From 409001948d9f221c94a61c3ee96de112755fc04d Mon Sep 17 00:00:00 2001 From: Brian King Date: Wed, 22 Oct 2008 05:53:45 +0000 Subject: powerpc: Update page-in counter for CMM A new field has been added to the VPA as a method for the client OS to communicate to firmware the number of page-ins it is performing when running collaborative memory overcommit. The hypervisor will use this information to better determine if a partition is experiencing memory pressure and needs more memory allocated to it. Signed-off-by: Brian King Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/lppaca.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index 2fe268b10333..25aaa97facd8 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -133,7 +133,8 @@ struct lppaca { //============================================================================= // CACHE_LINE_4-5 0x0180 - 0x027F Contains PMC interrupt data //============================================================================= - u8 pmc_save_area[256]; // PMC interrupt Area x00-xFF + u32 page_ins; // CMO Hint - # page ins by OS x00-x04 + u8 pmc_save_area[252]; // PMC interrupt Area x04-xFF } __attribute__((__aligned__(0x400))); extern struct lppaca lppaca[]; -- cgit v1.2.1 From 4ec577a28980a0790df3c3dfe9c81f6e2222acfb Mon Sep 17 00:00:00 2001 From: Mark Nelson Date: Mon, 27 Oct 2008 00:43:02 +0000 Subject: powerpc: Add new CPU feature: CPU_FTR_UNALIGNED_LD_STD Add a new CPU feature bit, CPU_FTR_UNALIGNED_LD_STD, to be added to the 64bit powerpc chips that can do unaligned load double and store double without any performance hit. This is added to Power6 and Cell and will be used in the next commit to disable the code that gets the destination address aligned on those CPUs where doing that doesn't improve performance. Signed-off-by: Mark Nelson Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/cputable.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 1e94b07a020e..803d174dae29 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -194,6 +194,7 @@ extern const char *powerpc_base_platform; #define CPU_FTR_VSX LONG_ASM_CONST(0x0010000000000000) #define CPU_FTR_SAO LONG_ASM_CONST(0x0020000000000000) #define CPU_FTR_CP_USE_DCBTZ LONG_ASM_CONST(0x0040000000000000) +#define CPU_FTR_UNALIGNED_LD_STD LONG_ASM_CONST(0x0080000000000000) #ifndef __ASSEMBLY__ @@ -404,7 +405,7 @@ extern const char *powerpc_base_platform; CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR) + CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD) #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_SMT | \ @@ -415,7 +416,8 @@ extern const char *powerpc_base_platform; CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_PAUSE_ZERO | CPU_FTR_CI_LARGE_PAGE | \ - CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ) + CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \ + CPU_FTR_UNALIGNED_LD_STD) #define CPU_FTRS_PA6T (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_CI_LARGE_PAGE | \ -- cgit v1.2.1 From 53280323350621985b3f2f8ffe649215304bcc5f Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 27 Oct 2008 19:48:29 +0000 Subject: powerpc/pci: Use common PHB resource hookup The 32-bit and 64-bit powerpc PCI code used to set up the resource pointers of the root bus of a given PHB in completely different places. This unifies this in large part, by making 32-bit use a routine very similar to what 64-bit does when initially scanning the PCI busses. The actual setup of the PHB resources itself is then moved to a common function in pci-common.c. This should cause no functional change on 64-bit. On 32-bit, the effect is that the PHB resources are going to be setup a bit earlier, instead of being setup from pcibios_fixup_bus(). Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/pci-bridge.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 9047af7baa69..2dfa8a3d8c76 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -290,6 +290,7 @@ extern void pci_process_bridge_OF_ranges(struct pci_controller *hose, /* Allocate & free a PCI host bridge structure */ extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev); extern void pcibios_free_controller(struct pci_controller *phb); +extern void pcibios_setup_phb_resources(struct pci_controller *hose); #ifdef CONFIG_PCI extern unsigned long pci_address_to_pio(phys_addr_t address); -- cgit v1.2.1 From ab56ced9c57b66862c687f3158045d15133f02d6 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 27 Oct 2008 19:48:33 +0000 Subject: powerpc/pci: Remove pcibios_do_bus_setup() The function pcibios_do_bus_setup() was used by pcibios_fixup_bus() to perform setup that is different between the 32-bit and 64-bit code. This difference no longer exists, thus the function is removed and the setup now done directly from pci-common.c. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 57a2a494886b..55542ac3eadb 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -235,7 +235,6 @@ extern void pci_resource_to_user(const struct pci_dev *dev, int bar, const struct resource *rsrc, resource_size_t *start, resource_size_t *end); -extern void pcibios_do_bus_setup(struct pci_bus *bus); extern void pcibios_fixup_of_probed_bus(struct pci_bus *bus); -- cgit v1.2.1 From 8b8da35804bb89eee23f9bcd5638e1f754bd4c91 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 27 Oct 2008 19:48:37 +0000 Subject: powerpc/pci: Split pcibios_fixup_bus() into bus setup and device setup Currently, our PCI code uses the pcibios_fixup_bus() callback, which is called by the generic code when probing PCI buses, for two different things. One is to set up things related to the bus itself, such as reading bridge resources for P2P bridges, fixing them up, or setting up the iommu's associated with bridges on some platforms. The other is some setup for each individual device under that bridge, mostly setting up DMA mappings and interrupts. The problem is that this approach doesn't work well with PCI hotplug when an existing bus is re-probed for new children. We fix this problem by splitting pcibios_fixup_bus into two routines: pcibios_setup_bus_self() is now called to setup the bus itself pcibios_setup_bus_devices() is now called to setup devices pcibios_fixup_bus() is then modified to call these two after reading the bridge bases, and the OF based PCI probe is modified to avoid calling into the first one when rescanning an existing bridge. [paulus@samba.org - fixed eeh.h for 32-bit compile now that pci-common.c is including it unconditionally.] Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/eeh.h | 8 +++++--- arch/powerpc/include/asm/pci.h | 5 +++-- 2 files changed, 8 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index b886bec67016..66ea9b8b95c5 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -17,8 +17,8 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#ifndef _PPC64_EEH_H -#define _PPC64_EEH_H +#ifndef _POWERPC_EEH_H +#define _POWERPC_EEH_H #ifdef __KERNEL__ #include @@ -110,6 +110,7 @@ static inline void eeh_remove_bus_device(struct pci_dev *dev) { } #define EEH_IO_ERROR_VALUE(size) (-1UL) #endif /* CONFIG_EEH */ +#ifdef CONFIG_PPC64 /* * MMIO read/write operations with EEH support. */ @@ -207,5 +208,6 @@ static inline void eeh_readsl(const volatile void __iomem *addr, void * buf, eeh_check_failure(addr, *(u32*)buf); } +#endif /* CONFIG_PPC64 */ #endif /* __KERNEL__ */ -#endif /* _PPC64_EEH_H */ +#endif /* _POWERPC_EEH_H */ diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 55542ac3eadb..32e03e6d25c5 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -221,6 +221,7 @@ extern void of_scan_pci_bridge(struct device_node *node, struct pci_dev *dev); extern void of_scan_bus(struct device_node *node, struct pci_bus *bus); +extern void of_rescan_bus(struct device_node *node, struct pci_bus *bus); extern int pci_read_irq_line(struct pci_dev *dev); @@ -235,8 +236,8 @@ extern void pci_resource_to_user(const struct pci_dev *dev, int bar, const struct resource *rsrc, resource_size_t *start, resource_size_t *end); -extern void pcibios_fixup_of_probed_bus(struct pci_bus *bus); - +extern void pcibios_setup_bus_devices(struct pci_bus *bus); +extern void pcibios_setup_bus_self(struct pci_bus *bus); #endif /* __KERNEL__ */ #endif /* __ASM_POWERPC_PCI_H */ -- cgit v1.2.1 From fd6852c8fa060bd45c82a2593e18f933f6c6204f Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 27 Oct 2008 19:48:52 +0000 Subject: powerpc/pci: Fix various pseries PCI hotplug issues The pseries PCI hotplug code has a number of issues, ranging from incorrect resource setup to crashes, depending on what is added, when, whether it contains a bridge, etc etc.... This fixes a whole bunch of these, while actually simplifying the code a bit, using more generic code in the process and factoring out common code between adding of a PHB, a slot or a device. