From 69111bac42f5ceacdd22e30947837ceb2c4493ed Mon Sep 17 00:00:00 2001 From: Christoph Lameter <cl@linux.com> Date: Tue, 21 Oct 2014 15:23:25 -0500 Subject: powerpc: Replace __get_cpu_var uses This still has not been merged and now powerpc is the only arch that does not have this change. Sorry about missing linuxppc-dev before. V2->V2 - Fix up to work against 3.18-rc1 __get_cpu_var() is used for multiple purposes in the kernel source. One of them is address calculation via the form &__get_cpu_var(x). This calculates the address for the instance of the percpu variable of the current processor based on an offset. Other use cases are for storing and retrieving data from the current processors percpu area. __get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment. __get_cpu_var() is defined as : __get_cpu_var() always only does an address determination. However, store and retrieve operations could use a segment prefix (or global register on other platforms) to avoid the address calculation. this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use optimized assembly code to read and write per cpu variables. This patch converts __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and less registers are used when code is generated. At the end of the patch set all uses of __get_cpu_var have been removed so the macro is removed too. The patch set includes passes over all arches as well. Once these operations are used throughout then specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by f.e. using a global register that may be set to the per cpu base. Transformations done to __get_cpu_var() 1. Determine the address of the percpu instance of the current processor. DEFINE_PER_CPU(int, y); int *x = &__get_cpu_var(y); Converts to int *x = this_cpu_ptr(&y); 2. Same as #1 but this time an array structure is involved. DEFINE_PER_CPU(int, y[20]); int *x = __get_cpu_var(y); Converts to int *x = this_cpu_ptr(y); 3. Retrieve the content of the current processors instance of a per cpu variable. DEFINE_PER_CPU(int, y); int x = __get_cpu_var(y) Converts to int x = __this_cpu_read(y); 4. Retrieve the content of a percpu struct DEFINE_PER_CPU(struct mystruct, y); struct mystruct x = __get_cpu_var(y); Converts to memcpy(&x, this_cpu_ptr(&y), sizeof(x)); 5. Assignment to a per cpu variable DEFINE_PER_CPU(int, y) __get_cpu_var(y) = x; Converts to __this_cpu_write(y, x); 6. Increment/Decrement etc of a per cpu variable DEFINE_PER_CPU(int, y); __get_cpu_var(y)++ Converts to __this_cpu_inc(y) Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> CC: Paul Mackerras <paulus@samba.org> Signed-off-by: Christoph Lameter <cl@linux.com> [mpe: Fix build errors caused by set/or_softirq_pending(), and rework assignment in __set_breakpoint() to use memcpy().] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> --- arch/powerpc/platforms/cell/interrupt.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/platforms/cell') diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c index 8a106b4172e0..4c11421847be 100644 --- a/arch/powerpc/platforms/cell/interrupt.c +++ b/arch/powerpc/platforms/cell/interrupt.c @@ -82,7 +82,7 @@ static void iic_unmask(struct irq_data *d) static void iic_eoi(struct irq_data *d) { - struct iic *iic = &__get_cpu_var(cpu_iic); + struct iic *iic = this_cpu_ptr(&cpu_iic); out_be64(&iic->regs->prio, iic->eoi_stack[--iic->eoi_ptr]); BUG_ON(iic->eoi_ptr < 0); } @@ -148,7 +148,7 @@ static unsigned int iic_get_irq(void) struct iic *iic; unsigned int virq; - iic = &__get_cpu_var(cpu_iic); + iic = this_cpu_ptr(&cpu_iic); *(unsigned long *) &pending = in_be64((u64 __iomem *) &iic->regs->pending_destr); if (!