From 28ea3c7529388c1e4177336a0e655c6c7272fd1c Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Sun, 27 Apr 2014 18:10:43 -0400 Subject: [PATCH 01/33] powerpc: Export flush_icache_range Commit aac416fc38c (lkdtm: flush icache and report actions) calls flush_icache_range from a module. It's exported on most architectures that implement it, but not on powerpc. This patch exports it to fix the module link failure. Signed-off-by: Jeff Mahoney Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/ppc_ksyms.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 3bd77edd7610..450850a49dce 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -120,6 +120,7 @@ EXPORT_SYMBOL(giveup_spe); EXPORT_SYMBOL(flush_instruction_cache); #endif EXPORT_SYMBOL(flush_dcache_range); +EXPORT_SYMBOL(flush_icache_range); #ifdef CONFIG_SMP #ifdef CONFIG_PPC32 From 4fb8d027dca0236c811272d342cf185569d91311 Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Mon, 28 Apr 2014 08:29:51 +0800 Subject: [PATCH 02/33] powerpc: Fix Oops in rtas_stop_self() commit 41dd03a9 may cause Oops in rtas_stop_self(). The reason is that the rtas_args was moved into stack space. For a box with more that 4GB RAM, the stack could easily be outside 32bit range, but RTAS is 32bit. So the patch moves rtas_args away from stack by adding static before it. Signed-off-by: Li Zhong Signed-off-by: Anton Blanchard Cc: stable@vger.kernel.org # 3.14+ Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/hotplug-cpu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 9b8e05078a63..20d62975856f 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -88,13 +88,14 @@ void set_default_offline_state(int cpu) static void rtas_stop_self(void) { - struct rtas_args args = { - .token = cpu_to_be32(rtas_stop_self_token), + static struct rtas_args args = { .nargs = 0, .nret = 1, .rets = &args.args[0], }; + args.token = cpu_to_be32(rtas_stop_self_token); + local_irq_disable(); BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE); From ba9a32b176c31ec4d3d7314bb2e529a85423f7a4 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Thu, 24 Apr 2014 16:55:33 +0930 Subject: [PATCH 03/33] powerpc/powernv: Fix sysparam sysfs error handling When a sysparam query in OPAL returned a negative value (error code), sysfs would spew out a decent chunk of memory; almost 64K more than expected. This was traced to a sign/unsigned mix up in the OPAL sysparam sysfs code at sys_param_show. The return value of sys_param_show is a ssize_t, calculated using return ret ? ret : attr->param_size; Alan Modra explains: "attr->param_size" is an unsigned int, "ret" an int, so the overall expression has type unsigned int. Result is that ret is cast to unsigned int before being cast to ssize_t. Instead of using the ternary operator, set ret to the param_size if an error is not detected. The same bug exists in the sysfs write callback; this patch fixes it in the same way. A note on debugging this next time: on my system gcc will warn about this if compiled with -Wsign-compare, which is not enabled by -Wall, only -Wextra. Signed-off-by: Joel Stanley Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal-sysparam.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c index 6b614726baf2..a51ea189aec3 100644 --- a/arch/powerpc/platforms/powernv/opal-sysparam.c +++ b/arch/powerpc/platforms/powernv/opal-sysparam.c @@ -121,9 +121,10 @@ static ssize_t sys_param_show(struct kobject *kobj, memcpy(buf, param_data_buf, attr->param_size); + ret = attr->param_size; out: mutex_unlock(&opal_sysparam_mutex); - return ret ? ret : attr->param_size; + return ret; } static ssize_t sys_param_store(struct kobject *kobj, @@ -138,7 +139,9 @@ static ssize_t sys_param_store(struct kobject *kobj, ret = opal_set_sys_param(attr->param_id, attr->param_size, param_data_buf); mutex_unlock(&opal_sysparam_mutex); - return ret ? ret : count; + if (!ret) + ret = count; + return ret; } void __init opal_sys_param_init(void) From b8569d230416c490065098684adf13c1751cb830 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Thu, 24 Apr 2014 16:55:34 +0930 Subject: [PATCH 04/33] powerpc/powernv: Use ssize_t for sysparam return values The OPAL calls are returning int64_t values, which the sysparam code stores in an int, and the sysfs callback returns ssize_t. Make code a easier to read by consistently using ssize_t. Signed-off-by: Joel Stanley Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal-sysparam.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c index a51ea189aec3..0675e1a90b40 100644 --- a/arch/powerpc/platforms/powernv/opal-sysparam.c +++ b/arch/powerpc/platforms/powernv/opal-sysparam.c @@ -39,10 +39,11 @@ struct param_attr { struct kobj_attribute kobj_attr; }; -static int opal_get_sys_param(u32 param_id, u32 length, void *buffer) +static ssize_t opal_get_sys_param(u32 param_id, u32 length, void *buffer) { struct opal_msg msg; - int ret, token; + ssize_t ret; + int token; token = opal_async_get_token_interruptible(); if (token < 0) { @@ -59,7 +60,7 @@ static int opal_get_sys_param(u32 param_id, u32 length, void *buffer) ret = opal_async_wait_response(token, &msg); if (ret) { - pr_err("%s: Failed to wait for the async response, %d\n", + pr_err("%s: Failed to wait for the async response, %zd\n", __func__, ret); goto out_token; } @@ -111,7 +112,7 @@ static ssize_t sys_param_show(struct kobject *kobj, { struct param_attr *attr = container_of(kobj_attr, struct param_attr, kobj_attr); - int ret; + ssize_t ret; mutex_lock(&opal_sysparam_mutex); ret = opal_get_sys_param(attr->param_id, attr->param_size, @@ -132,7 +133,7 @@ static ssize_t sys_param_store(struct kobject *kobj, { struct param_attr *attr = container_of(kobj_attr, struct param_attr, kobj_attr); - int ret; + ssize_t ret; mutex_lock(&opal_sysparam_mutex); memcpy(param_data_buf, buf, count); From 85390378f0a6abf3bdb10c3d504d77862a2d0ec9 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Thu, 24 Apr 2014 16:55:35 +0930 Subject: [PATCH 05/33] powerpc/powernv: Check sysfs size before copying The sysparam code currently uses the userspace supplied number of bytes when memcpy()ing in to a local 64-byte buffer. Limit the maximum number of bytes by the size of the buffer. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal-sysparam.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c index 0675e1a90b40..83f5f2a1c563 100644 --- a/arch/powerpc/platforms/powernv/opal-sysparam.c +++ b/arch/powerpc/platforms/powernv/opal-sysparam.c @@ -135,6 +135,10 @@ static ssize_t sys_param_store(struct kobject *kobj, kobj_attr); ssize_t ret; + /* MAX_PARAM_DATA_LEN is sizeof(param_data_buf) */ + if (count > MAX_PARAM_DATA_LEN) + count = MAX_PARAM_DATA_LEN; + mutex_lock(&opal_sysparam_mutex); memcpy(param_data_buf, buf, count); ret = opal_set_sys_param(attr->param_id, attr->param_size, From 16003d235bdb4d1ebcecfe4915c6e6d8c95f4a0c Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Thu, 24 Apr 2014 16:55:36 +0930 Subject: [PATCH 06/33] powerpc/powernv: Fix typos in sysparam code Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal-sysparam.