From ca08649eb5dd30f11a5a8fe8659b48899b7ea6a1 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Thu, 16 Aug 2012 11:31:27 -0400 Subject: [PATCH 1/3] Revert "xen PVonHVM: move shared_info to MMIO before kexec" This reverts commit 00e37bdb0113a98408de42db85be002f21dbffd3. During shutdown of PVHVM guests with more than 2VCPUs on certain machines we can hit the race where the replaced shared_info is not replaced fast enough and the PV time clock retries reading the same area over and over without any any success and is stuck in an infinite loop. Acked-by: Olaf Hering Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/xen/enlighten.c | 118 ++++--------------------------------- arch/x86/xen/suspend.c | 2 +- arch/x86/xen/xen-ops.h | 2 +- drivers/xen/platform-pci.c | 15 ----- include/xen/events.h | 2 - 5 files changed, 13 insertions(+), 126 deletions(-) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index a6f8acbdfc9a..f1814fc2cb77 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -31,7 +31,6 @@ #include #include #include -#include #include #include @@ -1472,130 +1471,38 @@ asmlinkage void __init xen_start_kernel(void) #endif } -#ifdef CONFIG_XEN_PVHVM -/* - * The pfn containing the shared_info is located somewhere in RAM. This - * will cause trouble if the current kernel is doing a kexec boot into a - * new kernel. The new kernel (and its startup code) can not know where - * the pfn is, so it can not reserve the page. The hypervisor will - * continue to update the pfn, and as a result memory corruption occours - * in the new kernel. - * - * One way to work around this issue is to allocate a page in the - * xen-platform pci device's BAR memory range. But pci init is done very - * late and the shared_info page is already in use very early to read - * the pvclock. So moving the pfn from RAM to MMIO is racy because some - * code paths on other vcpus could access the pfn during the small - * window when the old pfn is moved to the new pfn. There is even a - * small window were the old pfn is not backed by a mfn, and during that - * time all reads return -1. - * - * Because it is not known upfront where the MMIO region is located it - * can not be used right from the start in xen_hvm_init_shared_info. - * - * To minimise trouble the move of the pfn is done shortly before kexec. - * This does not eliminate the race because all vcpus are still online - * when the syscore_ops will be called. But hopefully there is no work - * pending at this point in time. Also the syscore_op is run last which - * reduces the risk further. - */ - -static struct shared_info *xen_hvm_shared_info; - -static void xen_hvm_connect_shared_info(unsigned long pfn) +void __ref xen_hvm_init_shared_info(void) { + int cpu; struct xen_add_to_physmap xatp; + static struct shared_info *shared_info_page = 0; + if (!shared_info_page) + shared_info_page = (struct shared_info *) + extend_brk(PAGE_SIZE, PAGE_SIZE); xatp.domid = DOMID_SELF; xatp.idx = 0; xatp.space = XENMAPSPACE_shared_info; - xatp.gpfn = pfn; + xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT; if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) BUG(); -} -static void xen_hvm_set_shared_info(struct shared_info *sip) -{ - int cpu; - - HYPERVISOR_shared_info = sip; + HYPERVISOR_shared_info = (struct shared_info *)shared_info_page; /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info * page, we use it in the event channel upcall and in some pvclock * related functions. We don't need the vcpu_info placement * optimizations because we don't use any pv_mmu or pv_irq op on * HVM. - * When xen_hvm_set_shared_info is run at boot time only vcpu 0 is - * online but xen_hvm_set_shared_info is run at resume time too and + * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is + * online but xen_hvm_init_shared_info is run at resume time too and * in that case multiple vcpus might be online. */ for_each_online_cpu(cpu) { per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; } } -/* Reconnect the shared_info pfn to a mfn */ -void xen_hvm_resume_shared_info(void) -{ - xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT); -} - -#ifdef CONFIG_KEXEC -static struct shared_info *xen_hvm_shared_info_kexec; -static unsigned long xen_hvm_shared_info_pfn_kexec; - -/* Remember a pfn in MMIO space for kexec reboot */ -void __devinit xen_hvm_prepare_kexec(struct shared_info *sip, unsigned long pfn) -{ - xen_hvm_shared_info_kexec = sip; - xen_hvm_shared_info_pfn_kexec = pfn; -} - -static void xen_hvm_syscore_shutdown(void) -{ - struct xen_memory_reservation reservation = { - .domid = DOMID_SELF, - .nr_extents = 1, - }; - unsigned long prev_pfn; - int rc; - - if (!xen_hvm_shared_info_kexec) - return; - - prev_pfn = __pa(xen_hvm_shared_info) >> PAGE_SHIFT; - set_xen_guest_handle(reservation.extent_start, &prev_pfn); - - /* Move