From cbf74cea070fa1f705de4712e25d9e56ae6543c7 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Mon, 30 May 2011 16:31:11 +0200 Subject: oprofile, x86: Add comments to IBS LVT offset initialization Adding a comment in the code as IBS LVT setup is not obvious at all ... Signed-off-by: Robert Richter --- arch/x86/kernel/apic/apic.c | 3 ++- arch/x86/oprofile/op_model_amd.c | 13 +++++++++---- 2 files changed, 11 insertions(+), 5 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index fabf01eff771..a0bf78a0918c 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -390,7 +390,8 @@ static unsigned int reserve_eilvt_offset(int offset, unsigned int new) /* * If mask=1, the LVT entry does not generate interrupts while mask=0 - * enables the vector. See also the BKDGs. + * enables the vector. See also the BKDGs. Must be called with + * preemption disabled. */ int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask) diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index 9fd8a567fe1e..9cbb710dc94b 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -609,16 +609,21 @@ static int setup_ibs_ctl(int ibs_eilvt_off) return 0; } +/* + * This runs only on the current cpu. We try to find an LVT offset and + * setup the local APIC. For this we must disable preemption. On + * success we initialize all nodes with this offset. This updates then + * the offset in the IBS_CTL per-node msr. The per-core APIC setup of + * the IBS interrupt vector is called from op_amd_setup_ctrs()/op_- + * amd_cpu_shutdown() using the new offset. + */ static int force_ibs_eilvt_setup(void) { int offset; int ret; - /* - * find the next free available EILVT entry, skip offset 0, - * pin search to this cpu - */ preempt_disable(); + /* find the next free available EILVT entry, skip offset 0 */ for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) { if (get_eilvt(offset)) break; -- cgit v1.2.3 From f124c6ae59e193705c9ddac57684d50006d710e6 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 3 Jun 2011 07:45:28 +0300 Subject: xen: off by one errors in multicalls.c b->args[] has MC_ARGS elements, so the comparison here should be ">=" instead of ">". Otherwise we read past the end of the array one space. CC: stable@kernel.org Signed-off-by: Dan Carpenter Signed-off-by: Konrad Rzeszutek Wilk Signed-off-by: Jeremy Fitzhardinge --- arch/x86/xen/multicalls.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c index 8bff7e7c290b..1b2b73ff0a6e 100644 --- a/arch/x86/xen/multicalls.c +++ b/arch/x86/xen/multicalls.c @@ -189,10 +189,10 @@ struct multicall_space __xen_mc_entry(size_t args) unsigned argidx = roundup(b->argidx, sizeof(u64)); BUG_ON(preemptible()); - BUG_ON(b->argidx > MC_ARGS); + BUG_ON(b->argidx >= MC_ARGS); if (b->mcidx == MC_BATCH || - (argidx + args) > MC_ARGS) { + (argidx + args) >= MC_ARGS) { mc_stats_flush(b->mcidx == MC_BATCH ? FL_SLOTS : FL_ARGS); xen_mc_flush(); argidx = roundup(b->argidx, sizeof(u64)); @@ -206,7 +206,7 @@ struct multicall_space __xen_mc_entry(size_t args) ret.args = &b->args[argidx]; b->argidx = argidx + args; - BUG_ON(b->argidx > MC_ARGS); + BUG_ON(b->argidx >= MC_ARGS); return ret; } @@ -216,7 +216,7 @@ struct multicall_space xen_mc_extend_args(unsigned long op, size_t size) struct multicall_space ret = { NULL, NULL }; BUG_ON(preemptible()); - BUG_ON(b->argidx > MC_ARGS); + BUG_ON(b->argidx >= MC_ARGS); if (b->mcidx == 0) return ret; @@ -224,14 +224,14 @@ struct multicall_space xen_mc_extend_args(unsigned long op, size_t size) if (b->entries[b->mcidx - 1].op != op) return ret; - if ((b->argidx + size) > MC_ARGS) + if ((b->argidx + size) >= MC_ARGS) return ret; ret.mc = &b->entries[b->mcidx - 1]; ret.args = &b->args[b->argidx]; b->argidx += size; - BUG_ON(b->argidx > MC_ARGS); + BUG_ON(b->argidx >= MC_ARGS); return ret; } -- cgit v1.2.3 From 221192bdff2583834984639121595fc9296120d3 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Mon, 30 May 2011 15:23:14 -0300 Subject: KVM: x86: use proper port value when checking io instruction permission Commit f6511935f42 moved the permission check for io instructions to the ->check_perm callback. It failed to copy the port value from RDX register for string and "in,out ax,dx" instructions. Fix it by reading RDX register at decode stage when appropriate. Fixes FC8.32 installation. Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/emulate.c | 82 +++++++++++++++++++++++++++++--------------------- 1 file changed, 47 insertions(+), 35 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index d6e2477feb18..6df88c7885c0 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -47,38 +47,40 @@ #define DstDI (5<<1) /* Destination is in ES:(E)DI */ #define DstMem64 (6<<1) /* 64bit memory operand */ #define DstImmUByte (7<<1) /* 8-bit unsigned immediate operand */ -#define DstMask (7<<1) +#define DstDX (8<<1) /* Destination is in DX register */ +#define DstMask (0xf<<1) /* Source operand type. */ -#define SrcNone (0<<4) /* No source operand. */ -#define SrcReg (1<<4) /* Register operand. */ -#define SrcMem (2<<4) /* Memory operand. */ -#define SrcMem16 (3<<4) /* Memory operand (16-bit). */ -#define SrcMem32 (4<<4) /* Memory operand (32-bit). */ -#define SrcImm (5<<4) /* Immediate operand. */ -#define SrcImmByte (6<<4) /* 8-bit sign-extended immediate operand. */ -#define SrcOne (7<<4) /* Implied '1' */ -#define SrcImmUByte (8<<4) /* 8-bit unsigned immediate operand. */ -#define SrcImmU (9<<4) /* Immediate operand, unsigned */ -#define SrcSI (0xa<<4) /* Source is in the DS:RSI */ -#define SrcImmFAddr (0xb<<4) /* Source is immediate far address */ -#define SrcMemFAddr (0xc<<4) /* Source is far address in memory */ -#define SrcAcc (0xd<<4) /* Source Accumulator */ -#define SrcImmU16 (0xe<<4) /* Immediate operand, unsigned, 16 bits */ -#define SrcMask (0xf<<4) +#define SrcNone (0<<5) /* No source operand. */ +#define SrcReg (1<<5) /* Register operand. */ +#define SrcMem (2<<5) /* Memory operand. */ +#define SrcMem16 (3<<5) /* Memory operand (16-bit). */ +#define SrcMem32 (4<<5) /* Memory operand (32-bit). */ +#define SrcImm (5<<5) /* Immediate operand. */ +#define SrcImmByte (6<<5) /* 8-bit sign-extended immediate operand. */ +#define SrcOne (7<<5) /* Implied '1' */ +#define SrcImmUByte (8<<5) /* 8-bit unsigned immediate operand. */ +#define SrcImmU (9<<5) /* Immediate operand, unsigned */ +#define SrcSI (0xa<<5) /* Source is in the DS:RSI */ +#define SrcImmFAddr (0xb<<5) /* Source is immediate far address */ +#define SrcMemFAddr (0xc<<5) /* Source is far address in memory */ +#define SrcAcc (0xd<<5) /* Source Accumulator */ +#define SrcImmU16 (0xe<<5) /* Immediate operand, unsigned, 16 bits */ +#define SrcDX (0xf<<5) /* Source is in DX register */ +#define SrcMask (0xf<<5) /* Generic ModRM decode. */ -#define ModRM (1<<8) +#define ModRM (1<<9) /* Destination is only written; never read. */ -#define Mov (1<<9) -#define BitOp (1<<10) -#define MemAbs (1<<11) /* Memory operand is absolute displacement */ -#define String (1<<12) /* String instruction (rep capable) */ -#define Stack (1<<13) /* Stack instruction (push/pop) */ -#define