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/pci-bridge.h | 3 --- arch/powerpc/include/asm/pci.h | 5 ++--- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 2dfa8a3d8c76..fa8b3b724438 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -241,9 +241,6 @@ extern void pcibios_remove_pci_devices(struct pci_bus *bus); /** Discover new pci devices under this bus, and add them */ extern void pcibios_add_pci_devices(struct pci_bus *bus); -extern void pcibios_fixup_new_pci_devices(struct pci_bus *bus); - -extern int pcibios_remove_root_bus(struct pci_controller *phb); static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus) { diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 32e03e6d25c5..1c721a632d8e 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -204,15 +204,14 @@ static inline struct resource *pcibios_select_root(struct pci_dev *pdev, return root; } -extern void pcibios_setup_new_device(struct pci_dev *dev); - extern void pcibios_claim_one_bus(struct pci_bus *b); -extern void pcibios_allocate_bus_resources(struct pci_bus *bus); +extern void pcibios_finish_adding_to_bus(struct pci_bus *bus); extern void pcibios_resource_survey(void); extern struct pci_controller *init_phb_dynamic(struct device_node *dn); +extern int remove_phb_dynamic(struct pci_controller *phb); extern struct pci_dev *of_create_pci_dev(struct device_node *node, struct pci_bus *bus, int devfn); -- cgit v1.2.1 From c73049f6aa58ac1d1a9ca8cb2b415ef97240b2d3 Mon Sep 17 00:00:00 2001 From: Mark Nelson Date: Mon, 27 Oct 2008 20:38:14 +0000 Subject: powerpc: Remove map_/unmap_single() from dma_mapping_ops Now that all of the remaining dma_mapping_ops have had their map_/unmap_single functions updated to become map/unmap_page functions, there is no need to have the map_/unmap_single function pointers in the dma_mapping_ops. So, this removes them and also removes the code that does the checking for which set of functions to use. Signed-off-by: Mark Nelson Acked-by: Becky Bruce Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/dma-mapping.h | 36 +++++----------------------------- 1 file changed, 5 insertions(+), 31 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index fddb229bd74f..3c4a2c21d606 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -60,12 +60,6 @@ struct dma_mapping_ops { dma_addr_t *dma_handle, gfp_t flag); void (*free_coherent)(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle); - dma_addr_t (*map_single)(struct device *dev, void *ptr, - size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs); - void (*unmap_single)(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs); int (*map_sg)(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, struct dma_attrs *attrs); @@ -149,10 +143,9 @@ static inline int dma_set_mask(struct device *dev, u64 dma_mask) } /* - * TODO: map_/unmap_single will ideally go away, to be completely - * replaced by map/unmap_page. Until then, we allow dma_ops to have - * one or the other, or both by checking to see if the specific - * function requested exists; and if not, falling back on the other set. + * map_/unmap_single actually call through to map/unmap_page now that all the + * dma_mapping_ops have been converted over. We just have to get the page and + * offset to pass through to map_page */ static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *cpu_addr, @@ -164,10 +157,6 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev, BUG_ON(!dma_ops); - if (dma_ops->map_single) - return dma_ops->map_single(dev, cpu_addr, size, direction, - attrs); - return dma_ops->map_page(dev, virt_to_page(cpu_addr), (unsigned long)cpu_addr % PAGE_SIZE, size, direction, attrs); @@ -183,11 +172,6 @@ static inline void dma_unmap_single_attrs(struct device *dev, BUG_ON(!dma_ops); - if (dma_ops->unmap_single) { - dma_ops->unmap_single(dev, dma_addr, size, direction, attrs); - return; - } - dma_ops->unmap_page(dev, dma_addr, size, direction, attrs); } @@ -201,12 +185,7 @@ static inline dma_addr_t dma_map_page_attrs(struct device *dev, BUG_ON(!dma_ops); - if (dma_ops->map_page) - return dma_ops->map_page(dev, page, offset, size, direction, - attrs); - - return dma_ops->map_single(dev, page_address(page) + offset, size, - direction, attrs); + return dma_ops->map_page(dev, page, offset, size, direction, attrs); } static inline void dma_unmap_page_attrs(struct device *dev, @@ -219,12 +198,7 @@ static inline void dma_unmap_page_attrs(struct device *dev, BUG_ON(!dma_ops); - if (dma_ops->unmap_page) { - dma_ops->unmap_page(dev, dma_address, size, direction, attrs); - return; - } - - dma_ops->unmap_single(dev, dma_address, size, direction, attrs); + dma_ops->unmap_page(dev, dma_address, size, direction, attrs); } static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, -- cgit v1.2.1 From 597bc5c00b666fe123abb0af64f6e86f7ab72a90 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 27 Oct 2008 23:56:03 +0000 Subject: powerpc: Improve resolution of VDSO clock_gettime Currently the clock_gettime implementation in the VDSO produces a result with microsecond resolution for the cases that are handled without a system call, i.e. CLOCK_REALTIME and CLOCK_MONOTONIC. The nanoseconds field of the result is obtained by computing a microseconds value and multiplying by 1000. This changes the code in the VDSO to do the computation for clock_gettime with nanosecond resolution. That means that the resolution of the result will ultimately depend on the timebase frequency. Because the timestamp in the VDSO datapage (stamp_xsec, the real time corresponding to the timebase count in tb_orig_stamp) is in units of 2^-20 seconds, it doesn't have sufficient resolution for computing a result with nanosecond resolution. Therefore this adds a copy of xtime to the VDSO datapage and updates it in update_gtod() along with the other time-related fields. Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/vdso_datapage.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index f01393224b52..13c2c283e178 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -39,6 +39,7 @@ #ifndef __ASSEMBLY__ #include +#include #define SYSCALL_MAP_SIZE ((__NR_syscalls + 31) / 32) @@ -83,6 +84,7 @@ struct vdso_data { __u32 icache_log_block_size; /* L1 i-cache log block size */ __s32 wtom_clock_sec; /* Wall to monotonic clock */ __s32 wtom_clock_nsec; + struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ }; @@ -102,6 +104,7 @@ struct vdso_data { __u32 tz_dsttime; /* Type of dst correction 0x5C */ __s32 wtom_clock_sec; /* Wall to monotonic clock */ __s32 wtom_clock_nsec; + struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 dcache_block_size; /* L1 d-cache block size */ __u32 icache_block_size; /* L1 i-cache block size */ -- cgit v1.2.1 From 3cc698789a3f44dabc5eed389b6c123caf787c0f Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Tue, 28 Oct 2008 00:18:11 +0000 Subject: powerpc: Eliminate unused do_gtod variable Since we started using the generic timekeeping code, we haven't had a powerpc-specific version of do_gettimeofday, and hence there is now nothing that reads the do_gtod variable in arch/powerpc/kernel/time.c. This therefore removes it and the code that sets it. Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/time.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index febd581ec9b0..27ccb764fdab 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -48,26 +48,6 @@ extern unsigned long ppc_proc_freq; extern unsigned long ppc_tb_freq; #define DEFAULT_TB_FREQ 125000000UL -/* - * By putting all of this stuff into a single struct we - * reduce the number of cache lines touched by do_gettimeofday. - * Both by collecting all of the data in one cache line and - * by touching only one TOC entry on ppc64. - */ -struct gettimeofday_vars { - u64 tb_to_xs; - u64 stamp_xsec; - u64 tb_orig_stamp; -}; - -struct gettimeofday_struct { - unsigned long tb_ticks_per_sec; - struct gettimeofday_vars vars[2]; - struct gettimeofday_vars * volatile varp; - unsigned var_idx; - unsigned tb_to_us; -}; - struct div_result { u64 result_high; u64 result_low; -- cgit v1.2.1 From 1c1b777a5673b57a6c0377ba60a790d05e4a0676 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Wed, 5 Nov 2008 09:51:12 -0800 Subject: powerpc: Use the new byteorder headers Signed-off-by: Harvey Harrison Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/byteorder.h | 38 ++++++++++++++++++++---------------- 1 file changed, 21 insertions(+), 17 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/byteorder.h b/arch/powerpc/include/asm/byteorder.h index b37752214a16..d5de325472e9 100644 --- a/arch/powerpc/include/asm/byteorder.h +++ b/arch/powerpc/include/asm/byteorder.h @@ -11,6 +11,8 @@ #include #include +#define __BIG_ENDIAN + #ifdef __GNUC__ #ifdef __KERNEL__ @@ -21,12 +23,19 @@ static __inline__ __u16 ld_le16(const volatile __u16 *addr) __asm__ __volatile__ ("lhbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr)); return val; } +#define __arch_swab16p ld_le16 static __inline__ void st_le16(volatile __u16 *addr, const __u16 val) { __asm__ __volatile__ ("sthbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr)); } +static inline void __arch_swab16s(__u16 *addr) +{ + st_le16(addr, *addr); +} +#define __arch_swab16s __arch_swab16s + static __inline__ __u32 ld_le32(const volatile __u32 *addr) { __u32 val; @@ -34,13 +43,20 @@ static __inline__ __u32 ld_le32(const volatile __u32 *addr) __asm__ __volatile__ ("lwbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr)); return val; } +#define __arch_swab32p ld_le32 static __inline__ void st_le32(volatile __u32 *addr, const __u32 val) { __asm__ __volatile__ ("stwbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr)); } -static __inline__ __attribute_const__ __u16 ___arch__swab16(__u16 value) +static inline void __arch_swab32s(__u32 *addr) +{ + st_le32(addr, *addr); +} +#define __arch_swab32s __arch_swab32s + +static inline __attribute_const__ __u16 __arch_swab16(__u16 value) { __u16 result; @@ -49,8 +65,9 @@ static __inline__ __attribute_const__ __u16 ___arch__swab16(__u16 value) : "r" (value), "0" (value >> 8)); return result; } +#define __arch_swab16 __arch_swab16 -static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 value) +static inline __attribute_const__ __u32 __arch_swab32(__u32 value) { __u32 result; @@ -61,29 +78,16 @@ static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 value) : "r" (value), "0" (value >> 24)); return result; } - -#define __arch__swab16(x) ___arch__swab16(x) -#define __arch__swab32(x) ___arch__swab32(x) - -/* The same, but returns converted value from the location pointer by addr. */ -#define __arch__swab16p(addr) ld_le16(addr) -#define __arch__swab32p(addr) ld_le32(addr) - -/* The same, but do the conversion in situ, ie. put the value back to addr. */ -#define __arch__swab16s(addr) st_le16(addr,*addr) -#define __arch__swab32s(addr) st_le32(addr,*addr) +#define __arch_swab32 __arch_swab32 #endif /* __KERNEL__ */ -#ifndef __STRICT_ANSI__ -#define __BYTEORDER_HAS_U64__ #ifndef __powerpc64__ #define __SWAB_64_THRU_32__ #endif /* __powerpc64__ */ -#endif /* __STRICT_ANSI__ */ #endif /* __GNUC__ */ -#include +#include #endif /* _ASM_POWERPC_BYTEORDER_H */ -- cgit v1.2.1 From 9b82f3e61758ed897200f0244b63a77c1791bcba Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 30 Oct 2008 08:12:58 +0000 Subject: powerpc/ps3: Replace the flip_ctl logic in ps3av and ps3fb by a mutex Introduce ps3_gpu_mutex to synchronizes GPU-related operations, like: - invoking the L1GPU_CONTEXT_ATTRIBUTE_FB_BLIT command using the lv1_gpu_context_attribute() hypervisor call, - handling the PS3AV_CID_AVB_PARAM packet in the PS3 A/V Settings driver. Signed-off-by: Geert Uytterhoeven Signed-off-by: Geoff Levand Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/ps3.h | 3 +++ arch/powerpc/include/asm/ps3av.h | 4 ---- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h index f9e34c493cbb..4299365590d8 100644 --- a/arch/powerpc/include/asm/ps3.h +++ b/arch/powerpc/include/asm/ps3.h @@ -516,4 +516,7 @@ void ps3_sync_irq(int node); u32 ps3_get_hw_thread_id(int cpu); u64 ps3_get_spe_id(void *arg); +/* mutex synchronizing GPU accesses and video mode changes */ +extern struct mutex ps3_gpu_mutex; + #endif diff --git a/arch/powerpc/include/asm/ps3av.h b/arch/powerpc/include/asm/ps3av.h index 5aa22cffdbd6..cd24ac16660a 100644 --- a/arch/powerpc/include/asm/ps3av.h +++ b/arch/powerpc/include/asm/ps3av.h @@ -740,8 +740,4 @@ extern int ps3av_audio_mute(int); extern int ps3av_audio_mute_analog(int); extern int ps3av_dev_open(void); extern int ps3av_dev_close(void); -extern void ps3av_register_flip_ctl(void (*flip_ctl)(int on, void *data), - void *flip_data); -extern void ps3av_flip_ctl(int on); - #endif /* _ASM_POWERPC_PS3AV_H_ */ -- cgit v1.2.1 From efc3624c9419cad3cca93dfabb7b12664773d2b1 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Wed, 5 Nov 2008 18:39:27 +0000 Subject: powerpc: Tell gcc when we clobber the carry in inline asm We have several instances of inline assembly code that use the addic or addic. instructions, but don't include XER in the list of clobbers. The addic and addic. instructions affect the carry bit, which is in the XER register. This adds "xer" to the list of clobbers for those inline asm statements that use addic or addic. and didn't already have it. Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/atomic.h | 18 +++++++++--------- arch/powerpc/include/asm/local.h | 4 ++-- arch/powerpc/include/asm/spinlock.h | 2 +- 3 files changed, 12 insertions(+), 12 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index f3fc733758f5..499be5bdd6fa 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -111,7 +111,7 @@ static __inline__ void atomic_inc(atomic_t *v) bne- 1b" : "=&r" (t), "+m" (v->counter) : "r" (&v->counter) - : "cc"); + : "cc", "xer"); } static __inline__ int atomic_inc_return(atomic_t *v) @@ -128,7 +128,7 @@ static __inline__ int atomic_inc_return(atomic_t *v) ISYNC_ON_SMP : "=&r" (t) : "r" (&v->counter) - : "cc", "memory"); + : "cc", "xer", "memory"); return t; } @@ -155,7 +155,7 @@ static __inline__ void atomic_dec(atomic_t *v) bne- 1b" : "=&r" (t), "+m" (v->counter) : "r" (&v->counter) - : "cc"); + : "cc", "xer"); } static __inline__ int atomic_dec_return(atomic_t *v) @@ -172,7 +172,7 @@ static __inline__ int atomic_dec_return(atomic_t *v) ISYNC_ON_SMP : "=&r" (t) : "r" (&v->counter) - : "cc", "memory"); + : "cc", "xer", "memory"); return t; } @@ -346,7 +346,7 @@ static __inline__ void atomic64_inc(atomic64_t *v) bne- 1b" : "=&r" (t), "+m" (v->counter) : "r" (&v->counter) - : "cc"); + : "cc", "xer"); } static __inline__ long atomic64_inc_return(atomic64_t *v) @@ -362,7 +362,7 @@ static __inline__ long atomic64_inc_return(atomic64_t *v) ISYNC_ON_SMP : "=&r" (t) : "r" (&v->counter) - : "cc", "memory"); + : "cc", "xer", "memory"); return t; } @@ -388,7 +388,7 @@ static __inline__ void atomic64_dec(atomic64_t *v) bne- 1b" : "=&r" (t), "+m" (v->counter) : "r" (&v->counter) - : "cc"); + : "cc", "xer"); } static __inline__ long atomic64_dec_return(atomic64_t *v) @@ -404,7 +404,7 @@ static __inline__ long atomic64_dec_return(atomic64_t *v) ISYNC_ON_SMP : "=&r" (t) : "r" (&v->counter) - : "cc", "memory"); + : "cc", "xer", "memory"); return t; } @@ -431,7 +431,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) "\n\ 2:" : "=&r" (t) : "r" (&v->counter) - : "cc", "memory"); + : "cc", "xer", "memory"); return t; } diff --git a/arch/powerpc/include/asm/local.h b/arch/powerpc/include/asm/local.h index 612d83276653..84b457a3c1bc 100644 --- a/arch/powerpc/include/asm/local.h +++ b/arch/powerpc/include/asm/local.h @@ -67,7 +67,7 @@ static __inline__ long local_inc_return(local_t *l) bne- 1b" : "=&r" (t) : "r" (&(l->a.counter)) - : "cc", "memory"); + : "cc", "xer", "memory"); return t; } @@ -94,7 +94,7 @@ static __inline__ long local_dec_return(local_t *l) bne- 1b" : "=&r" (t) : "r" (&(l->a.counter)) - : "cc", "memory"); + : "cc", "xer", "memory"); return t; } diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index f56a843f4705..36864364e601 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -277,7 +277,7 @@ static inline void __raw_read_unlock(raw_rwlock_t *rw) bne- 1b" : "=&r"(tmp) : "r"(&rw->lock) - : "cr0", "memory"); + : "cr0", "xer", "memory"); } static inline void __raw_write_unlock(raw_rwlock_t *rw) -- cgit v1.2.1 From 46d075be585eae2b74265e4e64ca38dde16a09c6 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Tue, 11 Nov 2008 17:50:48 +0000 Subject: powerpc: Optimise smp_wmb Change 2d1b2027626d5151fff8ef7c06ca8e7876a1a510 ("powerpc: Fixup lwsync at runtime") removed __SUBARCH_HAS_LWSYNC, causing smp_wmb to revert back to eieio for all CPUs. This restores the behaviour intorduced in 74f0609526afddd88bef40b651da24f3167b10b2 ("powerpc: Optimise smp_wmb on 64-bit processors"). Signed-off-by: Nick Piggin Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/synch.h | 4 ++++ arch/powerpc/include/asm/system.h | 4 ++-- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h index 45963e80f557..28f6ddbff4cf 100644 --- a/arch/powerpc/include/asm/synch.h +++ b/arch/powerpc/include/asm/synch.h @@ -5,6 +5,10 @@ #include #include +#if defined(__powerpc64__) || defined(CONFIG_PPC_E500MC) +#define __SUBARCH_HAS_LWSYNC +#endif + #ifndef __ASSEMBLY__ extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup; extern void do_lwsync_fixups(unsigned long value, void *fixup_start, diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h index d6648c143322..917f515bc671 100644 --- a/arch/powerpc/include/asm/system.h +++ b/arch/powerpc/include/asm/system.h @@ -45,14 +45,14 @@ #ifdef CONFIG_SMP #ifdef __SUBARCH_HAS_LWSYNC -# define SMPWMB lwsync +# define SMPWMB LWSYNC #else # define SMPWMB eieio #endif #define smp_mb() mb() #define smp_rmb() rmb() -#define smp_wmb() __asm__ __volatile__ (__stringify(SMPWMB) : : :"memory") +#define smp_wmb() __asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory") #define smp_read_barrier_depends() read_barrier_depends() #else #define smp_mb() barrier() -- cgit v1.2.1 From 957ab07b44d839ee8267e827fc4e8f1853798f57 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Tue, 11 Nov 2008 17:51:18 +0000 Subject: powerpc: Optimise smp_rmb After commit 598056d5af8fef1dbe8f96f5c2b641a528184e5a ("[POWERPC] Fix rmb to order cacheable vs. noncacheable"), rmb() becomes a sync instruction, which is needed to order cacheable vs noncacheable loads. However smp_rmb() is #defined to rmb(), and smp_rmb() can be an lwsync. This restores smp_rmb() performance by using lwsync there and updates the comments. Signed-off-by: Nick Piggin Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/system.h | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h index 917f515bc671..2a4be19a92c4 100644 --- a/arch/powerpc/include/asm/system.h +++ b/arch/powerpc/include/asm/system.h @@ -23,15 +23,17 @@ * read_barrier_depends() prevents data-dependent loads being reordered * across this point (nop on PPC). * - * We have to use the sync instructions for mb(), since lwsync doesn't - * order loads with respect to previous stores. Lwsync is fine for - * rmb(), though. Note that rmb() actually uses a sync on 32-bit - * architectures. + * *mb() variants without smp_ prefix must order all types of memory + * operations with one another. sync is the only instruction sufficient + * to do this. * - * For wmb(), we use sync since wmb is used in drivers to order - * stores to system memory with respect to writes to the device. - * However, smp_wmb() can be a lighter-weight lwsync or eieio barrier - * on SMP since it is only used to order updates to system memory. + * For the smp_ barriers, ordering is for cacheable memory operations + * only. We have to use the sync instruction for smp_mb(), since lwsync + * doesn't order loads with respect to previous stores. Lwsync can be + * used for smp_rmb() and smp_wmb(). + * + * However, on CPUs that don't support lwsync, lwsync actually maps to a + * heavy-weight sync, so smp_wmb() can be a lighter-weight eieio. */ #define mb() __asm__ __volatile__ ("sync" : : : "memory") #define rmb() __asm__ __volatile__ ("sync" : : : "memory") @@ -51,7 +53,7 @@ #endif #define smp_mb() mb() -#define smp_rmb() rmb() +#define smp_rmb() __asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory") #define smp_wmb() __asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory") #define smp_read_barrier_depends() read_barrier_depends() #else -- cgit v1.2.1 From ae564c63b8311fa73c21e456e00dba1f4b1ff6bc Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Tue, 11 Nov 2008 17:54:15 +0000 Subject: powerpc: Optimise mutex This implements an optimised mutex fastpath for powerpc, making use of acquire and release barrier semantics. This takes the mutex lock+unlock benchmark from 203 to 173 cycles on a G5. Signed-off-by: Nick Piggin Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/mutex.h | 135 +++++++++++++++++++++++++++++++++++++-- 1 file changed, 130 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/mutex.h b/arch/powerpc/include/asm/mutex.h index 458c1f7fbc18..dabc01c727b8 100644 --- a/arch/powerpc/include/asm/mutex.h +++ b/arch/powerpc/include/asm/mutex.h @@ -1,9 +1,134 @@ /* - * Pull in the generic implementation for the mutex fastpath. + * Optimised mutex implementation of include/asm-generic/mutex-dec.h algorithm + */ +#ifndef _ASM_POWERPC_MUTEX_H +#define _ASM_POWERPC_MUTEX_H + +static inline int __mutex_cmpxchg_lock(atomic_t *v, int old, int new) +{ + int t; + + __asm__ __volatile__ ( +"1: lwarx %0,0,%1 # mutex trylock\n\ + cmpw 0,%0,%2\n\ + bne- 2f\n" + PPC405_ERR77(0,%1) +" stwcx. %3,0,%1\n\ + bne- 1b" + ISYNC_ON_SMP + "\n\ +2:" + : "=&r" (t) + : "r" (&v->counter), "r" (old), "r" (new) + : "cc", "memory"); + + return t; +} + +static inline int __mutex_dec_return_lock(atomic_t *v) +{ + int t; + + __asm__ __volatile__( +"1: lwarx %0,0,%1 # mutex lock\n\ + addic %0,%0,-1\n" + PPC405_ERR77(0,%1) +" stwcx. %0,0,%1\n\ + bne- 1b" + ISYNC_ON_SMP + : "=&r" (t) + : "r" (&v->counter) + : "cc", "memory"); + + return t; +} + +static inline int __mutex_inc_return_unlock(atomic_t *v) +{ + int t; + + __asm__ __volatile__( + LWSYNC_ON_SMP +"1: lwarx %0,0,%1 # mutex unlock\n\ + addic %0,%0,1\n" + PPC405_ERR77(0,%1) +" stwcx. %0,0,%1 \n\ + bne- 1b" + : "=&r" (t) + : "r" (&v->counter) + : "cc", "memory"); + + return t; +} + +/** + * __mutex_fastpath_lock - try to take the lock by moving the count + * from 1 to a 0 value + * @count: pointer of type atomic_t + * @fail_fn: function to call if the original value was not 1 + * + * Change the count from 1 to a value lower than 1, and call if + * it wasn't 1 originally. This function MUST leave the value lower than + * 1 even when the "1" assertion wasn't true. + */ +static inline void +__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) +{ + if (unlikely(__mutex_dec_return_lock(count) < 0)) + fail_fn(count); +} + +/** + * __mutex_fastpath_lock_retval - try to take the lock by moving the count + * from 1 to a 0 value + * @count: pointer of type atomic_t + * @fail_fn: function to call if the original value was not 1 + * + * Change the count from 1 to a value lower than 1, and call if + * it wasn't 1 originally. This function returns 0 if the fastpath succeeds, + * or anything the slow path function returns. + */ +static inline int +__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *)) +{ + if (unlikely(__mutex_dec_return_lock(count) < 0)) + return fail_fn(count); + return 0; +} + +/** + * __mutex_fastpath_unlock - try to promote the count from 0 to 1 + * @count: pointer of type atomic_t + * @fail_fn: function to call if the original value was not 0 + * + * Try to promote the count from 0 to 1. If it wasn't 0, call . + * In the failure case, this function is allowed to either set the value to + * 1, or to set it to a value lower than 1. + */ +static inline void +__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) +{ + if (unlikely(__mutex_inc_return_unlock(count) <= 0)) + fail_fn(count); +} + +#define __mutex_slowpath_needs_to_unlock() 1 + +/** + * __mutex_fastpath_trylock - try to acquire the mutex, without waiting + * + * @count: pointer of type atomic_t + * @fail_fn: fallback function * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) + * Change the count from 1 to 0, and return 1 (success), or if the count + * was not 1, then return 0 (failure). */ +static inline int +__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) +{ + if (likely(__mutex_cmpxchg_lock(count, 1, 0) == 1)) + return 1; + return 0; +} -#include +#endif -- cgit v1.2.1 From 25ddd738c2ebffb6c2d3cf29c91b986d1bb39c99 Mon Sep 17 00:00:00 2001 From: Milton Miller Date: Fri, 14 Nov 2008 20:11:49 +0000 Subject: powerpc: Provide a separate handler for each IPI action With the new generic smp call function helpers, I noticed the code in smp_message_recv was a single function call in many cases. While getting the message number from the ipi data is easy, we can reduce the path length by a function and data-dependent switch by registering seperate IPI actions for these simple calls. Originally I left the ipi action array exposed, but then I realized the registration code should be common too. The three users each had their own name array, so I made a fourth to convert all users to use a common one. Signed-off-by: Milton Miller Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/smp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 1866cec4f967..c25f73d1d842 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -81,6 +81,13 @@ extern int cpu_to_core_id(int cpu); #define PPC_MSG_CALL_FUNC_SINGLE 2 #define PPC_MSG_DEBUGGER_BREAK 3 +/* + * irq controllers that have dedicated ipis per message and don't + * need additional code in the action handler may use this + */ +extern int smp_request_message_ipi(int virq, int message); +extern const char *smp_ipi_name[]; + void smp_init_iSeries(void); void smp_init_pSeries(void); void smp_init_cell(void); -- cgit v1.2.1 From 8fd6e5a8c81e2e9b912ea33c8425a10729db469b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 14 Nov 2008 16:21:19 -0800 Subject: powerpc: ftrace, convert to new dynamic ftrace arch API Impact: update to PowerPC ftrace arch API This patch converts PowerPC to use the new dynamic ftrace arch API. Thanks to Paul Mackennas for pointing out the mistakes of my original test_24bit_addr function. Signed-off-by: Steven Rostedt --- arch/powerpc/include/asm/ftrace.