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c index 83f5f2a1c563..c59e77a84721 100644 --- a/arch/powerpc/platforms/powernv/opal-sysparam.c +++ b/arch/powerpc/platforms/powernv/opal-sysparam.c @@ -222,13 +222,13 @@ void __init opal_sys_param_init(void) } if (of_property_read_u32_array(sysparam, "param-len", size, count)) { - pr_err("SYSPARAM: Missing propery param-len in the DT\n"); + pr_err("SYSPARAM: Missing property param-len in the DT\n"); goto out_free_perm; } if (of_property_read_u8_array(sysparam, "param-perm", perm, count)) { - pr_err("SYSPARAM: Missing propery param-perm in the DT\n"); + pr_err("SYSPARAM: Missing property param-perm in the DT\n"); goto out_free_perm; } From 63aecfb20a6629f1ca91d7a052f87988ceb6dd53 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Thu, 24 Apr 2014 16:55:37 +0930 Subject: [PATCH 07/33] powerpc/powernv: Check sysparam size before creation The size of the sysparam sysfs files is determined from the device tree at boot. However the buffer is hard coded to 64 bytes. If we encounter a parameter that is larger than 64, or miss-parse the device tree, the buffer will overflow when reading or writing to the parameter. Check it at discovery time, and if the parameter is too large, do not create a sysfs entry for it. Signed-off-by: Joel Stanley Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal-sysparam.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c index c59e77a84721..d202f9bc3683 100644 --- a/arch/powerpc/platforms/powernv/opal-sysparam.c +++ b/arch/powerpc/platforms/powernv/opal-sysparam.c @@ -241,6 +241,12 @@ void __init opal_sys_param_init(void) /* For each of the parameters, populate the parameter attributes */ for (i = 0; i < count; i++) { + if (size[i] > MAX_PARAM_DATA_LEN) { + pr_warn("SYSPARAM: Not creating parameter %d as size " + "exceeds buffer length\n", i); + continue; + } + sysfs_attr_init(&attr[i].kobj_attr.attr); attr[i].param_id = id[i]; attr[i].param_size = size[i]; From 298b34d7d578c3b4325248b823f3d83a8ea1541c Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 24 Apr 2014 16:14:25 +1000 Subject: [PATCH 08/33] powerpc/powernv: Fix kexec races going back to OPAL We have a subtle race when sending CPUs back to OPAL on kexec. We mark them as "in real mode" right before we send them down. Once we've booted the new kernel, it might try to call opal_reinit_cpus() to change endianness, and that requires all CPUs to be spinning inside OPAL. However there is no synchronization here and we've observed cases where the returning CPUs hadn't established their new state inside OPAL before opal_reinit_cpus() is called, causing it to fail. The proper fix is to actually wait for them to go down all the way from the kexec'ing kernel. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/setup.c | 48 ++++++++++++++++++++++++-- 1 file changed, 46 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 61cf8fa9c61b..8723d32632f5 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -162,18 +162,62 @@ static void pnv_shutdown(void) } #ifdef CONFIG_KEXEC +static void pnv_kexec_wait_secondaries_down(void) +{ + int my_cpu, i, notified = -1; + + my_cpu = get_cpu(); + + for_each_online_cpu(i) { + uint8_t status; + int64_t rc; + + if (i == my_cpu) + continue; + + for (;;) { + rc = opal_query_cpu_status(get_hard_smp_processor_id(i), + &status); + if (rc != OPAL_SUCCESS || status != OPAL_THREAD_STARTED) + break; + barrier(); + if (i != notified) { + printk(KERN_INFO "kexec: waiting for cpu %d " + "(physical %d) to enter OPAL\n", + i, paca[i].hw_cpu_id); + notified = i; + } + } + } +} + static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) { xics_kexec_teardown_cpu(secondary); - /* Return secondary CPUs to firmware on OPAL v3 */ - if (firmware_has_feature(FW_FEATURE_OPALv3) && secondary) { + /* On OPAL v3, we return all CPUs to firmware */ + + if (!firmware_has_feature(FW_FEATURE_OPALv3)) + return; + + if (secondary) { + /* Return secondary CPUs to firmware on OPAL v3 */ mb(); get_paca()->kexec_state = KEXEC_STATE_REAL_MODE; mb(); /* Return the CPU to OPAL */ opal_return_cpu(); + } else if (crash_shutdown) { + /* + * On crash, we don't wait for secondaries to go + * down as they might be unreachable or hung, so + * instead we just wait a bit and move on. + */ + mdelay(1); + } else { + /* Primary waits for the secondaries to have reached OPAL */ + pnv_kexec_wait_secondaries_down(); } } #endif /* CONFIG_KEXEC */ From cc146d1db0673396429ce4f906350d684ef4ca2a Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Thu, 24 Apr 2014 07:25:34 +1000 Subject: [PATCH 09/33] powerpc/powernv: Fix little endian issues in OPAL flash code With this patch I was able to update firmware on an LE kernel. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal-flash.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c index 714ef972406b..a968fd1888b3 100644 --- a/arch/powerpc/platforms/powernv/opal-flash.c +++ b/arch/powerpc/platforms/powernv/opal-flash.c @@ -131,11 +131,15 @@ static DEFINE_MUTEX(image_data_mutex); */ static inline void opal_flash_validate(void) { - struct validate_flash_t *args_buf = &validate_flash_data; + long ret; + void *buf = validate_flash_data.buf; + __be32 size, result; - args_buf->status = opal_validate_flash(__pa(args_buf->buf), - &(args_buf->buf_size), - &(args_buf->result)); + ret = opal_validate_flash(__pa(buf), &size, &result); + + validate_flash_data.status = ret; + validate_flash_data.buf_size = be32_to_cpu(size); + validate_flash_data.result = be32_to_cpu(result); } /* From 3f28c5af3964c11e61e9a58df77cae5ebdb8209e Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 23 Apr 2014 10:26:32 +0800 Subject: [PATCH 10/33] powerpc/powernv: Reduce multi-hit of iommu_add_device() During the EEH hotplug event, iommu_add_device() will be invoked three times and two of them will trigger warning or error. The three times to invoke the iommu_add_device() are: pci_device_add ... set_iommu_table_base_and_group <- 1st time, fail device_add ... tce_iommu_bus_notifier <- 2nd time, succees pcibios_add_pci_devices ... pcibios_setup_bus_devices <- 3rd time, re-attach The first time fails, since the dev->kobj->sd is not initialized. The dev->kobj->sd is initialized in device_add(). The third time's warning is triggered by the re-attach of the iommu_group. After applying this patch, the error iommu_tce: 0003:05:00.0 has not been added, ret=-14 and the warning [ 204.123609] ------------[ cut here ]------------ [ 204.123645] WARNING: at arch/powerpc/kernel/iommu.c:1125 [ 204.123680] Modules linked in: xt_CHECKSUM nf_conntrack_netbios_ns nf_conntrack_broadcast ipt_MASQUERADE ip6t_REJECT bnep bluetooth 6lowpan_iphc rfkill xt_conntrack ebtable_nat ebtable_broute bridge stp llc mlx4_ib ib_sa ib_mad ib_core ib_addr ebtable_filter ebtables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw ip6table_filter ip6_tables iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw bnx2x tg3 mlx4_core nfsd ptp mdio ses libcrc32c nfs_acl enclosure be2net pps_core shpchp lockd kvm uinput sunrpc binfmt_misc lpfc scsi_transport_fc ipr scsi_tgt [ 204.124356] CPU: 18 PID: 650 Comm: eehd Not tainted 3.14.0-rc5yw+ #102 [ 204.124400] task: c0000027ed485670 ti: c0000027ed50c000 task.ti: c0000027ed50c000 [ 204.124453] NIP: c00000000003cf80 LR: c00000000006c648 CTR: c00000000006c5c0 [ 204.124506] REGS: c0000027ed50f440 TRAP: 0700 Not tainted (3.14.0-rc5yw+) [ 204.124558] MSR: 9000000000029032 CR: 88008084 XER: 20000000 [ 204.124682] CFAR: c00000000006c644 SOFTE: 1 GPR00: c00000000006c648 c0000027ed50f6c0 c000000001398380 c0000027ec260300 GPR04: c0000027ea92c000 c00000000006ad00 c0000000016e41b0 0000000000000110 GPR08: c0000000012cd4c0 0000000000000001 c0000027ec2602ff 0000000000000062 GPR12: 0000000028008084 c00000000fdca200 c0000000000d1d90 c0000027ec281a80 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000000000000 0000000000000000 0000000000000000 0000000000000001 GPR24: 000000005342697b 