From 8e96a87c5431c256feb65bcfc5aec92d9f7839b6 Mon Sep 17 00:00:00 2001 From: Cyril Bur Date: Fri, 17 Jun 2016 14:58:34 +1000 Subject: [PATCH 1/4] powerpc/tm: Always reclaim in start_thread() for exec() class syscalls Userspace can quite legitimately perform an exec() syscall with a suspended transaction. exec() does not return to the old process, rather it load a new one and starts that, the expectation therefore is that the new process starts not in a transaction. Currently exec() is not treated any differently to any other syscall which creates problems. Firstly it could allow a new process to start with a suspended transaction for a binary that no longer exists. This means that the checkpointed state won't be valid and if the suspended transaction were ever to be resumed and subsequently aborted (a possibility which is exceedingly likely as exec()ing will likely doom the transaction) the new process will jump to invalid state. Secondly the incorrect attempt to keep the transactional state while still zeroing state for the new process creates at least two TM Bad Things. The first triggers on the rfid to return to userspace as start_thread() has given the new process a 'clean' MSR but the suspend will still be set in the hardware MSR. The second TM Bad Thing triggers in __switch_to() as the processor is still transactionally suspended but __switch_to() wants to zero the TM sprs for the new process. This is an example of the outcome of calling exec() with a suspended transaction. Note the first 700 is likely the first TM bad thing decsribed earlier only the kernel can't report it as we've loaded userspace registers. c000000000009980 is the rfid in fast_exception_return() Bad kernel stack pointer 3fffcfa1a370 at c000000000009980 Oops: Bad kernel stack pointer, sig: 6 [#1] CPU: 0 PID: 2006 Comm: tm-execed Not tainted NIP: c000000000009980 LR: 0000000000000000 CTR: 0000000000000000 REGS: c00000003ffefd40 TRAP: 0700 Not tainted MSR: 8000000300201031 CR: 00000000 XER: 00000000 CFAR: c0000000000098b4 SOFTE: 0 PACATMSCRATCH: b00000010000d033 GPR00: 0000000000000000 00003fffcfa1a370 0000000000000000 0000000000000000 GPR04: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR08: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR12: 00003fff966611c0 0000000000000000 0000000000000000 0000000000000000 NIP [c000000000009980] fast_exception_return+0xb0/0xb8 LR [0000000000000000] (null) Call Trace: Instruction dump: f84d0278 e9a100d8 7c7b03a6 e84101a0 7c4ff120 e8410170 7c5a03a6 e8010070 e8410080 e8610088 e8810090 e8210078 <4c000024> 48000000 e8610178 88ed023b Kernel BUG at c000000000043e80 [verbose debug info unavailable] Unexpected TM Bad Thing exception at c000000000043e80 (msr 0x201033) Oops: Unrecoverable exception, sig: 6 [#2] CPU: 0 PID: 2006 Comm: tm-execed Tainted: G D task: c0000000fbea6d80 ti: c00000003ffec000 task.ti: c0000000fb7ec000 NIP: c000000000043e80 LR: c000000000015a24 CTR: 0000000000000000 REGS: c00000003ffef7e0 TRAP: 0700 Tainted: G D MSR: 8000000300201033 CR: 28002828 XER: 00000000 CFAR: c000000000015a20 SOFTE: 0 PACATMSCRATCH: b00000010000d033 GPR00: 0000000000000000 c00000003ffefa60 c000000000db5500 c0000000fbead000 GPR04: 8000000300001033 2222222222222222 2222222222222222 00000000ff160000 GPR08: 0000000000000000 800000010000d033 c0000000fb7e3ea0 c00000000fe00004 GPR12: 0000000000002200 c00000000fe00000 0000000000000000 0000000000000000 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000000000000 0000000000000000 c0000000fbea7410 00000000ff160000 GPR24: c0000000ffe1f600 c0000000fbea8700 c0000000fbea8700 c0000000fbead000 GPR28: c000000000e20198 c0000000fbea6d80 c0000000fbeab680 c0000000fbea6d80 NIP [c000000000043e80] tm_restore_sprs+0xc/0x1c LR [c000000000015a24] __switch_to+0x1f4/0x420 Call Trace: Instruction dump: 7c800164 4e800020 7c0022a6 f80304a8 7c0222a6 f80304b0 7c0122a6 f80304b8 4e800020 e80304a8 7c0023a6 e80304b0 <7c0223a6> e80304b8 7c0123a6 4e800020 This fixes CVE-2016-5828. Fixes: bc2a9408fa65 ("powerpc: Hook in new transactional memory code") Cc: stable@vger.kernel.org # v3.9+ Signed-off-by: Cyril Bur Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/process.