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index b298f7a631e6..17efecc2bf03 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -7,7 +7,19 @@ #ifndef __ASSEMBLY__ extern void _mcount(void); -#endif + +#ifdef CONFIG_DYNAMIC_FTRACE +static inline unsigned long ftrace_call_adjust(unsigned long addr) +{ + /* reloction of mcount call site is the same as the address */ + return addr; +} + +struct dyn_arch_ftrace { + /* nothing yet */ +}; +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* __ASSEMBLY__ */ #endif -- cgit v1.2.1 From f48cb8b48b0b10025ca9c451b9b32cac3fcd33ba Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 14 Nov 2008 20:47:03 -0800 Subject: powerpc/ppc64: ftrace, handle module trampolines for dyn ftrace Impact: Allow 64 bit PowerPC to trace modules with dynamic ftrace This adds code to handle the PPC64 module trampolines, and allows for PPC64 to use dynamic ftrace. Thanks to Paul Mackerras for these updates: - fix the mod and rec->arch.mod NULL checks. - fix to is_bl_op compare. Thanks to Milton Miller for: - finding the nasty race with using two nops, and recommending instead that I use a branch 8 forward. Signed-off-by: Steven Rostedt --- arch/powerpc/include/asm/ftrace.h | 2 +- arch/powerpc/include/asm/module.h | 11 +++++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index 17efecc2bf03..e5f2ae8362f7 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -16,7 +16,7 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) } struct dyn_arch_ftrace { - /* nothing yet */ + struct module *mod; }; #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index e5f14b13ccf0..340bc699b620 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -34,6 +34,11 @@ struct mod_arch_specific { #ifdef __powerpc64__ unsigned int stubs_section; /* Index of stubs section in module */ unsigned int toc_section; /* What section is the TOC? */ +#ifdef CONFIG_DYNAMIC_FTRACE + unsigned long toc; + unsigned long tramp; +#endif + #else /* Indices of PLT sections within module. */ unsigned int core_plt_section; @@ -68,6 +73,12 @@ struct mod_arch_specific { # endif /* MODULE */ #endif +#ifdef CONFIG_DYNAMIC_FTRACE +# ifdef MODULE + asm(".section .ftrace.tramp,\"ax\",@nobits; .align 3; .previous"); +# endif /* MODULE */ +#endif + struct exception_table_entry; void sort_ex_table(struct exception_table_entry *start, -- cgit v1.2.1 From 7cc45e64323c8a1042f56e6a8d1dc982f98d52a8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Sat, 15 Nov 2008 02:39:05 -0500 Subject: powerpc/ppc32: ftrace, dynamic ftrace to handle modules Impact: add ability to trace modules on 32 bit PowerPC This patch performs the necessary trampoline calls to handle modules with dynamic ftrace on 32 bit PowerPC. Signed-off-by: Steven Rostedt --- arch/powerpc/include/asm/module.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index 340bc699b620..08454880a2c0 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -39,11 +39,14 @@ struct mod_arch_specific { unsigned long tramp; #endif -#else +#else /* powerpc64 */ /* Indices of PLT sections within module. */ unsigned int core_plt_section; unsigned int init_plt_section; +#ifdef CONFIG_DYNAMIC_FTRACE + unsigned long tramp; #endif +#endif /* powerpc64 */ /* List of BUG addresses, source line numbers and filenames */ struct list_head bug_list; -- cgit v1.2.1 From 4ee5f55175a85fc179c93f00dd7f6a99c896f4d6 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 27 Nov 2008 20:05:05 +0000 Subject: powerpc: Fix ppc32 mm_struct CPU tracking in SMP The 32-bit hash code didn't need it so far so we don't update mm->cpu_vm_mask on context switch. This however will break when we merge the RCU based page table freeing patch and other upcoming 32-bit embedded SMP work, so this adds the update. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/mmu_context.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 6b993ef452ff..b570209b71a8 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -180,6 +180,9 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, tsk->thread.pgdir = next->pgd; + if (!cpu_isset(smp_processor_id(), next->cpu_vm_mask)) + cpu_set(smp_processor_id(), next->cpu_vm_mask); + /* No need to flush userspace segments if the mm doesnt change */ if (prev == next) return; -- cgit v1.2.1 From df3b8611554e389e703fa753540289874fa5126c Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Wed, 19 Nov 2008 05:53:24 +0000 Subject: powerpc: Add a local_flush_tlb_page to handle kmap_atomic invalidates The tlb invalidates in kmap_atomic/kunmap_atomic can be called from IRQ context, however they are only local invalidates (on the processor that the kmap was called on). In the future we want to use IPIs to do tlb invalidates this causes issue since flush_tlb_page() is considered a broadcast invalidate. Add local_flush_tlb_page() as a non-broadcast invalidate and use it in kmap_atomic() since we don't have enough information in the flush_tlb_page() call to determine its local. Signed-off-by: Kumar Gala Acked-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/highmem.h | 4 ++-- arch/powerpc/include/asm/tlbflush.h | 14 ++++++++++++++ 2 files changed, 16 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h index 91c589520c0a..7dc52eca8b67 100644 --- a/arch/powerpc/include/asm/highmem.h +++ b/arch/powerpc/include/asm/highmem.h @@ -85,7 +85,7 @@ static inline void *kmap_atomic_prot(struct page *page, enum km_type type, pgpro BUG_ON(!pte_none(*(kmap_pte-idx))); #endif __set_pte_at(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot)); - flush_tlb_page(NULL, vaddr); + local_flush_tlb_page(vaddr); return (void*) vaddr; } @@ -113,7 +113,7 @@ static inline void kunmap_atomic(void *kvaddr, enum km_type type) * this pte without first remap it */ pte_clear(&init_mm, vaddr, kmap_pte-idx); - flush_tlb_page(NULL, vaddr); + local_flush_tlb_page(vaddr); #endif pagefault_enable(); } diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h index a2c6bfd85fb7..93716a9f4e16 100644 --- a/arch/powerpc/include/asm/tlbflush.h +++ b/arch/powerpc/include/asm/tlbflush.h @@ -6,6 +6,7 @@ * * - flush_tlb_mm(mm) flushes the specified mm context TLB's * - flush_tlb_page(vma, vmaddr) flushes one page + * - local_flush_tlb_page(vmaddr) flushes one page on the local processor * - flush_tlb_page_nohash(vma, vmaddr) flushes one page if SW loaded TLB * - flush_tlb_range(vma, start, end) flushes a range of pages * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages @@ -44,6 +45,11 @@ static inline void flush_tlb_mm(struct mm_struct *mm) _tlbil_pid(mm->context.id); } +static inline void local_flush_tlb_page(unsigned long vmaddr) +{ + _tlbil_va(vmaddr, 0); +} + static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) { @@ -81,6 +87,10 @@ extern void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +static inline void local_flush_tlb_page(unsigned long vmaddr) +{ + flush_tlb_page(NULL, vmaddr); +} #else /* @@ -138,6 +148,10 @@ static inline void flush_tlb_mm(struct mm_struct *mm) { } +static inline void local_flush_tlb_page(unsigned long vmaddr) +{ +} + static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) { -- cgit v1.2.1 From 0186f47e703fb7aa14b54459d642ef5374b3a685 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Wed, 19 Nov 2008 12:50:04 +0000 Subject: powerpc: Use RCU based pte freeing mechanism for all powerpc Refactor the RCU based pte free code that was used on ppc64 to be used on all powerpc. Additionally refactor pte_free() & pte_free_kernel() into common code between ppc32 & ppc64. Signed-off-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/pgalloc-32.h | 11 +++++++--- arch/powerpc/include/asm/pgalloc-64.h | 34 ----------------------------- arch/powerpc/include/asm/pgalloc.h | 41 +++++++++++++++++++++++++++++++++++ 3 files changed, 49 insertions(+), 37 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/pgalloc-32.h b/arch/powerpc/include/asm/pgalloc-32.h index 58c07147b3ea..0815eb40acae 100644 --- a/arch/powerpc/include/asm/pgalloc-32.h +++ b/arch/powerpc/include/asm/pgalloc-32.h @@ -3,6 +3,8 @@ #include +#define PTE_NONCACHE_NUM 0 /* dummy for now to share code w/ppc64 */ + extern void __bad_pte(pmd_t *pmd); extern pgd_t *pgd_alloc(struct mm_struct *mm); @@ -33,10 +35,13 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr); extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr); -extern void pte_free_kernel(struct mm_struct *mm, pte_t *pte); -extern void pte_free(struct mm_struct *mm, pgtable_t pte); -#define __pte_free_tlb(tlb, pte) pte_free((tlb)->mm, (pte)) +static inline void pgtable_free(pgtable_free_t pgf) +{ + void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK); + + free_page((unsigned long)p); +} #define