GroupMask (7<<14) /* Opcode uses one of the group mechanisms */ -#define Group (1<<14) /* Bits 3:5 of modrm byte extend opcode */ -#define GroupDual (2<<14) /* Alternate decoding of mod == 3 */ -#define Prefix (3<<14) /* Instruction varies with 66/f2/f3 prefix */ -#define RMExt (4<<14) /* Opcode extension in ModRM r/m if mod == 3 */ -#define Sse (1<<17) /* SSE Vector instruction */ +#define Mov (1<<10) +#define BitOp (1<<11) +#define MemAbs (1<<12) /* Memory operand is absolute displacement */ +#define String (1<<13) /* String instruction (rep capable) */ +#define Stack (1<<14) /* Stack instruction (push/pop) */ +#define GroupMask (7<<15) /* Opcode uses one of the group mechanisms */ +#define Group (1<<15) /* Bits 3:5 of modrm byte extend opcode */ +#define GroupDual (2<<15) /* Alternate decoding of mod == 3 */ +#define Prefix (3<<15) /* Instruction varies with 66/f2/f3 prefix */ +#define RMExt (4<<15) /* Opcode extension in ModRM r/m if mod == 3 */ +#define Sse (1<<18) /* SSE Vector instruction */ /* Misc flags */ #define Prot (1<<21) /* instruction generates #UD if not in prot-mode */ #define VendorSpecific (1<<22) /* Vendor specific instruction */ @@ -3154,8 +3156,8 @@ static struct opcode opcode_table[256] = { I(DstReg | SrcMem | ModRM | Src2Imm, em_imul_3op), I(SrcImmByte | Mov | Stack, em_push), I(DstReg | SrcMem | ModRM | Src2ImmByte, em_imul_3op), - D2bvIP(DstDI | Mov | String, ins, check_perm_in), /* insb, insw/insd */ - D2bvIP(SrcSI | ImplicitOps | String, outs, check_perm_out), /* outsb, outsw/outsd */ + D2bvIP(DstDI | SrcDX | Mov | String, ins, check_perm_in), /* insb, insw/insd */ + D2bvIP(SrcSI | DstDX | String, outs, check_perm_out), /* outsb, outsw/outsd */ /* 0x70 - 0x7F */ X16(D(SrcImmByte)), /* 0x80 - 0x87 */ @@ -3212,8 +3214,8 @@ static struct opcode opcode_table[256] = { /* 0xE8 - 0xEF */ D(SrcImm | Stack), D(SrcImm | ImplicitOps), D(SrcImmFAddr | No64), D(SrcImmByte | ImplicitOps), - D2bvIP(SrcNone | DstAcc, in, check_perm_in), - D2bvIP(SrcAcc | ImplicitOps, out, check_perm_out), + D2bvIP(SrcDX | DstAcc, in, check_perm_in), + D2bvIP(SrcAcc | DstDX, out, check_perm_out), /* 0xF0 - 0xF7 */ N, DI(ImplicitOps, icebp), N, N, DI(ImplicitOps | Priv, hlt), D(ImplicitOps), @@ -3613,6 +3615,12 @@ done_prefixes: memop.bytes = c->op_bytes + 2; goto srcmem_common; break; + case SrcDX: + c->src.type = OP_REG; + c->src.bytes = 2; + c->src.addr.reg = &c->regs[VCPU_REGS_RDX]; + fetch_register_operand(&c->src); + break; } if (rc != X86EMUL_CONTINUE) @@ -3682,6 +3690,12 @@ done_prefixes: c->dst.addr.mem.seg = VCPU_SREG_ES; c->dst.val = 0; break; + case DstDX: + c->dst.type = OP_REG; + c->dst.bytes = 2; + c->dst.addr.reg = &c->regs[VCPU_REGS_RDX]; + fetch_register_operand(&c->dst); + break; case ImplicitOps: /* Special instructions do their own operand decoding. */ default: @@ -4027,7 +4041,6 @@ special_insn: break; case 0xec: /* in al,dx */ case 0xed: /* in (e/r)ax,dx */ - c->src.val = c->regs[VCPU_REGS_RDX]; do_io_in: if (!pio_in_emulated(ctxt, ops, c->dst.bytes, c->src.val, &c->dst.val)) @@ -4035,7 +4048,6 @@ special_insn: break; case 0xee: /* out dx,al */ case 0xef: /* out dx,(e/r)ax */ - c->dst.val = c->regs[VCPU_REGS_RDX]; do_io_out: ops->pio_out_emulated(ctxt, c->src.bytes, c->dst.val, &c->src.val, 1); -- cgit v1.2.3 From 0de66d5b35ee148455e268b2782873204ffdef4b Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 6 Jun 2011 16:04:02 +0200 Subject: x86/amd-iommu: Fix 3 possible endless loops The driver contains several loops counting on an u16 value where the exit-condition is checked against variables that can have values up to 0xffff. In this case the loops will never exit. This patch fixed 3 such loops. Cc: stable@kernel.org Signed-off-by: Joerg Roedel --- arch/x86/kernel/amd_iommu_init.