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index e2f12cbcade9..0b93893424f5 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1505,6 +1505,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.regs = regs - 1; } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * Clear any transactional state, we're exec()ing. The cause is + * not important as there will never be a recheckpoint so it's not + * user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); +#endif + memset(regs->gpr, 0, sizeof(regs->gpr)); regs->ctr = 0; regs->link = 0; From cca0e542e02e48cce541a49c4046ec094ec27c1e Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Fri, 24 Jun 2016 14:49:02 +1000 Subject: [PATCH 2/4] powerpc/eeh: Fix wrong argument passed to eeh_rmv_device() When calling eeh_rmv_device() in eeh_reset_device() for partial hotplug case, @rmv_data instead of its address is the proper argument. Otherwise, the stack frame is corrupted when writing to @rmv_data (actually its address) in eeh_rmv_device(). It results in kernel crash as observed. This fixes the issue by passing @rmv_data, not its address to eeh_rmv_device() in eeh_reset_device(). Fixes: 67086e32b564 ("powerpc/eeh: powerpc/eeh: Support error recovery for VF PE") Reported-by: Pridhiviraj Paidipeddi Signed-off-by: Gavin Shan Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/eeh_driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index b5f73cb5eeb6..d70101e1e25c 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -647,7 +647,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, pci_unlock_rescan_remove(); } } else if (frozen_bus) { - eeh_pe_dev_traverse(pe, eeh_rmv_device, &rmv_data); + eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data); } /* From 190ce8693c23eae09ba5f303a83bf2fbeb6478b1 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Tue, 28 Jun 2016 13:01:04 +1000 Subject: [PATCH 3/4] powerpc/tm: Avoid SLB faults in treclaim/trecheckpoint when RI=0 Currently we have 2 segments that are bolted for the kernel linear mapping (ie 0xc000... addresses). This is 0 to 1TB and also the kernel stacks. Anything accessed outside of these regions may need to be faulted in. (In practice machines with TM always have 1T segments) If a machine has < 2TB of memory we never fault on the kernel linear mapping as these two segments cover all physical memory. If a machine has > 2TB of memory, there may be structures outside of these two segments that need to be faulted in. This faulting can occur when running as a guest as the hypervisor may remove any SLB that's not bolted. When we treclaim and trecheckpoint we have a window where we need to run with the userspace GPRs. This means that we no longer have a valid stack pointer in r1. For this window we therefore clear MSR RI to indicate that any exceptions taken at this point won't be able to be handled. This means that we can't take segment misses in this RI=0 window. In this RI=0 region, we currently access the thread_struct for the process being context switched to or from. This thread_struct access may cause a segment fault since it's not guaranteed to be covered by the two bolted segment entries described above. We've seen this with a crash when running as a guest with > 2TB of memory on PowerVM: Unrecoverable exception 4100 at c00000000004f138 Oops: Unrecoverable exception, sig: 6 [#1] SMP NR_CPUS=2048 NUMA pSeries CPU: 1280 PID: 7755 Comm: kworker/1280:1 Tainted: G X 4.4.13-46-default #1 task: c000189001df4210 ti: c000189001d5c000 task.ti: c000189001d5c000 NIP: c00000000004f138 LR: 0000000010003a24 CTR: 0000000010001b20 REGS: c000189001d5f730 TRAP: 4100 Tainted: G X (4.4.13-46-default) MSR: 8000000100001031 CR: 24000048 XER: 00000000 CFAR: c00000000004ed18 SOFTE: 0 GPR00: ffffffffc58d7b60 c000189001d5f9b0 00000000100d7d00 000000003a738288 GPR04: 0000000000002781 0000000000000006 0000000000000000 c0000d1f4d889620 GPR08: 000000000000c350 00000000000008ab 00000000000008ab 00000000100d7af0 GPR12: 00000000100d7ae8 00003ffe787e67a0 0000000000000000 0000000000000211 GPR16: 0000000010001b20 0000000000000000 0000000000800000 00003ffe787df110 GPR20: 0000000000000001 00000000100d1e10 0000000000000000 00003ffe787df050 GPR24: 0000000000000003 0000000000010000 0000000000000000 00003fffe79e2e30 GPR28: 00003fffe79e2e68 00000000003d0f00 00003ffe787e67a0 00003ffe787de680 NIP [c00000000004f138] restore_gprs+0xd0/0x16c LR [0000000010003a24] 0x10003a24 Call Trace: [c000189001d5f9b0] [c000189001d5f9f0] 0xc000189001d5f9f0 (unreliable) [c000189001d5fb90] [c00000000001583c] tm_recheckpoint+0x6c/0xa0 [c000189001d5fbd0] [c000000000015c40] __switch_to+0x2c0/0x350 [c000189001d5fc30] [c0000000007e647c] __schedule+0x32c/0x9c0 [c000189001d5fcb0] [c0000000007e6b58] schedule+0x48/0xc0 [c000189001d5fce0] [c0000000000deabc] worker_thread+0x22c/0x5b0 [c000189001d5fd80] [c0000000000e7000] kthread+0x110/0x130 [c000189001d5fe30] [c000000000009538] ret_from_kernel_thread+0x5c/0xa4 Instruction dump: 7cb103a6 7cc0e3a6 7ca222a6 78a58402 38c00800 7cc62838 08860000 7cc000a6 38a00006 78c60022 7cc62838 0b060000 7ccff120 e8270078 e8a70098 ---[ end trace 602126d0a1dedd54 ]--- This fixes this by copying the required data from the thread_struct to the stack before we clear MSR RI. Then once we clear RI, we only access the stack, guaranteeing there's no segment miss. We also tighten the region over which we set RI=0 on the treclaim() path. This may have a slight performance impact since we're adding an mtmsr instruction. Fixes: 090b9284d725 ("powerpc/tm: Clear MSR RI in non-recoverable TM code") Signed-off-by: Michael Neuling Reviewed-by: Cyril Bur Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/tm.S | 61 +++++++++++++++++++++++++++++----------- 1 file changed, 44 insertions(+), 17 deletions(-) diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index bf8f34a58670..b7019b559ddb 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim) std r3, STK_PARAM(R3)(r1) SAVE_NVGPRS(r1) - /* We need to setup MSR for VSX register save instructions. Here we - * also clear the MSR RI since when we do the treclaim, we won't have a - * valid kernel pointer for a while. We clear RI here as it avoids - * adding another mtmsr closer to the treclaim. This makes the region - * maked as non-recoverable wider than it needs to be but it saves on - * inserting another mtmsrd later. - */ + /* We need to setup MSR for VSX register save instructions. */ mfmsr r14 mr r15, r14 ori r15, r15, MSR_FP - li r16, MSR_RI + li r16, 0 ori r16, r16, MSR_EE /* IRQs hard off */ andc r15, r15, r16 oris r15, r15, MSR_VEC@h @@ -176,7 +170,17 @@ dont_backup_fp: 1: tdeqi r6, 0 EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 - /* The moment we treclaim, ALL of our GPRs will switch + /* Clear MSR RI since we are about to change r1, EE is already off. */ + li r4, 0 + mtmsrd r4, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + * + * The moment we treclaim, ALL of our GPRs will switch * to user register state. (FPRs, CCR etc. also!) * Use an sprg and a tm_scratch in the PACA to shuffle. */ @@ -197,6 +201,11 @@ dont_backup_fp: /* Store the PPR in r11 and reset to decent value */ std r11, GPR11(r1) /* Temporary stash */ + + /* Reset MSR RI so we can take SLB faults again */ + li r11, MSR_RI + mtmsrd r11, 1 + mfspr