check_pgt_cache() do { } while (0) diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h index 812a1d8f35cb..afda2bdd860f 100644 --- a/arch/powerpc/include/asm/pgalloc-64.h +++ b/arch/powerpc/include/asm/pgalloc-64.h @@ -7,7 +7,6 @@ * 2 of the License, or (at your option) any later version. */ -#include #include #include #include @@ -108,31 +107,6 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, return page; } -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) -{ - pgtable_page_dtor(ptepage); - __free_page(ptepage); -} - -#define PGF_CACHENUM_MASK 0x7 - -typedef struct pgtable_free { - unsigned long val; -} pgtable_free_t; - -static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum, - unsigned long mask) -{ - BUG_ON(cachenum > PGF_CACHENUM_MASK); - - return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum}; -} - static inline void pgtable_free(pgtable_free_t pgf) { void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK); @@ -144,14 +118,6 @@ static inline void pgtable_free(pgtable_free_t pgf) kmem_cache_free(pgtable_cache[cachenum], p); } -extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf); - -#define __pte_free_tlb(tlb,ptepage) \ -do { \ - pgtable_page_dtor(ptepage); \ - pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \ - PTE_NONCACHE_NUM, PTE_TABLE_SIZE-1)); \ -} while (0) #define __pmd_free_tlb(tlb, pmd) \ pgtable_free_tlb(tlb, pgtable_free_cache(pmd, \ PMD_CACHE_NUM, PMD_TABLE_SIZE-1)) diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h index b4505ed0f0f2..5d8480265a77 100644 --- a/arch/powerpc/include/asm/pgalloc.h +++ b/arch/powerpc/include/asm/pgalloc.h @@ -2,11 +2,52 @@ #define _ASM_POWERPC_PGALLOC_H #ifdef __KERNEL__ +#include + +static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) +{ + free_page((unsigned long)pte); +} + +static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) +{ + pgtable_page_dtor(ptepage); + __free_page(ptepage); +} + +typedef struct pgtable_free { + unsigned long val; +} pgtable_free_t; + +#define PGF_CACHENUM_MASK 0x7 + +static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum, + unsigned long mask) +{ + BUG_ON(cachenum > PGF_CACHENUM_MASK); + + return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum}; +} + #ifdef CONFIG_PPC64 #include #else #include #endif +extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf); + +#ifdef CONFIG_SMP +#define __pte_free_tlb(tlb,ptepage) \ +do { \ + pgtable_page_dtor(ptepage); \ + pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \ + PTE_NONCACHE_NUM, PTE_TABLE_SIZE-1)); \ +} while (0) +#else +#define __pte_free_tlb(tlb, pte) pte_free((tlb)->mm, (pte)) +#endif + + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_PGALLOC_H */ -- cgit v1.2.1 From 15e09c0ecaab4a1b4a7ed69db536c38948b92279 Mon Sep 17 00:00:00 2001 From: Becky Bruce Date: Thu, 20 Nov 2008 06:49:16 +0000 Subject: powerpc: Add sync_*_for_* to dma_ops We need to swap these out once we start using swiotlb, so add them to dma_ops. Create CONFIG_PPC_NEED_DMA_SYNC_OPS Kconfig option; this is currently enabled automatically if we're CONFIG_NOT_COHERENT_CACHE. In the future, this will also be enabled for builds that need swiotlb. If PPC_NEED_DMA_SYNC_OPS is not defined, the dma_sync_*_for_* ops compile to nothing. Otherwise, they access the dma_ops pointers for the sync ops. This patch also changes dma_sync_single_range_* to actually sync the range - previously it was using a generous dma_sync_single. dma_sync_single_* is now implemented as a dma_sync_single_range with an offset of 0. Signed-off-by: Becky Bruce Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/dma-mapping.h | 93 ++++++++++++++++++++++------------ 1 file changed, 62 insertions(+), 31 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index 3c4a2c21d606..9063184fa6fe 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -76,6 +76,22 @@ struct dma_mapping_ops { dma_addr_t dma_address, size_t size, enum dma_data_direction direction, struct dma_attrs *attrs); +#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS + void (*sync_single_range_for_cpu)(struct device *hwdev, + dma_addr_t dma_handle, unsigned long offset, + size_t size, + enum dma_data_direction direction); + void (*sync_single_range_for_device)(struct device *hwdev, + dma_addr_t dma_handle, unsigned long offset, + size_t size, + enum dma_data_direction direction); + void (*sync_sg_for_cpu)(struct device *hwdev, + struct scatterlist *sg, int nelems, + enum dma_data_direction direction); + void (*sync_sg_for_device)(struct device *hwdev, + struct scatterlist *sg, int nelems, + enum dma_data_direction direction); +#endif }; /* @@ -282,47 +298,78 @@ static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg, dma_unmap_sg_attrs(dev, sg, nhwentries, direction, NULL); } +#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction) { - BUG_ON(direction == DMA_NONE); - __dma_sync(bus_to_virt(dma_handle), size, direction); + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + BUG_ON(!dma_ops); + dma_ops->sync_single_range_for_cpu(dev, dma_handle, 0, + size, direction); } static inline void dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction) { - BUG_ON(direction == DMA_NONE); - __dma_sync(bus_to_virt(dma_handle), size, direction); + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + BUG_ON(!dma_ops); + dma_ops->sync_single_range_for_device(dev, dma_handle, + 0, size, direction); } static inline void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction direction) { - struct scatterlist *sg; - int i; - - BUG_ON(direction == DMA_NONE); + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - for_each_sg(sgl, sg, nents, i) - __dma_sync_page(sg_page(sg), sg->offset, sg->length, direction); + BUG_ON(!dma_ops); + dma_ops->sync_sg_for_cpu(dev, sgl, nents, direction); } static inline void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction direction) { - struct scatterlist *sg; - int i; + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - BUG_ON(direction == DMA_NONE); + BUG_ON(!dma_ops); + dma_ops->sync_sg_for_device(dev, sgl, nents, direction); +} + +static inline void dma_sync_single_range_for_cpu(struct device *dev, + dma_addr_t dma_handle, unsigned long offset, size_t size, + enum dma_data_direction direction) +{ + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); - for_each_sg(sgl, sg, nents, i) - __dma_sync_page(sg_page(sg), sg->offset, sg->length, direction); + BUG_ON(!dma_ops); + dma_ops->sync_single_range_for_cpu(dev, dma_handle, + offset, size, direction); +} + +static inline void dma_sync_single_range_for_device(struct device *dev, + dma_addr_t dma_handle, unsigned long offset, size_t size, + enum dma_data_direction direction) +{ + struct dma_mapping_ops *dma_ops = get_dma_ops(dev); + + BUG_ON(!dma_ops); + dma_ops->sync_single_range_for_device(dev, dma_handle, offset, + size, direction); } +#else /* CONFIG_PPC_NEED_DMA_SYNC_OPS */ +#define dma_sync_single_for_cpu(d, h, s, dir) ((void)0) +#define dma_sync_single_for_device(d, h, s, dir) ((void)0) +#define dma_sync_single_range_for_cpu(d, h, o, s, dir) ((void)0) +#define dma_sync_single_range_for_device(d, h, o, s, dir) ((void)0) +#define dma_sync_sg_for_cpu(d, s, n, dir) ((void)0) +#define dma_sync_sg_for_device(d, s, n, dir) ((void)0) +#endif static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { @@ -356,22 +403,6 @@ static inline int dma_get_cache_alignment(void) #endif } -static inline void dma_sync_single_range_for_cpu(struct device *dev, - dma_addr_t dma_handle, unsigned long offset, size_t size, - enum dma_data_direction direction) -{ - /* just sync everything for now */ - dma_sync_single_for_cpu(dev, dma_handle, offset + size, direction); -} - -static inline void dma_sync_single_range_for_device(struct device *dev, - dma_addr_t dma_handle, unsigned long offset, size_t size, - enum dma_data_direction direction) -{ - /* just sync everything for now */ - dma_sync_single_for_device(dev, dma_handle, offset + size, direction); -} - static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size, enum dma_data_direction direction) { -- cgit v1.2.1 From 3f3b1632022fcc8317fa3b3c1236471415b3a6b8 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Fri, 28 Nov 2008 09:13:23 +0000 Subject: powerpc and sparc: Introduce dev_archdata node accessors The name of the device_node field differ across the platforms, so we have to implement inlined accessors. This is needed to avoid ugly #ifdef in the generic code. Signed-off-by: Anton Vorontsov Acked-by: David S. Miller Acked-by: Grant Likely Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/device.