0000000000002906 c000001fe6ac9800 c000001fe6ac9800 GPR28: 0000000000000000 c0000000016e3a80 c0000027ea92c090 c0000027ea92c000 [ 204.125353] NIP [c00000000003cf80] .iommu_add_device+0x30/0x1f0 [ 204.125399] LR [c00000000006c648] .pnv_pci_ioda_dma_dev_setup+0x88/0xb0 [ 204.125443] Call Trace: [ 204.125464] [c0000027ed50f6c0] [c0000027ed50f750] 0xc0000027ed50f750 (unreliable) [ 204.125526] [c0000027ed50f750] [c00000000006c648] .pnv_pci_ioda_dma_dev_setup+0x88/0xb0 [ 204.125588] [c0000027ed50f7d0] [c000000000069cc8] .pnv_pci_dma_dev_setup+0x78/0x340 [ 204.125650] [c0000027ed50f870] [c000000000044408] .pcibios_setup_device+0x88/0x2f0 [ 204.125712] [c0000027ed50f940] [c000000000046040] .pcibios_setup_bus_devices+0x60/0xd0 [ 204.125774] [c0000027ed50f9c0] [c000000000043acc] .pcibios_add_pci_devices+0xdc/0x1c0 [ 204.125837] [c0000027ed50fa50] [c00000000086f970] .eeh_reset_device+0x36c/0x4f0 [ 204.125939] [c0000027ed50fb20] [c00000000003a2d8] .eeh_handle_normal_event+0x448/0x480 [ 204.126068] [c0000027ed50fbc0] [c00000000003a35c] .eeh_handle_event+0x4c/0x340 [ 204.126192] [c0000027ed50fc80] [c00000000003a74c] .eeh_event_handler+0xfc/0x1b0 [ 204.126319] [c0000027ed50fd30] [c0000000000d1ea0] .kthread+0x110/0x130 [ 204.126430] [c0000027ed50fe30] [c00000000000a460] .ret_from_kernel_thread+0x5c/0x7c [ 204.126556] Instruction dump: [ 204.126610] 7c0802a6 fba1ffe8 fbc1fff0 fbe1fff8 f8010010 f821ff71 7c7e1b78 60000000 [ 204.126787] 60000000 e87e0298 3143ffff 7d2a1910 <0b090000> 2fa90000 40de00c8 ebfe0218 [ 204.126966] ---[ end trace 6e7aefd80add2973 ]--- are cleared. This patch removes iommu_add_device() in pnv_pci_ioda_dma_dev_setup(), which revert part of the change in commit d905c5df(PPC: POWERNV: move iommu_add_device earlier). Signed-off-by: Wei Yang Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/pci-ioda.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 3b2b4fb3585b..1d992f137c48 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -462,7 +462,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev pe = &phb->ioda.pe_array[pdn->pe_number]; WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops); - set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table); + set_iommu_table_base(&pdev->dev, &pe->tce32_table); } static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb, From 4966bfa1b3347ee75e6d93859a2e8ce9a662390c Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 23 Apr 2014 10:26:33 +0800 Subject: [PATCH 11/33] powerpc/powernv: Release the refcount for pci_dev On PowerNV platform, we are holding an unnecessary refcount on a pci_dev, which leads to the pci_dev is not destroyed when hotplugging a pci device. This patch release the unnecessary refcount. Signed-off-by: Wei Yang Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/pci-ioda.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 1d992f137c48..98824aa99173 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -343,7 +343,6 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe) pci_name(dev)); continue; } - pci_dev_get(dev); pdn->pcidev = dev; pdn->pe_number = pe->pe_number; pe->dma_weight += pnv_ioda_dma_weight(dev); From 2bad742388d23c15f2cb355bb992046e30065a11 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 22 Apr 2014 15:01:22 +1000 Subject: [PATCH 12/33] powerpc/powernv: Use uint64_t instead of size_t in OPAL APIs Using size_t in our APIs is asking for trouble, especially when some OPAL calls use size_t pointers. Signed-off-by: Anton Blanchard Reviewed-by: Stewart Smith Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 12 ++++++------ arch/powerpc/platforms/powernv/opal-elog.c | 2 +- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index a2efdaa020b0..2a34485f7e0a 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -858,8 +858,8 @@ int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type, int64_t opal_lpc_read(uint32_t chip_id, enum OpalLPCAddressType addr_type, uint32_t addr, __be32 *data, uint32_t sz); -int64_t opal_read_elog(uint64_t buffer, size_t size, uint64_t log_id); -int64_t opal_get_elog_size(uint64_t *log_id, size_t *size, uint64_t *elog_type); +int64_t opal_read_elog(uint64_t buffer, uint64_t size, uint64_t log_id); +int64_t opal_get_elog_size(uint64_t *log_id, uint64_t *size, uint64_t *elog_type); int64_t opal_write_elog(uint64_t buffer, uint64_t size, uint64_t offset); int64_t opal_send_ack_elog(uint64_t log_id); void opal_resend_pending_logs(void); @@ -874,13 +874,13 @@ int64_t opal_dump_read(uint32_t dump_id, uint64_t buffer); int64_t opal_dump_ack(uint32_t dump_id); int64_t opal_dump_resend_notification(void); -int64_t opal_get_msg(uint64_t buffer, size_t size); -int64_t opal_check_completion(uint64_t buffer, size_t size, uint64_t token); +int64_t opal_get_msg(uint64_t buffer, uint64_t size); +int64_t opal_check_completion(uint64_t buffer, uint64_t size, uint64_t token); int64_t opal_sync_host_reboot(void); int64_t opal_get_param(uint64_t token, uint32_t param_id, uint64_t buffer, - size_t length); + uint64_t length); int64_t opal_set_param(uint64_t token, uint32_t param_id, uint64_t buffer, - size_t length); + uint64_t length); int64_t opal_sensor_read(uint32_t sensor_hndl, int token, __be32 *sensor_data); /* Internal functions */ diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index ef7bc2a97862..7e3821e611a8 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -238,7 +238,7 @@ static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) static void elog_work_fn(struct work_struct *work) { - size_t elog_size; + uint64_t elog_size; uint64_t log_id; uint64_t elog_type; int rc; From e2c8b93e65935498d9bd419cec900221ace70c5b Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 22 Apr 2014 15:01:23 +1000 Subject: [PATCH 13/33] powerpc/powernv: Remove some OPAL function declaration duplication We had some duplication of the internal OPAL functions. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 2a34485f7e0a..cb7d52ed86d2 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -884,7 +884,8 @@ int64_t opal_set_param(uint64_t token, uint32_t param_id, uint64_t buffer, int64_t opal_sensor_read(uint32_t sensor_hndl, int token, __be32 *sensor_data); /* Internal functions */ -extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data); +extern int early_init_dt_scan_opal(unsigned long node, const char *uname, + int depth, void *data); extern int early_init_dt_scan_recoverable_ranges(unsigned long node, const char *uname, int depth, void *data); @@ -893,10 +894,6 @@ extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len); extern void hvc_opal_init_early(void); -/* Internal functions */ -extern int early_init_dt_scan_opal(unsigned long node, const char *uname, - int depth, void *data); - extern int opal_notifier_register(struct notifier_block *nb); extern int opal_notifier_unregister(struct notifier_block *nb); @@ -906,9 +903,6 @@ extern void opal_notifier_enable(void); extern void opal_notifier_disable(void); extern void opal_notifier_update_evt(uint64_t evt_mask, uint64_t evt_val); -extern int opal_get_chars(uint32_t vtermno, char *buf, int count); -extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len); - extern int __opal_async_get_token(void); extern int opal_async_get_token_interruptible(void); extern int __opal_async_release_token(int token); @@ -916,8 +910,6 @@ extern int opal_async_release_token(int token); extern int opal_async_wait_response(uint64_t token, struct opal_msg *msg); extern int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data); -extern void hvc_opal_init_early(void); - struct rtc_time; extern int opal_set_rtc_time(struct rtc_time *tm); extern void opal_get_rtc_time(struct rtc_time *tm); From 56b4c993124d15f3b198cc757ba49a0022b5d695 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 22 Apr 2014 15:01:24 +1000 Subject: [PATCH 14/33] powerpc/powernv: Fix little endian issues with opal_do_notifier calls The bitmap in opal_poll_events and opal_handle_interrupt is big endian, so we need to byteswap it on little endian builds. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/opal.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 49d2f00019e5..17cfc70082aa 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -242,14 +242,14 @@ void opal_notifier_update_evt(uint64_t evt_mask, void opal_notifier_enable(void) { int64_t rc; - uint64_t evt = 0; + __be64 evt = 0; atomic_set(&opal_notifier_hold, 0); /* Process pending events */ rc = opal_poll_events(&evt); if (rc == OPAL_SUCCESS && evt) - opal_do_notifier(evt); + opal_do_notifier(be64_to_cpu(evt)); } void opal_notifier_disable(void) @@ -529,7 +529,7 @@ static irqreturn_t opal_interrupt(int irq, void *data) opal_handle_interrupt(virq_to_hw(irq), &events); - opal_do_notifier(events); + opal_do_notifier(be64_to_cpu(events)); return IRQ_HANDLED; } From 14ad0c58d5df6e5911a5413abdc2a9be6a8acb51 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 22 Apr 2014 15:01:25 +1000 Subject: [PATCH 15/33] powerpc/powernv: Fix little endian issues in OPAL error log code Fix little endian issues with the OPAL error log code. Signed-off-by: Anton Blanchard Reviewed-by: Stewart Smith Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 2 +- arch/powerpc/platforms/powernv/opal-elog.c | 9 ++++++++- 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index cb7d52ed86d2..1a752ac8c0ba 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -859,7 +859,7 @@ int64_t opal_lpc_read(uint32_t chip_id, enum OpalLPCAddressType addr_type, uint32_t addr, __be32 *data, uint32_t sz); int64_t opal_read_elog(uint64_t buffer, uint64_t size, uint64_t log_id); -int64_t opal_get_elog_size(uint64_t *log_id, uint64_t *size, uint64_t *elog_type); +int64_t opal_get_elog_size(__be64 *log_id, __be64 *size, __be64 *elog_type); int64_t opal_write_elog(uint64_t buffer, uint64_t size, uint64_t offset); int64_t opal_send_ack_elog(uint64_t log_id); void opal_resend_pending_logs(void); diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index 7e3821e611a8..10268c41d830 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -238,18 +238,25 @@ static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) static void elog_work_fn(struct work_struct *work) { + __be64 size; + __be64 id; + __be64 type; uint64_t elog_size; uint64_t log_id; uint64_t elog_type; int rc; char name[2+16+1]; - rc = opal_get_elog_size(&log_id, &elog_size, &elog_type); + rc = opal_get_elog_size(&id, &size, &type); if (rc != OPAL_SUCCESS) { pr_err("ELOG: Opal log read failed\n"); return; } + elog_size = be64_to_cpu(size); + log_id = be64_to_cpu(id); + elog_type = be64_to_cpu(type); + BUG_ON(elog_size > OPAL_MAX_ERRLOG_SIZE); if (elog_size >= OPAL_MAX_ERRLOG_SIZE) From 3441f04b4b62758a798f9fbbf2047dfedf0329a5 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 22 Apr 2014 15:01:26 +1000 Subject: [PATCH 16/33] powerpc/powernv: Create OPAL sglist helper functions and fix endian issues We have two copies of code that creates an OPAL sg list. Consolidate these into a common set of helpers and fix the endian issues. The flash interface embedded a version number in the num_entries field, whereas the dump interface did did not. Since versioning wasn't added to the flash interface and it is impossible to add this in a backwards compatible way, just remove it. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 14 ++- arch/powerpc/platforms/powernv/opal-dump.c | 81 +-------------- arch/powerpc/platforms/powernv/opal-flash.c | 106 +------------------- arch/powerpc/platforms/powernv/opal.c | 63 ++++++++++++ 4 files changed, 76 insertions(+), 188 deletions(-) diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 1a752ac8c0ba..afb0fedd1214 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -41,14 +41,14 @@ struct opal_takeover_args { * size except the last one in the list to be as well. */ struct opal_sg_entry { - void *data; - long length; + __be64 data; + __be64 length; }; -/* sg list */ +/* SG list */ struct opal_sg_list { - unsigned long num_entries; - struct opal_sg_list *next; + __be64 length; + __be64 next; struct opal_sg_entry entry[]; }; @@ -929,6 +929,10 @@ extern int opal_resync_timebase(void); extern void opal_lpc_init(void); +struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, + unsigned long vmalloc_size); +void opal_free_sg_list(struct opal_sg_list *sg); + #endif /* __ASSEMBLY__ */ #endif /* __OPAL_H */ diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index b9827b0d87e4..f0b472427c57 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -209,80 +209,6 @@ static struct kobj_type dump_ktype = { .default_attrs = dump_default_attrs, }; -static void free_dump_sg_list(struct opal_sg_list *list) -{ - struct opal_sg_list *sg1; - while (list) { - sg1 = list->next; - kfree(list); - list = sg1; - } - list = NULL; -} - -static struct opal_sg_list *dump_data_to_sglist(struct dump_obj *dump) -{ - struct opal_sg_list *sg1, *list = NULL; - void *addr; - int64_t size; - - addr = dump->buffer; - size = dump->size; - - sg1 = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!sg1) - goto nomem; - - list = sg1; - sg1->num_entries = 0; - while (size > 0) { - /* Translate virtual address to physical address */ - sg1->entry[sg1->num_entries].data = - (void *)(vmalloc_to_pfn(addr) << PAGE_SHIFT); - - if (size > PAGE_SIZE) - sg1->entry[sg1->num_entries].length = PAGE_SIZE; - else - sg1->entry[sg1->num_entries].length = size; - - sg1->num_entries++; - if (sg1->num_entries >= SG_ENTRIES_PER_NODE) { - sg1->next = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!sg1->next) - goto nomem; - - sg1 = sg1->next; - sg1->num_entries = 0; - } - addr += PAGE_SIZE; - size -= PAGE_SIZE; - } - return list; - -nomem: - pr_err("%s : Failed to allocate memory\n", __func__); - free_dump_sg_list(list); - return NULL; -} - -static void sglist_to_phy_addr(struct opal_sg_list *list) -{ - struct opal_sg_list *sg, *next; - - for (sg = list; sg; sg = next) { - next = sg->next; - /* Don't translate NULL pointer for last entry */ - if (sg->next) - sg->next = (struct opal_sg_list *)__pa(sg->next); - else - sg->next = NULL; - - /* Convert num_entries to length */ - sg->num_entries = - sg->num_entries * sizeof(struct opal_sg_entry) + 16; - } -} - static int64_t dump_read_info(uint32_t *id, uint32_t *size, uint32_t *type) { int rc; @@ -314,15 +240,12 @@ static int64_t dump_read_data(struct dump_obj *dump) } /* Generate SG list */ - list = dump_data_to_sglist(dump); + list = opal_vmalloc_to_sg_list(dump->buffer, dump->size); if (!list) { rc = -ENOMEM; goto out; } - /* Translate sg list addr to real address */ - sglist_to_phy_addr(list); - /* First entry address */ addr = __pa(list); @@ -341,7 +264,7 @@ static int64_t dump_read_data(struct dump_obj *dump) __func__, dump->id); /* Free SG list */ - free_dump_sg_list(list); + opal_free_sg_list(list); out: return rc; diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c index a968fd1888b3..dc487ff04704 100644 --- a/arch/powerpc/platforms/powernv/opal-flash.c +++ b/arch/powerpc/platforms/powernv/opal-flash.c @@ -79,9 +79,6 @@ /* XXX: Assume candidate image size is <= 1GB */ #define MAX_IMAGE_SIZE 0x40000000 -/* Flash sg list version */ -#define SG_LIST_VERSION (1UL) - /* Image status */ enum { IMAGE_INVALID, @@ -271,94 +268,12 @@ static ssize_t manage_store(struct kobject *kobj, return count; } -/* - * Free sg list - */ -static void free_sg_list(struct opal_sg_list *list) -{ - struct opal_sg_list *sg1; - while (list) { - sg1 = list->next; - kfree(list); - list = sg1; - } - list = NULL; -} - -/* - * Build candidate image scatter gather list - * - * list format: - * ----------------------------------- - * | VER (8) | Entry length in bytes | - * ----------------------------------- - * | Pointer to next entry | - * ----------------------------------- - * | Address of memory area 1 | - * ----------------------------------- - * | Length of memory area 1 | - * ----------------------------------- - * | ......... | - * ----------------------------------- - * | ......... | - * ----------------------------------- - * | Address of memory area N | - * ----------------------------------- - * | Length of memory area N | - * ----------------------------------- - */ -static struct opal_sg_list *image_data_to_sglist(void) -{ - struct opal_sg_list *sg1, *list = NULL; - void *addr; - int size; - - addr = image_data.data; - size = image_data.size; - - sg1 = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!sg1) - return NULL; - - list = sg1; - sg1->num_entries = 0; - while (size > 0) { - /* Translate virtual address to physical address */ - sg1->entry[sg1->num_entries].data = - (void *)(vmalloc_to_pfn(addr) << PAGE_SHIFT); - - if (size > PAGE_SIZE) - sg1->entry[sg1->num_entries].length = PAGE_SIZE; - else - sg1->entry[sg1->num_entries].length = size; - - sg1->num_entries++; - if (sg1->num_entries >= SG_ENTRIES_PER_NODE) { - sg1->next = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!sg1->next) { - pr_err("%s : Failed to allocate memory\n", - __func__); - goto nomem; - } - - sg1 = sg1->next; - sg1->num_entries = 0; - } - addr += PAGE_SIZE; - size -= PAGE_SIZE; - } - return list; -nomem: - free_sg_list(list); - return NULL; -} - /* * OPAL update flash */ static int opal_flash_update(int op) { - struct opal_sg_list *sg, *list, *next; + struct opal_sg_list *list; unsigned long addr; int64_t rc = OPAL_PARAMETER; @@ -368,30 +283,13 @@ static int opal_flash_update(int op) goto flash; } - list = image_data_to_sglist(); + list = opal_vmalloc_to_sg_list(image_data.data, image_data.size); if (!list) goto invalid_img; /* First entry address */ addr = __pa(list); - /* Translate sg list address to absolute */ - for (sg = list; sg; sg = next) { - next = sg->next; - /* Don't translate NULL pointer for last entry */ - if (sg->next) - sg->next = (struct opal_sg_list *)__pa(sg->next); - else - sg->next = NULL; - - /* - * Convert num_entries to version/length format - * to satisfy OPAL. - */ - sg->num_entries = (SG_LIST_VERSION << 56) | - (sg->num_entries * sizeof(struct opal_sg_entry) + 16); - } - pr_alert("FLASH: Image is %u bytes\n", image_data.size); pr_alert("FLASH: Image update requested\n"); pr_alert("FLASH: Image will be updated during system reboot\n"); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 17cfc70082aa..360ad80c754c 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -638,3 +638,66 @@ void opal_shutdown(void) /* Export this so that test modules can use it */ EXPORT_SYMBOL_GPL(opal_invalid_call); + +/* Convert a region of vmalloc memory to an opal sg list */ +struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, + unsigned long vmalloc_size) +{ + struct opal_sg_list *sg, *first = NULL; + unsigned long i = 0; + + sg = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!sg) + goto nomem; + + first = sg; + + while (vmalloc_size > 0) { + uint64_t data = vmalloc_to_pfn(vmalloc_addr) << PAGE_SHIFT; + uint64_t length = min(vmalloc_size, PAGE_SIZE); + + sg->entry[i].data = cpu_to_be64(data); + sg->entry[i].length = cpu_to_be64(length); + i++; + + if (i >= SG_ENTRIES_PER_NODE) { + struct opal_sg_list *next; + + next = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!next) + goto nomem; + + sg->length = cpu_to_be64( + i * sizeof(struct opal_sg_entry) + 16); + i = 0; + sg->next = cpu_to_be64(__pa(next)); + sg = next; + } + + vmalloc_addr += length; + vmalloc_size -= length; + } + + sg->length = cpu_to_be64(i * sizeof(struct opal_sg_entry) + 16); + + return first; + +nomem: + pr_err("%s : Failed to allocate memory\n", __func__); + opal_free_sg_list(first); + return NULL; +} + +void opal_free_sg_list(struct opal_sg_list *sg) +{ + while (sg) { + uint64_t next = be64_to_cpu(sg->next); + + kfree(sg); + + if (next) + sg = __va(next); + else + sg = NULL; + } +} From 2d6b63bbdd7a649ea17fae19f8bab07d4b292a09 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 22 Apr 2014 15:01:27 +1000 Subject: [PATCH 17/33] powerpc/powernv: Fix little endian issues in OPAL dump code Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/opal.h | 4 ++-- arch/powerpc/platforms/powernv/opal-dump.c | 13 +++++++++---- 2 files changed, 11 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index afb0fedd1214..66ad7a74116f 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -868,8 +868,8 @@ int64_t opal_validate_flash(uint64_t buffer, uint32_t *size, uint32_t *result); int64_t opal_manage_flash(uint8_t op); int64_t opal_update_flash(uint64_t blk_list); int64_t opal_dump_init(uint8_t dump_type); -int64_t opal_dump_info(uint32_t *dump_id, uint32_t *dump_size); -int64_t opal_dump_info2(uint32_t *dump_id, uint32_t *dump_size, uint32_t *dump_type); +int64_t opal_dump_info(__be32 *dump_id, __be32 *dump_size); +int64_t opal_dump_info2(__be32 *dump_id, __be32 *dump_size, __be32 *dump_type); int64_t opal_dump_read(uint32_t dump_id, uint64_t buffer); int64_t opal_dump_ack(uint32_t dump_id); int64_t opal_dump_resend_notification(void); diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index f0b472427c57..788a1977b9a5 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -209,15 +209,20 @@ static struct kobj_type dump_ktype = { .default_attrs = dump_default_attrs, }; -static int64_t dump_read_info(uint32_t *id, uint32_t *size, uint32_t *type) +static int64_t dump_read_info(uint32_t *dump_id, uint32_t *dump_size, uint32_t *dump_type) { + __be32 id, size, type; int rc; - *type = 0xffffffff; - rc = opal_dump_info2(id, size, type); + type = cpu_to_be32(0xffffffff); + rc = opal_dump_info2(&id, &size, &type); if (rc == OPAL_PARAMETER) - rc = opal_dump_info(id, size); + rc = opal_dump_info(&id, &size); + + *dump_id = be32_to_cpu(id); + *dump_size = be32_to_cpu(size); + *dump_type = be32_to_cpu(type); if (rc) pr_warn("%s: Failed to get dump info (%d)\n", From 29ef7a3e26283606f181000b11e5fd37d73ab98f Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 21 Apr 2014 10:37:36 +0530 Subject: [PATCH 18/33] powerpc/mm: Fix tlbie to add AVAL fields for 64K pages The if condition check was based on a draft ISA doc. Remove the same. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/hash_native_64.c | 38 ++++++++++++++------------------ 1 file changed, 16 insertions(+), 22 deletions(-) diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 3ea26c25590b..cf1d325eae8b 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -82,17 +82,14 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize) va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1); va |= penc << 12; va |= ssize << 8; - /* Add AVAL part */ - if (psize != apsize) { - /* - * MPSS, 64K base page size and 16MB parge page size - * We don't need all the bits, but rest of the bits - * must be ignored by the processor. - * vpn cover upto 65 bits of va. (0...65) and we need - * 58..64 bits of va. - */ - va |= (vpn & 0xfe); - } + /* + * AVAL bits: + * We don't need all the bits, but rest of the bits + * must be ignored by the processor. + * vpn cover upto 65 bits of va. (0...65) and we need + * 58..64 bits of va. + */ + va |= (vpn & 0xfe); /* AVAL */ va |= 1; /* L */ asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2) : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206) @@ -133,17 +130,14 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize) va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1); va |= penc << 12; va |= ssize << 8; - /* Add AVAL part */ - if (psize != apsize) { - /* - * MPSS, 64K base page size and 16MB parge page size - * We don't need all the bits, but rest of the bits - * must be ignored by the processor. - * vpn cover upto 65 bits of va. (0...65) and we need - * 58..64 bits of va. - */ - va |= (vpn & 0xfe); - } + /* + * AVAL bits: + * We don't need all the bits, but rest of the bits + * must be ignored by the processor. + * vpn cover upto 65 bits of va. (0...65) and we need + * 58..64 bits of va. + */ + va |= (vpn & 0xfe); va |= 1; /* L */ asm volatile(".long 0x7c000224 | (%0 << 11) | (1 << 21)" : : "r"(va) : "memory"); From e98bf005d5feafb3a089868420c1f3743d304e14 Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Tue, 15 Apr 2014 10:10:50 -0700 Subject: [PATCH 19/33] powerpc/perf/hv_24x7: Probe errors changed to pr_debug(), padding fixed fixup for "powerpc/perf: Add support for the hv 24x7 interface" Makes the "not enabled" message less awful (and hides it in most cases). Signed-off-by: Cody P Schafer Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/hv-24x7.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 297c91051413..f5bca73d92b8 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -485,13 +485,13 @@ static int hv_24x7_init(void) struct hv_perf_caps caps; if (!firmware_has_feature(FW_FEATURE_LPAR)) { - pr_info("not a virtualized system, not enabling\n"); + pr_debug("not a virtualized system, not enabling\n"); return -ENODEV; } hret = hv_perf_caps_get(&caps); if (hret) { - pr_info("could not obtain capabilities, error 0x%80lx, not enabling\n", + pr_debug("could not obtain capabilities, not enabling, rc=%ld\n", hret); return -ENODEV; } From 0a8cf9e28c094cd934deaedfd3ec07830f2a63cf Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Tue, 15 Apr 2014 10:10:51 -0700 Subject: [PATCH 20/33] powerpc/perf/hv_gpci: Probe failures use pr_debug(), and padding reduced fixup for "powerpc/perf: Add support for the hv gpci (get performance counter info) interface". Makes the "not enabled" message less awful (and hidden unless debugging). Signed-off-by: Cody P Schafer Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/hv-gpci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 278ba7b9c2b5..8fee1dccaaec 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -273,13 +273,13 @@ static int hv_gpci_init(void) struct hv_perf_caps caps; if (!firmware_has_feature(FW_FEATURE_LPAR)) { - pr_info("not a virtualized system, not enabling\n"); + pr_debug("not a virtualized system, not enabling\n"); return -ENODEV; } hret = hv_perf_caps_get(&caps); if (hret) { - pr_info("could not obtain capabilities, error 0x%80lx, not enabling\n", + pr_debug("could not obtain capabilities, not enabling, rc=%ld\n", hret); return -ENODEV; } From 58a685c2d8f0616b5c6cfa0f7a9f2d081af3c6fd Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Tue, 15 Apr 2014 10:10:52 -0700 Subject: [PATCH 21/33] powerpc/perf/hv-gpci: Make device attr static Signed-off-by: Cody P Schafer Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/hv-gpci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 8fee1dccaaec..c9d399a2df82 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -78,7 +78,7 @@ static ssize_t kernel_version_show(struct device *dev, return sprintf(page, "0x%x\n", COUNTER_INFO_VERSION_CURRENT); } -DEVICE_ATTR_RO(kernel_version); +static DEVICE_ATTR_RO(kernel_version); HV_CAPS_ATTR(version, "0x%x\n"); HV_CAPS_ATTR(ga, "%d\n"); HV_CAPS_ATTR(expanded, "%d\n"); From 78d13166b189ff1741327d748a7f8d73e65d70bd Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Tue, 15 Apr 2014 10:10:53 -0700 Subject: [PATCH 22/33] powerpc/perf/hv-24x7: Use (unsigned long) not (u32) values when calling plpar_hcall_norets() Signed-off-by: Cody P Schafer Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/hv-24x7.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index f5bca73d92b8..3e8f60a1d53f 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -155,14 +155,26 @@ static ssize_t read_offset_data(void *dest, size_t dest_len, return copy_len; } +static unsigned long h_get_24x7_catalog_page_(unsigned long phys_4096, + unsigned long version, + unsigned long index) +{ + pr_devel("h_get_24x7_catalog_page(0x%lx, %lu, %lu)", + phys_4096, + version, + index); + WARN_ON(!IS_ALIGNED(phys_4096, 4096)); + return plpar_hcall_norets(H_GET_24X7_CATALOG_PAGE, + phys_4096, + version, + index); +} + static unsigned long h_get_24x7_catalog_page(char page[static 4096], u32 version, u32 index) { - WARN_ON(!IS_ALIGNED((unsigned long)page, 4096)); - return plpar_hcall_norets(H_GET_24X7_CATALOG_PAGE, - virt_to_phys(page), - version, - index); + return h_get_24x7_catalog_page_(virt_to_phys(page), + version, index); } static ssize_t catalog_read(struct file *filp, struct kobject *kobj, From 1ee9fcc1a021e54454a23b107a47d10fb603508c Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Tue, 15 Apr 2014 10:10:54 -0700 Subject: [PATCH 23/33] powerpc/perf/hv-24x7: Remove [static 4096], sparse chokes on it Signed-off-by: Cody P Schafer Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/hv-24x7.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 3e8f60a1d53f..95a67f81f22a 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -170,7 +170,7 @@ static unsigned long h_get_24x7_catalog_page_(unsigned long phys_4096, index); } -static unsigned long h_get_24x7_catalog_page(char page[static 4096], +static unsigned long h_get_24x7_catalog_page(char page[], u32 version, u32 index) { return h_get_24x7_catalog_page_(virt_to_phys(page), From bbad3e50e8ed2d48294c141e687d411430cacbcf Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Tue, 15 Apr 2014 10:10:55 -0700 Subject: [PATCH 24/33] powerpc/perf/hv-24x7: Catalog version number is be64, not be32 The catalog version number was changed from a be32 (with proceeding 32bits of padding) to a be64, update the code to treat it as a be64 Signed-off-by: Cody P Schafer Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/hv-24x7.