r11, SPRN_PPR HMT_MEDIUM @@ -397,11 +406,6 @@ restore_gprs: ld r5, THREAD_TM_DSCR(r3) ld r6, THREAD_TM_PPR(r3) - /* Clear the MSR RI since we are about to change R1. EE is already off - */ - li r4, 0 - mtmsrd r4, 1 - REST_GPR(0, r7) /* GPR0 */ REST_2GPRS(2, r7) /* GPR2-3 */ REST_GPR(4, r7) /* GPR4 */ @@ -439,10 +443,33 @@ restore_gprs: ld r6, _CCR(r7) mtcr r6 - REST_GPR(1, r7) /* GPR1 */ - REST_GPR(5, r7) /* GPR5-7 */ REST_GPR(6, r7) - ld r7, GPR7(r7) + + /* + * Store r1 and r5 on the stack so that we can access them + * after we clear MSR RI. + */ + + REST_GPR(5, r7) + std r5, -8(r1) + ld r5, GPR1(r7) + std r5, -16(r1) + + REST_GPR(7, r7) + + /* Clear MSR RI since we are about to change r1. EE is already off */ + li r5, 0 + mtmsrd r5, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + */ + + ld r5, -8(r1) + ld r1, -16(r1) /* Commit register state as checkpointed state: */ TRECHKPT From bfa37087aa04e45f56c41142dfceecb79b8e6ef9 Mon Sep 17 00:00:00 2001 From: Darren Stevens Date: Wed, 29 Jun 2016 21:06:28 +0100 Subject: [PATCH 4/4] powerpc: Initialise pci_io_base as early as possible Commit d6a9996e84ac ("powerpc/mm: vmalloc abstraction in preparation for radix") turned kernel memory and IO addresses from #defined constants to variables initialised at runtime. On PA6T (pasemi) systems the setup_arch() machine call initialises the onboard PCI-e root-ports, and uses pci_io_base to do this, which is now before its value has been set, resulting in a panic early in boot before console IO is initialised. Move the pci_io_base initialisation to the same place as vmalloc ranges are set (hash__early_init_mmu()/radix__early_init_mmu()) - this is the earliest possible place we can initialise it. Fixes: d6a9996e84ac ("powerpc/mm: vmalloc abstraction in preparation for radix") Reported-by: Christian Zigotzky Signed-off-by: Darren Stevens Reviewed-by: Aneesh Kumar K.V [mpe: Add #ifdef CONFIG_PCI, massage change log slightly] Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/pgtable.h | 1 + arch/powerpc/kernel/pci_64.c | 1 - arch/powerpc/mm/hash_utils_64.c | 4 ++++ arch/powerpc/mm/pgtable-radix.c | 5 +++++ 4 files changed, 10 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 88a5ecaa157b..ab84c89c9e98 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -230,6 +230,7 @@ extern unsigned long __kernel_virt_size; #define KERN_VIRT_SIZE __kernel_virt_size extern struct page *vmemmap; extern unsigned long ioremap_bot; +extern unsigned long pci_io_base; #endif /* __ASSEMBLY__ */ #include diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 3759df52bd67..a5ae49a2dcc4 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -47,7 +47,6 @@ static int __init pcibios_init(void) printk(KERN_INFO "PCI: Probing PCI hardware\n"); - pci_io_base = ISA_IO_BASE; /* For now, override phys_mem_access_prot. If we need it,g * later, we may move that initialization to each ppc_md */ diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 5b22ba0b58bc..2971ea18c768 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -922,6 +922,10 @@ void __init hash__early_init_mmu(void) vmemmap = (struct page *)H_VMEMMAP_BASE; ioremap_bot = IOREMAP_BASE; +#ifdef CONFIG_PCI + pci_io_base = ISA_IO_BASE; +#endif + /* Initialize the MMU Hash table and create the linear mapping * of memory. Has to be done before SLB initialization as this is * currently where the page size encoding is obtained. diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index e58707deef5c..7931e1496f0d 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -328,6 +328,11 @@ void __init radix__early_init_mmu(void) __vmalloc_end = RADIX_VMALLOC_END; vmemmap = (struct page *)RADIX_VMEMMAP_BASE; ioremap_bot = IOREMAP_BASE; + +#ifdef CONFIG_PCI + pci_io_base = ISA_IO_BASE; +#endif + /* * For now radix also use the same frag size */