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h index dfd504caccc1..7d2277cef09a 100644 --- a/arch/powerpc/include/asm/device.h +++ b/arch/powerpc/include/asm/device.h @@ -18,4 +18,16 @@ struct dev_archdata { void *dma_data; }; +static inline void dev_archdata_set_node(struct dev_archdata *ad, + struct device_node *np) +{ + ad->of_node = np; +} + +static inline struct device_node * +dev_archdata_get_node(const struct dev_archdata *ad) +{ + return ad->of_node; +} + #endif /* _ASM_POWERPC_DEVICE_H */ -- cgit v1.2.1 From cf03033658739accd24f18f864107151a2e9a796 Mon Sep 17 00:00:00 2001 From: Liu Yu Date: Tue, 28 Oct 2008 11:50:18 +0800 Subject: powerpc/math-emu: Fix single float point division bug PowerPC float point division emulation is derived from gcc. I reported this problem on gcc maillist and got this reply: http://gcc.gnu.org/ml/gcc/2008-03/msg00543.html Since UDIV_NEEDS_NORMALIZATION is not used by kernel, we should use _FP_DIV_MEAT_1_udiv_norm to make sure the single float point is normalized before udiv_qrnnd. Signed-off-by: Liu Yu Signed-off-by: Kumar Gala --- arch/powerpc/include/asm/sfp-machine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/sfp-machine.h b/arch/powerpc/include/asm/sfp-machine.h index ced34f1dc8f8..da12ea79cb99 100644 --- a/arch/powerpc/include/asm/sfp-machine.h +++ b/arch/powerpc/include/asm/sfp-machine.h @@ -82,7 +82,7 @@ #define _FP_MUL_MEAT_S(R,X,Y) _FP_MUL_MEAT_1_wide(_FP_WFRACBITS_S,R,X,Y,umul_ppmm) #define _FP_MUL_MEAT_D(R,X,Y) _FP_MUL_MEAT_2_wide(_FP_WFRACBITS_D,R,X,Y,umul_ppmm) -#define _FP_DIV_MEAT_S(R,X,Y) _FP_DIV_MEAT_1_udiv(S,R,X,Y) +#define _FP_DIV_MEAT_S(R,X,Y) _FP_DIV_MEAT_1_udiv_norm(S,R,X,Y) #define _FP_DIV_MEAT_D(R,X,Y) _FP_DIV_MEAT_2_udiv(D,R,X,Y) /* These macros define what NaN looks like. They're supposed to expand to -- cgit v1.2.1 From 463a8c01e153c06480b862d83d6a71bf5666a577 Mon Sep 17 00:00:00 2001 From: Liu Yu Date: Tue, 28 Oct 2008 11:50:19 +0800 Subject: powerpc/math-emu: Adopt new version of _FP_CHOOSENAN Move to using the same macro definition for _FP_CHOOSENAN as s390, sh, sparc32/64. The original author didn't understand this and matched what sparc64 was doing and they have updated to this definition. Signed-off-by: Liu Yu Signed-off-by: Kumar Gala --- arch/powerpc/include/asm/sfp-machine.h | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/sfp-machine.h b/arch/powerpc/include/asm/sfp-machine.h index da12ea79cb99..88af036b1fef 100644 --- a/arch/powerpc/include/asm/sfp-machine.h +++ b/arch/powerpc/include/asm/sfp-machine.h @@ -111,16 +111,24 @@ #define FP_EX_DIVZERO (1 << (31 - 5)) #define FP_EX_INEXACT (1 << (31 - 6)) -/* This macro appears to be called when both X and Y are NaNs, and - * has to choose one and copy it to R. i386 goes for the larger of the - * two, sparc64 just picks Y. I don't understand this at all so I'll - * go with sparc64 because it's shorter :-> -- PMM +/* + * If one NaN is signaling and the other is not, + * we choose that one, otherwise we choose X. */ -#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP) \ - do { \ - R##_s = Y##_s; \ - _FP_FRAC_COPY_##wc(R,Y); \ - R##_c = FP_CLS_NAN; \ +#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP) \ + do { \ + if ((_FP_FRAC_HIGH_RAW_##fs(Y) & _FP_QNANBIT_##fs) \ + && !(_FP_FRAC_HIGH_RAW_##fs(X) & _FP_QNANBIT_##fs)) \ + { \ + R##_s = X##_s; \ + _FP_FRAC_COPY_##wc(R,X); \ + } \ + else \ + { \ + R##_s = Y##_s; \ + _FP_FRAC_COPY_##wc(R,Y); \ + } \ + R##_c = FP_CLS_NAN; \ } while (0) -- cgit v1.2.1 From 6a800f36acd5bf06b5fe2cb27c4d0524d60c3df5 Mon Sep 17 00:00:00 2001 From: Liu Yu Date: Tue, 28 Oct 2008 11:50:21 +0800 Subject: powerpc: Add SPE/EFP math emulation for E500v1/v2 processors. This patch add the handlers of SPE/EFP exceptions. The code is used to emulate float point arithmetic, when MSR(SPE) is enabled and receive EFP data interrupt or EFP round interrupt. This patch has no conflict with or dependence on FP math-emu. The code has been tested by TestFloat. Now the code doesn't support SPE/EFP instructions emulation (it won't be called when receive program interrupt), but it could be easily added. Signed-off-by: Liu Yu Signed-off-by: Kumar Gala --- arch/powerpc/include/asm/processor.h | 6 ++++++ arch/powerpc/include/asm/sfp-machine.h | 36 ++++++++++++++++++++++++---------- 2 files changed, 32 insertions(+), 10 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 101ed87f7d84..cd7a47860e5a 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -207,6 +207,11 @@ struct thread_struct { #define INIT_SP_LIMIT \ (_ALIGN_UP(sizeof(init_thread_info), 16) + (unsigned long) &init_stack) +#ifdef CONFIG_SPE +#define SPEFSCR_INIT .spefscr = SPEFSCR_FINVE | SPEFSCR_FDBZE | SPEFSCR_FUNFE | SPEFSCR_FOVFE, +#else +#define SPEFSCR_INIT +#endif #ifdef CONFIG_PPC32 #define INIT_THREAD { \ @@ -215,6 +220,7 @@ struct thread_struct { .fs = KERNEL_DS, \ .pgdir = swapper_pg_dir, \ .fpexc_mode = MSR_FE0 | MSR_FE1, \ + SPEFSCR_INIT \ } #else #define INIT_THREAD { \ diff --git a/arch/powerpc/include/asm/sfp-machine.h b/arch/powerpc/include/asm/sfp-machine.h index 88af036b1fef..3d9f831c3c55 100644 --- a/arch/powerpc/include/asm/sfp-machine.h +++ b/arch/powerpc/include/asm/sfp-machine.h @@ -97,6 +97,20 @@ #define _FP_KEEPNANFRACP 1 +#ifdef FP_EX_BOOKE_E500_SPE +#define FP_EX_INEXACT (1 << 21) +#define FP_EX_INVALID (1 << 20) +#define FP_EX_DIVZERO (1 << 19) +#define FP_EX_UNDERFLOW (1 << 18) +#define FP_EX_OVERFLOW (1 << 17) +#define FP_INHIBIT_RESULTS 0 + +#define __FPU_FPSCR (current->thread.spefscr) +#define __FPU_ENABLED_EXC \ +({ \ + (__FPU_FPSCR >> 2) & 0x1f; \ +}) +#else /* Exception flags. We use the bit positions of the appropriate bits in the FPSCR, which also correspond to the FE_* bits. This makes everything easier ;-). */ @@ -111,6 +125,18 @@ #define FP_EX_DIVZERO (1 << (31 - 5)) #define FP_EX_INEXACT (1 << (31 - 6)) +#define __FPU_FPSCR (current->thread.fpscr.val) + +/* We only actually write to the destination register + * if exceptions signalled (if any) will not trap. + */ +#define __FPU_ENABLED_EXC \ +({ \ + (__FPU_FPSCR >> 3) & 0x1f; \ +}) + +#endif + /* * If one NaN is signaling and the other is not, * we choose that one, otherwise we choose X. @@ -135,16 +161,6 @@ #include #include -#define __FPU_FPSCR (current->thread.fpscr.val) - -/* We only actually write to the destination register - * if exceptions signalled (if any) will not trap. - */ -#define __FPU_ENABLED_EXC \ -({ \ - (__FPU_FPSCR >> 3) & 0x1f; \ -}) - #define __FPU_TRAP_P(bits) \ ((__FPU_ENABLED_EXC & (bits)) != 0) -- cgit v1.2.1 From b3898895355f73973eb3aef3489e999d3fb8e2bc Mon Sep 17 00:00:00 2001 From: Trent Piepho Date: Wed, 19 Nov 2008 03:13:14 -0800 Subject: powerpc: Better setup of boot page TLB entry The initial TLB mapping for the kernel boot didn't set the memory coherent attribute, MAS2[M], in SMP mode. If this code supported booting a secondary processor, which it doesn't yet, but if it did, then when a secondary processor boots, it would probably signal the primary processor by setting a variable called something like __secondary_hold_acknowledge. However, due to the lack of the M bit, the primary processor would not snoop the transaction (even if a transaction were broadcast). If primary CPU's L1 D-cache had a copy, it would not be flushed and the CPU would never see the ack. Which would have resulted in the primary CPU spinning for a long time, perhaps a full second before it gives up, while it would have waited for the ack from the secondary CPU that it wouldn't have been able to see because of the stale cache. The value of MAS2 for the boot page TLB1 entry is a compile time constant, so there is no need to calculate it in powerpc assembly language. Also, from the MPC8572 manual section 6.12.5.3, "Bits that represent offsets within a page are ignored and should be cleared." Existing code didn't clear them, this code does. The same when the page of KERNELBASE is found; we don't need to use asm to mask the lower 12 bits off. In the code that computes the address to rfi from, don't hard code the offset to 24 bytes, but have the assembler figure that out for us. Signed-off-by: Trent Piepho Signed-off-by: Kumar Gala --- arch/powerpc/include/asm/mmu-fsl-booke.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/mmu-fsl-booke.h b/arch/powerpc/include/asm/mmu-fsl-booke.h index 925d93cf64d8..5588a41f439c 100644 --- a/arch/powerpc/include/asm/mmu-fsl-booke.h +++ b/arch/powerpc/include/asm/mmu-fsl-booke.h @@ -40,6 +40,8 @@ #define MAS2_M 0x00000004 #define MAS2_G 0x00000002 #define MAS2_E 0x00000001 +#define MAS2_EPN_MASK(size) (~0 << (2*(size) + 10)) +#define MAS2_VAL(addr, size, flags) ((addr) & MAS2_EPN_MASK(size) | (flags)) #define MAS3_RPN 0xFFFFF000 #define MAS3_U0 0x00000200 -- cgit v1.2.1 From 8309ce7280536b07716026ff588acbcc0ee1a546 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 12 Dec 2008 17:33:25 +1100 Subject: powerpc: Fix bogus cache flushing on all 40x and BookE processors v2 We were missing the CPU_FTR_NOEXECUTE bit in our cputable for all these processors. The result is that update_mmu_cache() would flush the cache for all pages mapped to userspace which is totally unnecessary on those processors since we already handle flushing on execute in the page fault path. This should provide a nice speed up ;-) Signed-off-by: Benjamin Herrenschmidt Acked-by: Josh Boyer Signed-off-by: Kumar Gala --- arch/powerpc/include/asm/cputable.