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 95a67f81f22a..e0766b82e165 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -171,7 +171,7 @@ static unsigned long h_get_24x7_catalog_page_(unsigned long phys_4096, } static unsigned long h_get_24x7_catalog_page(char page[], - u32 version, u32 index) + u64 version, u32 index) { return h_get_24x7_catalog_page_(virt_to_phys(page), version, index); @@ -185,7 +185,7 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj, ssize_t ret = 0; size_t catalog_len = 0, catalog_page_len = 0, page_count = 0; loff_t page_offset = 0; - uint32_t catalog_version_num = 0; + uint64_t catalog_version_num = 0; void *page = kmem_cache_alloc(hv_page_cache, GFP_USER); struct hv_24x7_catalog_page_0 *page_0 = page; if (!page) @@ -197,7 +197,7 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj, goto e_free; } - catalog_version_num = be32_to_cpu(page_0->version); + catalog_version_num = be64_to_cpu(page_0->version); catalog_page_len = be32_to_cpu(page_0->length); catalog_len = catalog_page_len * 4096; @@ -220,8 +220,9 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj, page, 4096, page_offset * 4096); e_free: if (hret) - pr_err("h_get_24x7_catalog_page(ver=%d, page=%lld) failed: rc=%ld\n", - catalog_version_num, page_offset, hret); + pr_err("h_get_24x7_catalog_page(ver=%lld, page=%lld) failed:" + " rc=%ld\n", + catalog_version_num, page_offset, hret); kfree(page); pr_devel("catalog_read: offset=%lld(%lld) count=%zu(%zu) catalog_len=%zu(%zu) => %zd\n", @@ -255,7 +256,7 @@ e_free: \ static DEVICE_ATTR_RO(_name) PAGE_0_ATTR(catalog_version, "%lld\n", - (unsigned long long)be32_to_cpu(page_0->version)); + (unsigned long long)be64_to_cpu(page_0->version)); PAGE_0_ATTR(catalog_len, "%lld\n", (unsigned long long)be32_to_cpu(page_0->length) * 4096); static BIN_ATTR_RO(catalog, 0/* real length varies */); From a2dd5da77f2cc9fc9ff11ea6b699556254e94a6c Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 14 Apr 2014 21:54:05 +1000 Subject: [PATCH 25/33] powerpc: Rename duplicate COMMAND_LINE_SIZE define We have two definitions of COMMAND_LINE_SIZE, one for the kernel and one for the boot wrapper. I assume this is so the boot wrapper can be self sufficient and not rely on kernel headers. Having two defines with the same name is confusing, I just updated the wrong one when trying to bump it. Make the boot wrapper define unique by calling it BOOT_COMMAND_LINE_SIZE. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/boot/main.c | 8 ++++---- arch/powerpc/boot/ops.h | 2 +- arch/powerpc/boot/ps3.c | 4 ++-- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c index a28f02165e97..d367a0aece2a 100644 --- a/arch/powerpc/boot/main.c +++ b/arch/powerpc/boot/main.c @@ -139,18 +139,18 @@ static struct addr_range prep_initrd(struct addr_range vmlinux, void *chosen, * edit the command line passed to vmlinux (by setting /chosen/bootargs). * The buffer is put in it's own section so that tools may locate it easier. */ -static char cmdline[COMMAND_LINE_SIZE] +static char cmdline[BOOT_COMMAND_LINE_SIZE] __attribute__((__section__("__builtin_cmdline"))); static void prep_cmdline(void *chosen) { if (cmdline[0] == '\0') - getprop(chosen, "bootargs", cmdline, COMMAND_LINE_SIZE-1); + getprop(chosen, "bootargs", cmdline, BOOT_COMMAND_LINE_SIZE-1); printf("\n\rLinux/PowerPC load: %s", cmdline); /* If possible, edit the command line */ if (console_ops.edit_cmdline) - console_ops.edit_cmdline(cmdline, COMMAND_LINE_SIZE); + console_ops.edit_cmdline(cmdline, BOOT_COMMAND_LINE_SIZE); printf("\n\r"); /* Put the command line back into the devtree for the kernel */ @@ -174,7 +174,7 @@ void start(void) * built-in command line wasn't set by an external tool */ if ((loader_info.cmdline_len > 0) && (cmdline[0] == '\0')) memmove(cmdline, loader_info.cmdline, - min(loader_info.cmdline_len, COMMAND_LINE_SIZE-1)); + min(loader_info.cmdline_len, BOOT_COMMAND_LINE_SIZE-1)); if (console_ops.open && (console_ops.open() < 0)) exit(); diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h index b3218ce451bb..339e041e8dda 100644 --- a/arch/powerpc/boot/ops.h +++ b/arch/powerpc/boot/ops.h @@ -15,7 +15,7 @@ #include "types.h" #include "string.h" -#define COMMAND_LINE_SIZE 512 +#define BOOT_COMMAND_LINE_SIZE 512 #define MAX_PATH_LEN 256 #define MAX_PROP_LEN 256 /* What should this be? */ diff --git a/arch/powerpc/boot/ps3.c b/arch/powerpc/boot/ps3.c index 9954d98871d0..4ec2d86d3c50 100644 --- a/arch/powerpc/boot/ps3.c +++ b/arch/powerpc/boot/ps3.c @@ -47,13 +47,13 @@ BSS_STACK(4096); * The buffer is put in it's own section so that tools may locate it easier. */ -static char cmdline[COMMAND_LINE_SIZE] +static char cmdline[BOOT_COMMAND_LINE_SIZE] __attribute__((__section__("__builtin_cmdline"))); static void prep_cmdline(void *chosen) { if (cmdline[0] == '\0') - getprop(chosen, "bootargs", cmdline, COMMAND_LINE_SIZE-1); + getprop(chosen, "bootargs", cmdline, BOOT_COMMAND_LINE_SIZE-1); else setprop_str(chosen, "bootargs", cmdline); From a5980d064fe292584da73ddd180f4f140f9ab97d Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 14 Apr 2014 21:54:52 +1000 Subject: [PATCH 26/33] powerpc: Bump COMMAND_LINE_SIZE to 2048 I've had a report that the current limit is too small for an automated network based installer. Bump it. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/uapi/asm/setup.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/uapi/asm/setup.h b/arch/powerpc/include/uapi/asm/setup.h index 552df83f1a49..ae3fb68cb28e 100644 --- a/arch/powerpc/include/uapi/asm/setup.h +++ b/arch/powerpc/include/uapi/asm/setup.h @@ -1 +1,6 @@ -#include +#ifndef _UAPI_ASM_POWERPC_SETUP_H +#define _UAPI_ASM_POWERPC_SETUP_H + +#define COMMAND_LINE_SIZE 2048 + +#endif /* _UAPI_ASM_POWERPC_SETUP_H */ From 579a53cafdd641f2d67ba4f4fbd9cc4180b8717d Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 14 Apr 2014 21:55:25 +1000 Subject: [PATCH 27/33] powerpc: Bump BOOT_COMMAND_LINE_SIZE to 2048 Bump the boot wrapper BOOT_COMMAND_LINE_SIZE to match the kernel. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/boot/ops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h index 339e041e8dda..8aad3c55aeda 100644 --- a/arch/powerpc/boot/ops.h +++ b/arch/powerpc/boot/ops.h @@ -15,7 +15,7 @@ #include "types.h" #include "string.h" -#define BOOT_COMMAND_LINE_SIZE 512 +#define BOOT_COMMAND_LINE_SIZE 2048 #define MAX_PATH_LEN 256 #define MAX_PROP_LEN 256 /* What should this be? */ From 0c930692107be4b91c3eeecfd9c9d600039f966f Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 14 Apr 2014 21:23:32 +1000 Subject: [PATCH 28/33] powerpc: Fix error return in rtas_flash module init module_init should return 0 or a negative errno. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/rtas_flash.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 2f3cdb01506d..658e89d2025b 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -705,7 +705,7 @@ static int __init rtas_flash_init(void) if (rtas_token("ibm,update-flash-64-and-reboot") == RTAS_UNKNOWN_SERVICE) { pr_info("rtas_flash: no firmware flash support\n"); - return 1; + return -EINVAL; } rtas_validate_flash_data.buf = kzalloc(VALIDATE_BUF_SIZE, GFP_KERNEL); From 42dbfc8649737cb622b2a7e02045401c4c09561c Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Thu, 10 Apr 2014 16:25:31 +0800 Subject: [PATCH 29/33] powerpc/pseries: Protect remove_memory() with device hotplug lock While testing memory hot-remove, I found following dead lock: Process #1141 is drmgr, trying to remove some memory, i.e. memory499. It holds the memory_hotplug_mutex, and blocks when trying to remove file "online" under dir memory499, in kernfs_drain(), at wait_event(root->deactivate_waitq, atomic_read(&kn->active) == KN_DEACTIVATED_BIAS); Process #1120 is trying to online memory499 by echo 1 > memory499/online In .kernfs_fop_write, it uses kernfs_get_active() to increase &kn->active, thus blocking process #1141. While itself is blocked later when trying to acquire memory_hotplug_mutex, which is held by process The backtrace of both processes are shown below: [] 0xc000000001b18600 [] .__switch_to+0x144/0x200 [] .online_pages+0x74/0x7b0 [] .memory_subsys_online+0x9c/0x150 [] .device_online+0xb8/0x120 [] .online_store+0xb4/0xc0 [] .dev_attr_store+0x64/0xa0 [] .sysfs_kf_write+0x7c/0xb0 [] .kernfs_fop_write+0x154/0x1e0 [] .vfs_write+0xe0/0x260 [] .SyS_write+0x64/0x110 [] syscall_exit+0x0/0x7c [] 0xc000000001b18600 [] .