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 9179c21120a8..bfc8453bd98d 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -731,8 +731,8 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu, { u8 *p = (u8 *)h; u8 *end = p, flags = 0; - u16 dev_i, devid = 0, devid_start = 0, devid_to = 0; - u32 ext_flags = 0; + u16 devid = 0, devid_start = 0, devid_to = 0; + u32 dev_i, ext_flags = 0; bool alias = false; struct ivhd_entry *e; @@ -887,7 +887,7 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu, /* Initializes the device->iommu mapping for the driver */ static int __init init_iommu_devices(struct amd_iommu *iommu) { - u16 i; + u32 i; for (i = iommu->first_device; i <= iommu->last_device; ++i) set_iommu_for_device(iommu, i); @@ -1177,7 +1177,7 @@ static int __init init_memory_definitions(struct acpi_table_header *table) */ static void init_device_table(void) { - u16 devid; + u32 devid; for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) { set_dev_entry_bit(devid, DEV_ENTRY_VALID); -- cgit v1.2.3 From 27c2127a15d340706c0aa84e311188a14468d841 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 30 May 2011 15:56:24 +0200 Subject: x86/amd-iommu: Use only per-device dma_ops Unfortunatly there are systems where the AMD IOMMU does not cover all devices. This breaks with the current driver as it initializes the global dma_ops variable. This patch limits the AMD IOMMU to the devices listed in the IVRS table fixing DMA for devices not covered by the IOMMU. Cc: stable@kernel.org Signed-off-by: Joerg Roedel --- arch/x86/kernel/amd_iommu.c | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index cd8cbeb5fa34..b2c309b07427 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include @@ -2383,6 +2384,23 @@ static struct dma_map_ops amd_iommu_dma_ops = { .dma_supported = amd_iommu_dma_supported, }; +static unsigned device_dma_ops_init(void) +{ + struct pci_dev *pdev = NULL; + unsigned unhandled = 0; + + for_each_pci_dev(pdev) { + if (!check_device(&pdev->dev)) { + unhandled += 1; + continue; + } + + pdev->dev.archdata.dma_ops = &amd_iommu_dma_ops; + } + + return unhandled; +} + /* * The function which clues the AMD IOMMU driver into dma_ops. */ @@ -2395,7 +2413,7 @@ void __init amd_iommu_init_api(void) int __init amd_iommu_init_dma_ops(void) { struct amd_iommu *iommu; - int ret; + int ret, unhandled; /* * first allocate a default protection domain for every IOMMU we @@ -2421,7 +2439,11 @@ int __init amd_iommu_init_dma_ops(void) swiotlb = 0; /* Make the driver finally visible to the drivers */ - dma_ops = &amd_iommu_dma_ops; + unhandled = device_dma_ops_init(); + if (unhandled && max_pfn > MAX_DMA32_PFN) { + /* There are unhandled devices - initialize swiotlb for them */ + swiotlb = 1; + } amd_iommu_stats_init(); -- cgit v1.2.3 From 26018874e3584f1658570d41d57d4c34f6a53aa0 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 6 Jun 2011 16:50:14 +0200 Subject: x86/amd-iommu: Fix boot crash with hidden PCI devices Some PCIe cards ship with a PCI-PCIe bridge which is not visible as a PCI device in Linux. But the device-id of the bridge is present in the IOMMU tables which causes a boot crash in the IOMMU driver. This patch fixes by removing these cards from the IOMMU handling. This is a pure -stable fix, a real fix to handle this situation appriatly will follow for the next merge window. Cc: stable@kernel.org # > 2.6.32 Signed-off-by: Joerg Roedel --- arch/x86/kernel/amd_iommu.