(pending.flags & CBE_IIC_IRQ_VALID)) @@ -163,7 +163,7 @@ static unsigned int iic_get_irq(void) void iic_setup_cpu(void) { - out_be64(&__get_cpu_var(cpu_iic).regs->prio, 0xff); + out_be64(this_cpu_ptr(&cpu_iic.regs->prio), 0xff); } u8 iic_get_target_id(int cpu) -- cgit v1.2.1 From 9178ba294b6839eeff1a91bed95515d783f3ee6c Mon Sep 17 00:00:00 2001 From: Alexander Graf <agraf@suse.de> Date: Mon, 13 Oct 2014 16:01:09 +0200 Subject: powerpc: Convert power off logic to pm_power_off The generic Linux framework to power off the machine is a function pointer called pm_power_off. The trick about this pointer is that device drivers can potentially implement it rather than board files. Today on powerpc we set pm_power_off to invoke our generic full machine power off logic which then calls ppc_md.power_off to invoke machine specific power off. However, when we want to add a power off GPIO via the "gpio-poweroff" driver, this card house falls apart. That driver only registers itself if pm_power_off is NULL to ensure it doesn't override board specific logic. However, since we always set pm_power_off to the generic power off logic (which will just not power off the machine if no ppc_md.power_off call is implemented), we can't implement power off via the generic GPIO power off driver. To fix this up, let's get rid of the ppc_md.power_off logic and just always use pm_power_off as was intended. Then individual drivers such as the GPIO power off driver can implement power off logic via that function pointer. With this patch set applied and a few patches on top of QEMU that implement a power off GPIO on the virt e500 machine, I can successfully turn off my virtual machine after halt. Signed-off-by: Alexander Graf <agraf@suse.de> [mpe: Squash into one patch and update changelog based on cover letter] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> --- arch/powerpc/platforms/cell/celleb_setup.c | 4 ++-- arch/powerpc/platforms/cell/qpace_setup.c | 2 +- arch/powerpc/platforms/cell/setup.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/platforms/cell') diff --git a/arch/powerpc/platforms/cell/celleb_setup.c b/arch/powerpc/platforms/cell/celleb_setup.c index 34e8ce2976aa..90be8ec51686 100644 --- a/arch/powerpc/platforms/cell/celleb_setup.c +++ b/arch/powerpc/platforms/cell/celleb_setup.c @@ -142,6 +142,7 @@ static int __init celleb_probe_beat(void) powerpc_firmware_features |= FW_FEATURE_CELLEB_ALWAYS | FW_FEATURE_BEAT | FW_FEATURE_LPAR; hpte_init_beat_v3(); + pm_power_off = beat_power_off; return 1; } @@ -190,6 +191,7 @@ static int __init celleb_probe_native(void) powerpc_firmware_features |= FW_FEATURE_CELLEB_ALWAYS; hpte_init_native(); + pm_power_off = rtas_power_off; return 1; } @@ -204,7 +206,6 @@ define_machine(celleb_beat) { .setup_arch = celleb_setup_arch_beat, .show_cpuinfo = celleb_show_cpuinfo, .restart = beat_restart, - .power_off = beat_power_off, .halt = beat_halt, .get_rtc_time = beat_get_rtc_time, .set_rtc_time = beat_set_rtc_time, @@ -230,7 +231,6 @@ define_machine(celleb_native) { .setup_arch = celleb_setup_arch_native, .show_cpuinfo = celleb_show_cpuinfo, .restart = rtas_restart, - .power_off = rtas_power_off, .halt = rtas_halt, .get_boot_time = rtas_get_boot_time, .get_rtc_time = rtas_get_rtc_time, diff --git a/arch/powerpc/platforms/cell/qpace_setup.c b/arch/powerpc/platforms/cell/qpace_setup.c index 6e3409d590ac..d328140dc6f5 100644 --- a/arch/powerpc/platforms/cell/qpace_setup.c +++ b/arch/powerpc/platforms/cell/qpace_setup.c @@ -127,6 +127,7 @@ static int __init qpace_probe(void) return 0; hpte_init_native(); + pm_power_off = rtas_power_off; return 1; } @@ -137,7 +138,6 @@ define_machine(qpace) { .setup_arch = qpace_setup_arch, .show_cpuinfo = qpace_show_cpuinfo, .restart = rtas_restart, - .power_off = rtas_power_off, .halt = rtas_halt, .get_boot_time = rtas_get_boot_time, .get_rtc_time = rtas_get_rtc_time, diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c index 6ae25fb62015..d62aa982d530 100644 --- a/arch/powerpc/platforms/cell/setup.c +++ b/arch/powerpc/platforms/cell/setup.c @@ -259,6 +259,7 @@ static int __init cell_probe(void) return 0; hpte_init_native(); + pm_power_off = rtas_power_off; return 1; } @@ -269,7 +270,6 @@ define_machine(cell) { .setup_arch = cell_setup_arch, .show_cpuinfo = cell_show_cpuinfo, .restart = rtas_restart, - .power_off = rtas_power_off, .halt = rtas_halt, .get_boot_time = rtas_get_boot_time, .get_rtc_time = rtas_get_rtc_time, -- cgit v1.2.1 From 68cf0d642f62267b960f947370539ff3582c4935 Mon Sep 17 00:00:00 2001 From: Anton Blanchard <anton@samba.org> Date: Wed, 17 Sep 2014 22:15:35 +1000 Subject: powerpc: Remove superfluous bootmem includes Lots of places included bootmem.h even when not using bootmem. Signed-off-by: Anton Blanchard <anton@samba.org> Tested-by: Emil Medve <Emilian.Medve@Freescale.