__switch_to+0x144/0x200 [] .__kernfs_remove+0x204/0x300 [] .kernfs_remove_by_name_ns+0x68/0xf0 [] .sysfs_remove_file_ns+0x38/0x60 [] .device_remove_attrs+0x54/0xc0 [] .device_del+0x158/0x250 [] .device_unregister+0x34/0xa0 [] .unregister_memory_section+0x164/0x170 [] .__remove_pages+0x108/0x4c0 [] .arch_remove_memory+0x60/0xc0 [] .remove_memory+0x8c/0xe0 [] .pseries_remove_memblock+0xd4/0x160 [] .pseries_memory_notifier+0x27c/0x290 [] .notifier_call_chain+0x8c/0x100 [] .__blocking_notifier_call_chain+0x6c/0xe0 [] .of_property_notify+0x7c/0xc0 [] .of_update_property+0x3c/0x1b0 [] .ofdt_write+0x3dc/0x740 [] .proc_reg_write+0xac/0x110 [] .vfs_write+0xe0/0x260 [] .SyS_write+0x64/0x110 [] syscall_exit+0x0/0x7c This patch uses lock_device_hotplug() to protect remove_memory() called in pseries_remove_memblock(), which is also stated before function remove_memory(): * NOTE: The caller must call lock_device_hotplug() to serialize hotplug * and online/offline operations before this call, as required by * try_offline_node(). */ void __ref remove_memory(int nid, u64 start, u64 size) With this lock held, the other process(#1120 above) trying to online the memory block will retry the system call when calling lock_device_hotplug_sysfs(), and finally find No such device error. Signed-off-by: Li Zhong Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/hotplug-memory.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 573b488fc48b..7f75c94af822 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -100,10 +100,10 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz start_pfn = base >> PAGE_SHIFT; - if (!pfn_valid(start_pfn)) { - memblock_remove(base, memblock_size); - return 0; - } + lock_device_hotplug(); + + if (!pfn_valid(start_pfn)) + goto out; block_sz = memory_block_size_bytes(); sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; @@ -114,8 +114,10 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz base += MIN_MEMORY_BLOCK_SIZE; } +out: /* Update memory regions for memory remove */ memblock_remove(base, memblock_size); + unlock_device_hotplug(); return 0; } From f203891117323dd31c11adcbba60452c933d604e Mon Sep 17 00:00:00 2001 From: Preeti U Murthy Date: Fri, 11 Apr 2014 16:01:48 +0530 Subject: [PATCH 30/33] ppc/powernv: Set the runlatch bits correctly for offline cpus Up until now we have been setting the runlatch bits for a busy CPU and clearing it when a CPU enters idle state. The runlatch bit has thus been consistent with the utilization of a CPU as long as the CPU is online. However when a CPU is hotplugged out the runlatch bit is not cleared. It needs to be cleared to indicate an unused CPU. Hence this patch has the runlatch bit cleared for an offline CPU just before entering an idle state and sets it immediately after it exits the idle state. Signed-off-by: Preeti U Murthy Acked-by: Paul Mackerras Reviewed-by: Srivatsa S. Bhat Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/powernv/smp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 908672bdcea6..bf5fcd452168 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -30,6 +30,7 @@ #include #include #include +#include #include "powernv.h" @@ -156,7 +157,9 @@ static void pnv_smp_cpu_kill_self(void) */ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1); while (!generic_check_cpu_restart(cpu)) { + ppc64_runlatch_off(); power7_nap(); + ppc64_runlatch_on(); if (!generic_check_cpu_restart(cpu)) { DBG("CPU%d Unexpected exit while offline !\n", cpu); /* We may be getting an IPI, so we re-enable From fd17dc7b9a8d57150ee0121c4c83edbb7e26eece Mon Sep 17 00:00:00 2001 From: Preeti U Murthy Date: Fri, 11 Apr 2014 16:01:58 +0530 Subject: [PATCH 31/33] ppc/kvm: Set the runlatch bit of a CPU just before starting guest The secondary threads in the core are kept offline before launching guests in kvm on powerpc: "371fefd6f2dc4666:KVM: PPC: Allow book3s_hv guests to use SMT processor modes." Hence their runlatch bits are cleared. When the secondary threads are called in to start a guest, their runlatch bits need to be set to indicate that they are busy. The primary thread has its runlatch bit set though, but there is no harm in setting this bit once again. Hence set the runlatch bit for all threads before they start guest. Signed-off-by: Preeti U Murthy Acked-by: Paul Mackerras Reviewed-by: Srivatsa S. Bhat Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index ffbb871c2bd8..b25407533618 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -242,6 +242,12 @@ kvm_novcpu_exit: */ .globl kvm_start_guest kvm_start_guest: + + /* Set runlatch bit the minute you wake up from nap */ + mfspr r1, SPRN_CTRLF + ori r1, r1, 1 + mtspr SPRN_CTRLT, r1 + ld r2,PACATOC(r13) li r0,KVM_HWTHREAD_IN_KVM From 582b910edafd283dfab78f41f437a92a65ee5103 Mon Sep 17 00:00:00 2001 From: Preeti U Murthy Date: Fri, 11 Apr 2014 16:02:08 +0530 Subject: [PATCH 32/33] ppc/kvm: Clear the runlatch bit of a vcpu before napping When the guest cedes the vcpu or the vcpu has no guest to run it naps. Clear the runlatch bit of the vcpu before napping to indicate an idle cpu. Signed-off-by: Preeti U Murthy Acked-by: Paul Mackerras Reviewed-by: Srivatsa S. Bhat Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index b25407533618..b031f932c0cc 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -315,6 +315,11 @@ kvm_no_guest: li r0, KVM_HWTHREAD_IN_NAP stb r0, HSTATE_HWTHREAD_STATE(r13) kvm_do_nap: + /* Clear the runlatch bit before napping */ + mfspr r2, SPRN_CTRLF + clrrdi r2, r2, 1 + mtspr SPRN_CTRLT, r2 + li r3, LPCR_PECE0 mfspr r4, SPRN_LPCR rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1 @@ -2005,8 +2010,13 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) /* * Take a nap until a decrementer or external or doobell interrupt - * occurs, with PECE1, PECE0 and PECEDP set in LPCR + * occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the + * runlatch bit before napping. */ + mfspr r2, SPRN_CTRLF + clrrdi r2, r2, 1 + mtspr SPRN_CTRLT, r2 + li r0,1 stb r0,HSTATE_HWTHREAD_REQ(r13) mfspr r5,SPRN_LPCR From e4565362c7adc31201135c4b6d649fc1bdc3bf20 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Tue, 8 Apr 2014 14:20:19 +1000 Subject: [PATCH 33/33] powerpc/4xx: Fix section mismatch in ppc4xx_pci.c This patch fixes this section mismatch: WARNING: vmlinux.o(.text+0x1efc4): Section mismatch in reference from the function apm821xx_pciex_init_port_hw() to the function .init.text:ppc4xx_pciex_wait_on_sdr.isra.9() The function apm821xx_pciex_init_port_hw() references the function __init ppc4xx_pciex_wait_on_sdr.isra.9(). This is often because apm821xx_pciex_init_port_hw lacks a __init annotation or the annotation of ppc4xx_pciex_wait_on_sdr.isra.9 is wrong. apm821xx_pciex_init_port_hw is only referenced by a struct in __initdata, so it should be safe to add __init to apm821xx_pciex_init_port_hw. Signed-off-by: Alistair Popple Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/sysdev/ppc4xx_pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c index 64603a10b863..4914fd3f41ec 100644 --- a/arch/powerpc/sysdev/ppc4xx_pci.c +++ b/arch/powerpc/sysdev/ppc4xx_pci.c @@ -1058,7 +1058,7 @@ static int __init apm821xx_pciex_core_init(struct device_node *np) return 1; } -static int apm821xx_pciex_init_port_hw(struct ppc4xx_pciex_port *port) +static int __init apm821xx_pciex_init_port_hw(struct ppc4xx_pciex_port *port) { u32 val;