST_HANDLE_STRUCT(xen_hvm_pagetable_dying_t); +enum hvmmem_type_t { + HVMMEM_ram_rw, /* Normal read/write guest RAM */ + HVMMEM_ram_ro, /* Read-only; writes are discarded */ + HVMMEM_mmio_dm, /* Reads and write go to the device model */ +}; + +#define HVMOP_get_mem_type 15 +/* Return hvmmem_type_t for the specified pfn. */ +struct xen_hvm_get_mem_type { + /* Domain to be queried. */ + domid_t domid; + /* OUT variable. */ + uint16_t mem_type; + uint16_t pad[2]; /* align next field on 8-byte boundary */ + /* IN variable. */ + uint64_t pfn; +}; +DEFINE_GUEST_HANDLE_STRUCT(xen_hvm_get_mem_type); + #endif /* __XEN_PUBLIC_HVM_HVM_OP_H__ */ -- cgit v0.10.2 From cd0608e71e9757f4dae35bcfb4e88f4d1a03a8ab Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Wed, 10 Oct 2012 13:30:47 -0400 Subject: xen/bootup: allow read_tscp call for Xen PV guests. The hypervisor will trap it. However without this patch, we would crash as the .read_tscp is set to NULL. This patch fixes it and sets it to the native_read_tscp call. CC: stable@vger.kernel.org Signed-off-by: Konrad Rzeszutek Wilk diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 70f1404..668bbfe 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1164,6 +1164,8 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, + .read_tscp = native_read_tscp, + .iret = xen_iret, .irq_enable_sysexit = xen_sysexit, #ifdef CONFIG_X86_64 -- cgit v0.10.2 From 1a7bbda5b1ab0e02622761305a32dc38735b90b2 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Wed, 10 Oct 2012 13:25:48 -0400 Subject: xen/bootup: allow {read|write}_cr8 pvops call. We actually do not do anything about it. Just return a default value of zero and if the kernel tries to write anything but 0 we BUG_ON. This fixes the case when an user tries to suspend the machine and it blows up in save_processor_state b/c 'read_cr8' is set to NULL and we get: kernel BUG at /home/konrad/ssd/linux/arch/x86/include/asm/paravirt.h:100! invalid opcode: 0000 [#1] SMP Pid: 2687, comm: init.late Tainted: G O 3.6.0upstream-00002-gac264ac-dirty #4 Bochs Bochs RIP: e030:[] [] save_processor_state+0x212/0x270 .. snip.. Call Trace: [] do_suspend_lowlevel+0xf/0xac [] ? x86_acpi_suspend_lowlevel+0x10c/0x150 [] acpi_suspend_enter+0x57/0xd5 CC: stable@vger.kernel.org Signed-off-by: Konrad Rzeszutek Wilk diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 668bbfe..4466feb 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -987,7 +987,16 @@ static void xen_write_cr4(unsigned long cr4) native_write_cr4(cr4); } - +#ifdef CONFIG_X86_64 +static inline unsigned long xen_read_cr8(void) +{ + return 0; +} +static inline void xen_write_cr8(unsigned long val) +{ + BUG_ON(val); +} +#endif static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) { int ret; @@ -1156,6 +1165,11 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .read_cr4_safe = native_read_cr4_safe, .write_cr4 = xen_write_cr4, +#ifdef CONFIG_X86_64 + .read_cr8 = xen_read_cr8, + .write_cr8 = xen_write_cr8, +#endif + .wbinvd = native_wbinvd, .read_msr = native_read_msr_safe, -- cgit v0.10.2 From cb6b6df111e46b9d0f79eb971575fd50555f43f4 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Wed, 10 Oct 2012 13:23:36 -0400 Subject: xen/pv-on-hvm kexec: add quirk for Xen 3.4 and shutdown watches. The commit 254d1a3f02ebc10ccc6e4903394d8d3f484f715e, titled "xen/pv-on-hvm kexec: shutdown watches from old kernel" assumes that the XenBus backend can deal with reading of values from: "control/platform-feature-xs_reset_watches": ... a patch for xenstored is required so that it accepts the XS_RESET_WATCHES request from a client (see changeset 23839:42a45baf037d in xen-unstable.hg). Without the patch for xenstored the registration of watches will fail and some features of a PVonHVM guest are not available. The guest is still able to boot, but repeated kexec boots will fail." Sadly this is not true when using a Xen 3.4 hypervisor and booting a PVHVM guest. We end up hanging at: err = xenbus_scanf(XBT_NIL, "control", "platform-feature-xs_reset_watches", "%d", &supported); This can easily be seen with guests hanging at xenbus_init: NX (Execute Disable) protection: active SMBIOS 2.4 present. DMI: Xen HVM domU, BIOS 3.4.0 05/13/2011 Hypervisor detected: Xen HVM Xen version 3.4. Xen Platform PCI: I/O protocol version 1 ... snip .. calling xenbus_init+0x0/0x27e @ 1 Reverting the commit or using the attached patch fixes the issue. This fix checks whether the hypervisor is older than 4.0 and if so does not try to perform the read. Fixes-Oracle-Bug: 14708233 CC: stable@vger.kernel.org Acked-by: Olaf Hering [v2: Added a comment in the source code] Signed-off-by: Konrad Rzeszutek Wilk diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 131dec0..48220e1 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -48,6 +48,7 @@ #include #include #include "xenbus_comms.h" +#include struct xs_stored_msg { struct list_head list; @@ -618,7 +619,24 @@ static struct xenbus_watch *find_watch(const char *token) return NULL; } +/* + * Certain older XenBus toolstack cannot handle reading values that are + * not populated. Some Xen 3.4 installation are incapable of doing this + * so if we are running on anything older than 4 do not attempt to read + * control/platform-feature-xs_reset_watches. + */ +static bool xen_strict_xenbus_quirk() +{ + uint32_t eax, ebx, ecx, edx, base; + + base = xen_cpuid_base(); + cpuid(base + 1, &eax, &ebx, &ecx, &edx); + if ((eax >> 16) < 4) + return true; + return false; + +} static void xs_reset_watches(void) { int err, supported = 0; @@ -626,6 +644,9 @@ static void xs_reset_watches(void) if (!xen_hvm_domain() || xen_initial_domain()) return; + if (xen_strict_xenbus_quirk()) + return; + err = xenbus_scanf(XBT_NIL, "control", "platform-feature-xs_reset_watches", "%d", &supported); if (err != 1 || !supported) -- cgit v0.10.2