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> --- arch/powerpc/platforms/cell/celleb_scc_epci.c | 1 - arch/powerpc/platforms/cell/celleb_scc_pciex.c | 1 - 2 files changed, 2 deletions(-) (limited to 'arch/powerpc/platforms/cell') diff --git a/arch/powerpc/platforms/cell/celleb_scc_epci.c b/arch/powerpc/platforms/cell/celleb_scc_epci.c index 844c0facb4f7..9438bbed402f 100644 --- a/arch/powerpc/platforms/cell/celleb_scc_epci.c +++ b/arch/powerpc/platforms/cell/celleb_scc_epci.c @@ -25,7 +25,6 @@ #include <linux/pci.h> #include <linux/init.h> #include <linux/pci_regs.h> -#include <linux/bootmem.h> #include <asm/io.h> #include <asm/irq.h> diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c index 4278acfa2ede..f22387598040 100644 --- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c +++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c @@ -25,7 +25,6 @@ #include <linux/string.h> #include <linux/slab.h> #include <linux/init.h> -#include <linux/bootmem.h> #include <linux/delay.h> #include <linux/interrupt.h> -- cgit v1.2.1 From e39f223fc93580c86ccf6b3422033e349f57f0dd Mon Sep 17 00:00:00 2001 From: Michael Ellerman <mpe@ellerman.id.au> Date: Tue, 18 Nov 2014 16:47:35 +1100 Subject: powerpc: Remove more traces of bootmem Although we are now selecting NO_BOOTMEM, we still have some traces of bootmem lying around. That is because even with NO_BOOTMEM there is still a shim that converts bootmem calls into memblock calls, but ultimately we want to remove all traces of bootmem. Most of the patch is conversions from alloc_bootmem() to memblock_virt_alloc(). In general a call such as: p = (struct foo *)alloc_bootmem(x); Becomes: p = memblock_virt_alloc(x, 0); We don't need the cast because memblock_virt_alloc() returns a void *. The alignment value of zero tells memblock to use the default alignment, which is SMP_CACHE_BYTES, the same value alloc_bootmem() uses. We remove a number of NULL checks on the result of memblock_virt_alloc(). That is because memblock_virt_alloc() will panic if it can't allocate, in exactly the same way as alloc_bootmem(), so the NULL checks are and always have been redundant. The memory returned by memblock_virt_alloc() is already zeroed, so we remove several memsets of the result of memblock_virt_alloc(). Finally we convert a few uses of __alloc_bootmem(x, y, MAX_DMA_ADDRESS) to just plain memblock_virt_alloc(). We don't use memblock_alloc_base() because MAX_DMA_ADDRESS is ~0ul on powerpc, so limiting the allocation to that is pointless, 16XB ought to be enough for anyone. Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> --- arch/powerpc/platforms/cell/celleb_pci.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/platforms/cell') diff --git a/arch/powerpc/platforms/cell/celleb_pci.c b/arch/powerpc/platforms/cell/celleb_pci.c index 2b98a36ef8fb..3ce70ded2d6a 100644 --- a/arch/powerpc/platforms/cell/celleb_pci.c +++ b/arch/powerpc/platforms/cell/celleb_pci.c @@ -29,7 +29,7 @@ #include <linux/pci.h> #include <linux/string.h> #include <linux/init.h> -#include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/pci_regs.h> #include <linux/of.h> #include <linux/of_device.h> @@ -401,11 +401,11 @@ error: } else { if (config && *config) { size = 256; - free_bootmem(__pa(*config), size); + memblock_free(__pa(*config), size); } if (res && *res) { size = sizeof(struct celleb_pci_resource); - free_bootmem(__pa(*res), size); + memblock_free(__pa(*res), size); } } -- cgit v1.2.1 From aefa5688c070727b8729de1aef85cad7b9933fc7 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Date: Thu, 4 Dec 2014 11:00:14 +0530 Subject: powerpc/mm: don't do tlbie for updatepp request with NO HPTE fault upatepp can get called for a nohpte fault when we find from the linux page table that the translation was hashed before. In that case we are sure that there is no existing translation, hence we could avoid doing tlbie. We could possibly race with a