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index b2c309b07427..7c3a95e54ec5 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -155,6 +155,10 @@ static int iommu_init_device(struct device *dev) pdev = pci_get_bus_and_slot(PCI_BUS(alias), alias & 0xff); if (pdev) dev_data->alias = &pdev->dev; + else { + kfree(dev_data); + return -ENOTSUPP; + } atomic_set(&dev_data->bind, 0); @@ -164,6 +168,20 @@ static int iommu_init_device(struct device *dev) return 0; } +static void iommu_ignore_device(struct device *dev) +{ + u16 devid, alias; + + devid = get_device_id(dev); + alias = amd_iommu_alias_table[devid]; + + memset(&amd_iommu_dev_table[devid], 0, sizeof(struct dev_table_entry)); + memset(&amd_iommu_dev_table[alias], 0, sizeof(struct dev_table_entry)); + + amd_iommu_rlookup_table[devid] = NULL; + amd_iommu_rlookup_table[alias] = NULL; +} + static void iommu_uninit_device(struct device *dev) { kfree(dev->archdata.iommu); @@ -193,7 +211,9 @@ int __init amd_iommu_init_devices(void) continue; ret = iommu_init_device(&pdev->dev); - if (ret) + if (ret == -ENOTSUPP) + iommu_ignore_device(&pdev->dev); + else if (ret) goto out_free; } -- cgit v1.2.3 From fd8a7de177b6f56a0fc59ad211c197a7df06b1ad Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 20 Jul 2010 14:34:50 +0200 Subject: x86: cpu-hotplug: Prevent softirq wakeup on wrong CPU After a newly plugged CPU sets the cpu_online bit it enables interrupts and goes idle. The cpu which brought up the new cpu waits for the cpu_online bit and when it observes it, it sets the cpu_active bit for this cpu. The cpu_active bit is the relevant one for the scheduler to consider the cpu as a viable target. With forced threaded interrupt handlers which imply forced threaded softirqs we observed the following race: cpu 0 cpu 1 bringup(cpu1); set_cpu_online(smp_processor_id(), true); local_irq_enable(); while (!cpu_online(cpu1)); timer_interrupt() -> wake_up(softirq_thread_cpu1); -> enqueue_on(softirq_thread_cpu1, cpu0); ^^^^ cpu_notify(CPU_ONLINE, cpu1); -> sched_cpu_active(cpu1) -> set_cpu_active((cpu1, true); When an interrupt happens before the cpu_active bit is set by the cpu which brought up the newly onlined cpu, then the scheduler refuses to enqueue the woken thread which is bound to that newly onlined cpu on that newly onlined cpu due to the not yet set cpu_active bit and selects a fallback runqueue. Not really an expected and desirable behaviour. So far this has only been observed with forced hard/softirq threading, but in theory this could happen without forced threaded hard/softirqs as well. It's probably unobservable as it would take a massive interrupt storm on the newly onlined cpu which causes the softirq loop to wake up the softirq thread and an even longer delay of the cpu which waits for the cpu_online bit. Signed-off-by: Thomas Gleixner Reviewed-by: Peter Zijlstra Cc: stable@kernel.org # 2.6.39 --- arch/x86/kernel/smpboot.