pfn to MMIO, disconnects previous pfn from mfn */ - xen_hvm_connect_shared_info(xen_hvm_shared_info_pfn_kexec); - - /* Update pointers, following hypercall is also a memory barrier */ - xen_hvm_set_shared_info(xen_hvm_shared_info_kexec); - - /* Allocate new mfn for previous pfn */ - do { - rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation); - if (rc == 0) - msleep(123); - } while (rc == 0); - - /* Make sure the previous pfn is really connected to a (new) mfn */ - BUG_ON(rc != 1); -} - -static struct syscore_ops xen_hvm_syscore_ops = { - .shutdown = xen_hvm_syscore_shutdown, -}; -#endif - -/* Use a pfn in RAM, may move to MMIO before kexec. */ -static void __init xen_hvm_init_shared_info(void) -{ - /* Remember pointer for resume */ - xen_hvm_shared_info = extend_brk(PAGE_SIZE, PAGE_SIZE); - xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT); - xen_hvm_set_shared_info(xen_hvm_shared_info); -} - +#ifdef CONFIG_XEN_PVHVM static void __init init_hvm_pv_info(void) { int major, minor; @@ -1646,9 +1553,6 @@ static void __init xen_hvm_guest_init(void) init_hvm_pv_info(); xen_hvm_init_shared_info(); -#ifdef CONFIG_KEXEC - register_syscore_ops(&xen_hvm_syscore_ops); -#endif if (xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index ae8a00c39de4..45329c8c226e 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -30,7 +30,7 @@ void xen_arch_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; - xen_hvm_resume_shared_info(); + xen_hvm_init_shared_info(); xen_callback_vector(); xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 1e4329e04e0f..202d4c150154 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -41,7 +41,7 @@ void xen_enable_syscall(void); void xen_vcpu_restore(void); void xen_callback_vector(void); -void xen_hvm_resume_shared_info(void); +void xen_hvm_init_shared_info(void); void xen_unplug_emulated_devices(void); void __init xen_build_dynamic_phys_to_machine(void); diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index d4c50d63acbc..97ca359ae2bd 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -101,19 +101,6 @@ static int platform_pci_resume(struct pci_dev *pdev) return 0; } -static void __devinit prepare_shared_info(void) -{ -#ifdef CONFIG_KEXEC - unsigned long addr; - struct shared_info *hvm_shared_info; - - addr = alloc_xen_mmio(PAGE_SIZE); - hvm_shared_info = ioremap(addr, PAGE_SIZE); - memset(hvm_shared_info, 0, PAGE_SIZE); - xen_hvm_prepare_kexec(hvm_shared_info, addr >> PAGE_SHIFT); -#endif -} - static int __devinit platform_pci_init(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -151,8 +138,6 @@ static int __devinit platform_pci_init(struct pci_dev *pdev, platform_mmio = mmio_addr; platform_mmiolen = mmio_len; - prepare_shared_info(); - if (!xen_have_vector_callback) { ret = xen_allocate_irq(pdev); if (ret) { diff --git a/include/xen/events.h b/include/xen/events.h index 9c641deb65d2..04399b28e821 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -58,8 +58,6 @@ void notify_remote_via_irq(int irq); void xen_irq_resume(void); -void xen_hvm_prepare_kexec(struct shared_info *sip, unsigned long pfn); - /* Clear an irq's pending state, in preparation for polling on it */ void xen_clear_irq_pending(int irq); void xen_set_irq_pending(int irq); From 250a41e0ecc433cdd553a364d0fc74c766425209 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Fri, 17 Aug 2012 09:27:35 -0400 Subject: [PATCH 2/3] xen/p2m: Reuse existing P2M leafs if they are filled with 1:1 PFNs or INVALID. If P2M leaf is completly packed with INVALID_P2M_ENTRY or with 1:1 PFNs (so IDENTITY_FRAME type PFNs), we can swap the P2M leaf with either a p2m_missing or p2m_identity respectively. The old page (which was created via extend_brk or was grafted on from the mfn_list) can be re-used for setting new PFNs. This also means we can remove git commit: 5bc6f9888db5739abfa0cae279b4b442e4db8049 xen/p2m: Reserve 8MB of _brk space for P2M leafs when populating back which tried to fix this. and make the amount that is required to be reserved much smaller. CC: stable@vger.kernel.org # for 3.5 only. Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/xen/p2m.c | 95 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 92 insertions(+), 3 deletions(-) diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index b2e91d40a4cb..d4b255463253 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -196,9 +196,11 @@ RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3); /* When we populate back during bootup, the amount of pages can vary. The * max we have is seen is 395979, but that does not mean it can't be more. - * But some machines can have 3GB I/O holes even. So lets reserve enough - * for 4GB of I/O and E820 holes. */ -RESERVE_BRK(p2m_populated, PMD_SIZE * 4); + * Some machines can have 3GB I/O holes even. With early_can_reuse_p2m_middle + * it can re-use Xen provided mfn_list array, so we only need to allocate at + * most three P2M top nodes. */ +RESERVE_BRK(p2m_populated, PAGE_SIZE * 3); + static inline unsigned p2m_top_index(unsigned long pfn) { BUG_ON(pfn >= MAX_P2M_PFN); @@ -575,12 +577,99 @@ static bool __init early_alloc_p2m(unsigned long pfn) } return true; } + +/* + * Skim over the P2M tree looking at pages that are either filled with + * INVALID_P2M_ENTRY or with 1:1 PFNs. If found, re-use that page and + * replace the P2M leaf with a p2m_missing or p2m_identity. + * Stick the old page in the new P2M tree location. + */ +bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_mfn) +{ + unsigned topidx; + unsigned mididx; + unsigned ident_pfns; + unsigned inv_pfns; + unsigned long *p2m; + unsigned long *mid_mfn_p; + unsigned idx; + unsigned long pfn; + + /* We only look when this entails a P2M middle layer */ + if (p2m_index(set_pfn)) + return false; + + for (pfn = 0; pfn <= MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) { + topidx = p2m_top_index(pfn); + + if (!p2m_top[topidx]) + continue; + + if (p2m_top[topidx] == p2m_mid_missing) + continue; + + mididx = p2m_mid_index(pfn); + p2m = p2m_top[topidx][mididx]; + if (!p2m) + continue; + + if ((p2m == p2m_missing) || (p2m == p2m_identity)) + continue; + + if ((unsigned long)p2m == INVALID_P2M_ENTRY) + continue; + + ident_pfns = 0; + inv_pfns = 0; + for (idx = 0; idx < P2M_PER_PAGE; idx++) { + /* IDENTITY_PFNs are 1:1 */ + if (p2m[idx] == IDENTITY_FRAME(pfn + idx)) + ident_pfns++; + else if (p2m[idx] == INVALID_P2M_ENTRY) + inv_pfns++; + else + break; + } + if ((ident_pfns == P2M_PER_PAGE) || (inv_pfns == P2M_PER_PAGE)) + goto found; + } + return false; +found: + /* Found one, replace old with p2m_identity or p2m_missing */ + p2m_top[topidx][mididx] = (ident_pfns ? p2m_identity : p2m_missing); + /* And the other for save/restore.. */ + mid_mfn_p = p2m_top_mfn_p[topidx]; + /* NOTE: Even if it is a p2m_identity it should still be point to + * a page filled with INVALID_P2M_ENTRY entries. */ + mid_mfn_p[mididx] = virt_to_mfn(p2m_missing); + + /* Reset where we want to stick the old page in. */ + topidx = p2m_top_index(set_pfn); + mididx = p2m_mid_index(set_pfn); + + /* This shouldn't happen */ + if (WARN_ON(p2m_top[topidx] == p2m_mid_missing)) + early_alloc_p2m(set_pfn); + + if (WARN_ON(p2m_top[topidx][mididx] != p2m_missing)) + return false; + + p2m_init(p2m); + p2m_top[topidx][mididx] = p2m; + mid_mfn_p = p2m_top_mfn_p[topidx]; + mid_mfn_p[mididx] = virt_to_mfn(p2m); + + return true; +} bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn) { if (unlikely(!__set_phys_to_machine(pfn, mfn))) { if (!early_alloc_p2m(pfn)) return false; + if (early_can_reuse_p2m_middle(pfn, mfn)) + return __set_phys_to_machine(pfn, mfn); + if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/)) return false; From c96aae1f7f393387d160211f60398d58463a7e65 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Fri, 17 Aug 2012 16:43:28 -0400 Subject: [PATCH 3/3] xen/setup: Fix one-off error when adding for-balloon PFNs to the P2M. When we are finished with return PFNs to the hypervisor, then populate it back, and also mark the E820 MMIO and E820 gaps as IDENTITY_FRAMEs, we then call P2M to set areas that can be used for ballooning. We were off by one, and ended up over-writting a P2M entry that most likely was an IDENTITY_FRAME. For example: 1-1 mapping on 40000->40200 1-1 mapping on bc558->bc5ac 1-1 mapping on bc5b4->bc8c5 1-1 mapping on bc8c6->bcb7c 1-1 mapping on bcd00->100000 Released 614 pages of unused memory Set 277889 page(s) to 1-1 mapping Populating 40200-40466 pfn range: 614 pages added => here we set from 40466 up to bc559 P2M tree to be INVALID_P2M_ENTRY. We should have done it up to bc558. The end result is that if anybody is trying to construct a PTE for PFN bc558 they end up with ~PAGE_PRESENT. CC: stable@vger.kernel.org Reported-by-and-Tested-by: Andre Przywara Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/xen/setup.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index ead85576d54a..d11ca11d14fc 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -78,9 +78,16 @@ static void __init xen_add_extra_mem(u64 start, u64 size) memblock_reserve(start, size); xen_max_p2m_pfn = PFN_DOWN(start + size); + for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) { + unsigned long mfn = pfn_to_mfn(pfn); + + if (WARN(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn)) + continue; + WARN(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n", + pfn, mfn); - for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++) __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); + } } static unsigned long __init xen_do_chunk(unsigned long start,