parallel fault filling the TLB. But that should be ok because updatepp is only ever relaxing permissions. We also look at linux pte permission bits when filling hash pte permission bits. We also hold the linux pte busy bits while inserting/updating a hashpte entry, hence a paralle update of linux pte is not possible. On the other hand mprotect involves ptep_modify_prot_start which cause a hpte invalidate and not updatepp. Performance number: We use randbox_access_bench written by Anton. Kernel with THP disabled and smaller hash page table size. 86.60% random_access_b [kernel.kallsyms] [k] .native_hpte_updatepp 2.10% random_access_b random_access_bench [.] doit 1.99% random_access_b [kernel.kallsyms] [k] .do_raw_spin_lock 1.85% random_access_b [kernel.kallsyms] [k] .native_hpte_insert 1.26% random_access_b [kernel.kallsyms] [k] .native_flush_hash_range 1.18% random_access_b [kernel.kallsyms] [k] .__delay 0.69% random_access_b [kernel.kallsyms] [k] .native_hpte_remove 0.37% random_access_b [kernel.kallsyms] [k] .clear_user_page 0.34% random_access_b [kernel.kallsyms] [k] .__hash_page_64K 0.32% random_access_b [kernel.kallsyms] [k] fast_exception_return 0.30% random_access_b [kernel.kallsyms] [k] .hash_page_mm With Fix: 27.54% random_access_b random_access_bench [.] doit 22.90% random_access_b [kernel.kallsyms] [k] .native_hpte_insert 5.76% random_access_b [kernel.kallsyms] [k] .native_hpte_remove 5.20% random_access_b [kernel.kallsyms] [k] fast_exception_return 5.12% random_access_b [kernel.kallsyms] [k] .__hash_page_64K 4.80% random_access_b [kernel.kallsyms] [k] .hash_page_mm 3.31% random_access_b [kernel.kallsyms] [k] data_access_common 1.84% random_access_b [kernel.kallsyms] [k] .trace_hardirqs_on_caller Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> --- arch/powerpc/platforms/cell/beat_htab.c | 4 ++-- arch/powerpc/platforms/cell/spu_base.c | 5 +++-- arch/powerpc/platforms/cell/spufs/fault.c | 2 +- 3 files changed, 6 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/platforms/cell') diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c index d4d245c0d787..bee9232fe619 100644 --- a/arch/powerpc/platforms/cell/beat_htab.c +++ b/arch/powerpc/platforms/cell/beat_htab.c @@ -186,7 +186,7 @@ static long beat_lpar_hpte_updatepp(unsigned long slot, unsigned long newpp, unsigned long vpn, int psize, int apsize, - int ssize, int local) + int ssize, unsigned long flags) { unsigned long lpar_rc; u64 dummy0, dummy1; @@ -369,7 +369,7 @@ static long beat_lpar_hpte_updatepp_v3(unsigned long slot, unsigned long newpp, unsigned long vpn, int psize, int apsize, - int ssize, int local) + int ssize, unsigned long flags) { unsigned long lpar_rc; unsigned long want_v; diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c index ffcbd242e669..f7af74f83693 100644 --- a/arch/powerpc/platforms/cell/spu_base.c +++ b/arch/powerpc/platforms/cell/spu_base.c @@ -181,7 +181,8 @@ static int __spu_trap_data_seg(struct spu *spu, unsigned long ea) return 0; } -extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap); //XXX +extern int hash_page(unsigned long ea, unsigned long access, + unsigned long trap, unsigned long dsisr); //XXX static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr) { int ret; @@ -196,7 +197,7 @@ static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr) (REGION_ID(ea) != USER_REGION_ID)) { spin_unlock(&spu->register_lock); - ret = hash_page(ea, _PAGE_PRESENT, 0x300); + ret = hash_page(ea, _PAGE_PRESENT, 0x300, dsisr); spin_lock(&spu->register_lock); if (!ret) { diff --git a/arch/powerpc/platforms/cell/spufs/fault.c b/arch/powerpc/platforms/cell/spufs/fault.c index e45894a08118..d98f845ac777 100644 --- a/arch/powerpc/platforms/cell/spufs/fault.c +++ b/arch/powerpc/platforms/cell/spufs/fault.c @@ -144,7 +144,7 @@ int spufs_handle_class1(struct spu_context *ctx) access = (_PAGE_PRESENT | _PAGE_USER); access |= (dsisr & MFC_DSISR_ACCESS_PUT) ? _PAGE_RW : 0UL; local_irq_save(flags); - ret = hash_page(ea, access, 0x300); + ret = hash_page(ea, access, 0x300, dsisr); local_irq_restore(flags); /* hashing failed, so try the actual fault handler */ -- cgit v1.2.1