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 33a0c11797de..9fd3137230d4 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -285,6 +285,19 @@ notrace static void __cpuinit start_secondary(void *unused) per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; x86_platform.nmi_init(); + /* + * Wait until the cpu which brought this one up marked it + * online before enabling interrupts. If we don't do that then + * we can end up waking up the softirq thread before this cpu + * reached the active state, which makes the scheduler unhappy + * and schedule the softirq thread on the wrong cpu. This is + * only observable with forced threaded interrupts, but in + * theory it could also happen w/o them. It's just way harder + * to achieve. + */ + while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask)) + cpu_relax(); + /* enable local interrupts */ local_irq_enable(); -- cgit v1.2.3 From 977cb76d52e7aa040e18a84b29fe6fd80d79319b Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 6 Jun 2011 10:15:49 +0200 Subject: x86: devicetree: Add missing early_init_dt_setup_initrd_arch stub This patch fixes the following build failure: drivers/built-in.o: In function `early_init_dt_check_for_initrd': /home/florian/dev/kernel/x86/linux-2.6-x86/drivers/of/fdt.c:571: undefined reference to `early_init_dt_setup_initrd_arch' make: *** [.tmp_vmlinux1] Error 1 which happens as soon as we enable initrd support on a x86 devicetree platform such as Intel CE4100. Signed-off-by: Florian Fainelli Acked-by: Grant Likely Cc: Maxime Bizon Acked-by: Sebastian Andrzej Siewior Cc: stable@kernel.org # 2.6.39 Link: http://lkml.kernel.org/r/201106061015.50039.ffainelli@freebox.fr Signed-off-by: Thomas Gleixner --- arch/x86/kernel/devicetree.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 690bc8461835..9aeb78a23de4 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -98,6 +99,16 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS)); } +#ifdef CONFIG_BLK_DEV_INITRD +void __init early_init_dt_setup_initrd_arch(unsigned long start, + unsigned long end) +{ + initrd_start = (unsigned long)__va(start); + initrd_end = (unsigned long)__va(end); + initrd_below_start_ok = 1; +} +#endif + void __init add_dtb(u64 data) { initial_dtb = data + offsetof(struct setup_data, data); -- cgit v1.2.3 From dac853ae89043f1b7752875300faf614de43c74b Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Thu, 9 Jun 2011 20:05:18 +0200 Subject: exec: delay address limit change until point of no return Unconditionally changing the address limit to USER_DS and not restoring it to its old value in the error path is wrong because it prevents us using kernel memory on repeated calls to this function. This, in fact, breaks the fallback of hard coded paths to the init program from being ever successful if the first candidate fails to load. With this patch applied switching to USER_DS is delayed until the point of no return is reached which makes it possible to have a multi-arch rootfs with one arch specific init binary for each of the (hard coded) probed paths. Since the address limit is already set to USER_DS when start_thread() will be invoked, this redundancy can be safely removed. Signed-off-by: Mathias Krause Cc: Al Viro Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- arch/x86/kernel/process_32.c | 1 - arch/x86/kernel/process_64.c | 1 - 2 files changed, 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 8d128783af47..a3d0dc59067b 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -245,7 +245,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) { set_user_gs(regs, 0); regs->fs = 0; - set_fs(USER_DS); regs->ds = __USER_DS; regs->es = __USER_DS; regs->ss = __USER_DS; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 6c9dd922ac0d..ca6f7ab8df33 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -338,7 +338,6 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, regs->cs = _cs; regs->ss = _ss; regs->flags = X86_EFLAGS_IF; - set_fs(USER_DS); /* * Free the old FP and other extended state */ -- cgit v1.2.3