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 803d174dae29..f3d9d7417166 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -163,6 +163,7 @@ extern const char *powerpc_base_platform; #define CPU_FTR_SPE ASM_CONST(0x0000000002000000) #define CPU_FTR_NEED_PAIRED_STWCX ASM_CONST(0x0000000004000000) #define CPU_FTR_LWSYNC ASM_CONST(0x0000000008000000) +#define CPU_FTR_NOEXECUTE ASM_CONST(0x0000000010000000) /* * Add the 64-bit processor unique features in the top half of the word; @@ -177,7 +178,6 @@ extern const char *powerpc_base_platform; #define CPU_FTR_SLB LONG_ASM_CONST(0x0000000100000000) #define CPU_FTR_16M_PAGE LONG_ASM_CONST(0x0000000200000000) #define CPU_FTR_TLBIEL LONG_ASM_CONST(0x0000000400000000) -#define CPU_FTR_NOEXECUTE LONG_ASM_CONST(0x0000000800000000) #define CPU_FTR_IABR LONG_ASM_CONST(0x0000002000000000) #define CPU_FTR_MMCRA LONG_ASM_CONST(0x0000004000000000) #define CPU_FTR_CTRL LONG_ASM_CONST(0x0000008000000000) @@ -367,19 +367,20 @@ extern const char *powerpc_base_platform; #define CPU_FTRS_CLASSIC32 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | CPU_FTR_HPTE_TABLE) #define CPU_FTRS_8XX (CPU_FTR_USE_TB) -#define CPU_FTRS_40X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN) -#define CPU_FTRS_44X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN) +#define CPU_FTRS_40X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) +#define CPU_FTRS_44X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) #define CPU_FTRS_E200 (CPU_FTR_USE_TB | CPU_FTR_SPE_COMP | \ CPU_FTR_NODSISRALIGN | CPU_FTR_COHERENT_ICACHE | \ - CPU_FTR_UNIFIED_ID_CACHE) + CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_NOEXECUTE) #define CPU_FTRS_E500 (CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \ - CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN) + CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \ + CPU_FTR_NOEXECUTE) #define CPU_FTRS_E500_2 (CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \ CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_BIG_PHYS | \ - CPU_FTR_NODSISRALIGN) + CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) #define CPU_FTRS_E500MC (CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_BIG_PHYS | CPU_FTR_NODSISRALIGN | \ - CPU_FTR_L2CSR | CPU_FTR_LWSYNC) + CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE) #define CPU_FTRS_GENERIC_32 (CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN) /* 64-bit CPUs */ -- cgit v1.2.1 From 15cb1cc981183861e4e653b67a0ea451f720af85 Mon Sep 17 00:00:00 2001 From: Geoff Levand Date: Wed, 3 Dec 2008 13:52:05 +0000 Subject: powerpc: Fix typo in pgtable-ppc64.h Fix a minor comment typo in pgtable-ppc64.h. Signed-off-by: Geoff Levand Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/pgtable-ppc64.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index 4c0a8c62859d..1f0a330f03f4 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -100,7 +100,7 @@ #define _PAGE_WRENABLE (_PAGE_RW | _PAGE_DIRTY) -/* __pgprot defined in arch/powerpc/incliude/asm/page.h */ +/* __pgprot defined in arch/powerpc/include/asm/page.h */ #define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_ACCESSED) #define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_USER) -- cgit v1.2.1 From 46d01492b2c50791b9b66f9b9154ac8d25acaeb9 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 3 Dec 2008 13:52:21 +0000 Subject: powerpc/ps3: Add sub-match id modalias support commit 059e4938f8b060b10c4352e6c45739473bc73267 ("powerpc/ps3: Add a sub-match id to ps3_system_bus") forgot to update the module alias support: - Add the sub-match ids to the module aliases, so udev can distinguish between different types of sub-devices. - Rename PS3_MODULE_ALIAS_GRAPHICS to PS3_MODULE_ALIAS_GPU_FB, as ps3fb binds to the "FB" sub-device. Signed-off-by: Geert Uytterhoeven Signed-off-by: Geoff Levand Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/ps3.h | 53 +++++++++++++++++++++--------------------- 1 file changed, 26 insertions(+), 27 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h index 4299365590d8..cff30c0ef1ff 100644 --- a/arch/powerpc/include/asm/ps3.h +++ b/arch/powerpc/include/asm/ps3.h @@ -305,30 +305,34 @@ static inline const char* ps3_result(int result) /* system bus routines */ enum ps3_match_id { - PS3_MATCH_ID_EHCI = 1, - PS3_MATCH_ID_OHCI = 2, - PS3_MATCH_ID_GELIC = 3, - PS3_MATCH_ID_AV_SETTINGS = 4, - PS3_MATCH_ID_SYSTEM_MANAGER = 5, - PS3_MATCH_ID_STOR_DISK = 6, - PS3_MATCH_ID_STOR_ROM = 7, - PS3_MATCH_ID_STOR_FLASH = 8, - PS3_MATCH_ID_SOUND = 9, - PS3_MATCH_ID_GRAPHICS = 10, - PS3_MATCH_ID_LPM = 11, + PS3_MATCH_ID_EHCI = 1, + PS3_MATCH_ID_OHCI = 2, + PS3_MATCH_ID_GELIC = 3, + PS3_MATCH_ID_AV_SETTINGS = 4, + PS3_MATCH_ID_SYSTEM_MANAGER = 5, + PS3_MATCH_ID_STOR_DISK = 6, + PS3_MATCH_ID_STOR_ROM = 7, + PS3_MATCH_ID_STOR_FLASH = 8, + PS3_MATCH_ID_SOUND = 9, + PS3_MATCH_ID_GPU = 10, + PS3_MATCH_ID_LPM = 11, }; -#define PS3_MODULE_ALIAS_EHCI "ps3:1" -#define PS3_MODULE_ALIAS_OHCI "ps3:2" -#define PS3_MODULE_ALIAS_GELIC "ps3:3" -#define PS3_MODULE_ALIAS_AV_SETTINGS "ps3:4" -#define PS3_MODULE_ALIAS_SYSTEM_MANAGER "ps3:5" -#define PS3_MODULE_ALIAS_STOR_DISK "ps3:6" -#define PS3_MODULE_ALIAS_STOR_ROM "ps3:7" -#define PS3_MODULE_ALIAS_STOR_FLASH "ps3:8" -#define PS3_MODULE_ALIAS_SOUND "ps3:9" -#define PS3_MODULE_ALIAS_GRAPHICS "ps3:10" -#define PS3_MODULE_ALIAS_LPM "ps3:11" +enum ps3_match_sub_id { + PS3_MATCH_SUB_ID_GPU_FB = 1, +}; + +#define PS3_MODULE_ALIAS_EHCI "ps3:1:0" +#define PS3_MODULE_ALIAS_OHCI "ps3:2:0" +#define PS3_MODULE_ALIAS_GELIC "ps3:3:0" +#define PS3_MODULE_ALIAS_AV_SETTINGS "ps3:4:0" +#define PS3_MODULE_ALIAS_SYSTEM_MANAGER "ps3:5:0" +#define PS3_MODULE_ALIAS_STOR_DISK "ps3:6:0" +#define PS3_MODULE_ALIAS_STOR_ROM "ps3:7:0" +#define PS3_MODULE_ALIAS_STOR_FLASH "ps3:8:0" +#define PS3_MODULE_ALIAS_SOUND "ps3:9:0" +#define PS3_MODULE_ALIAS_GPU_FB "ps3:10:1" +#define PS3_MODULE_ALIAS_LPM "ps3:11:0" enum ps3_system_bus_device_type { PS3_DEVICE_TYPE_IOC0 = 1, @@ -337,11 +341,6 @@ enum ps3_system_bus_device_type { PS3_DEVICE_TYPE_LPM, }; -enum ps3_match_sub_id { - /* for PS3_MATCH_ID_GRAPHICS */ - PS3_MATCH_SUB_ID_FB = 1, -}; - /** * struct ps3_system_bus_device - a device on the system bus */ -- cgit v1.2.1 From 0efbb57e06d881a39a7f261e5c33558aedec0f79 Mon Sep 17 00:00:00 2001 From: Becky Bruce Date: Thu, 4 Dec 2008 08:12:40 +0000 Subject: powerpc: Fix !CONFIG_PPC_NEED_DMA_SYNC_OPS build warning Change #define stubs of dma_sync ops to be empty static inlines to avoid build warning. Signed-off-by: Becky Bruce Acked-by: Stephen Rothwell Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/dma-mapping.h | 41 +++++++++++++++++++++++++++++----- 1 file changed, 35 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index 9063184fa6fe..86cef7ddc8d5 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -363,12 +363,41 @@ static inline void dma_sync_single_range_for_device(struct device *dev, size, direction); } #else /* CONFIG_PPC_NEED_DMA_SYNC_OPS */ -#define dma_sync_single_for_cpu(d, h, s, dir) ((void)0) -#define dma_sync_single_for_device(d, h, s, dir) ((void)0) -#define dma_sync_single_range_for_cpu(d, h, o, s, dir) ((void)0) -#define dma_sync_single_range_for_device(d, h, o, s, dir) ((void)0) -#define dma_sync_sg_for_cpu(d, s, n, dir) ((void)0) -#define dma_sync_sg_for_device(d, s, n, dir) ((void)0) +static inline void dma_sync_single_for_cpu(struct device *dev, + dma_addr_t dma_handle, size_t size, + enum dma_data_direction direction) +{ +} + +static inline void dma_sync_single_for_device(struct device *dev, + dma_addr_t dma_handle, size_t size, + enum dma_data_direction direction) +{ +} + +static inline void dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, + enum dma_data_direction direction) +{ +} + +static inline void dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, + enum dma_data_direction direction) +{ +} + +static inline void dma_sync_single_range_for_cpu(struct device *dev, + dma_addr_t dma_handle, unsigned long offset, size_t size, + enum dma_data_direction direction) +{ +} + +static inline void dma_sync_single_range_for_device(struct device *dev, + dma_addr_t dma_handle, unsigned long offset, size_t size, + enum dma_data_direction direction) +{ +} #endif static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) -- cgit v1.2.1 From 6b82b3e4b54b2fce2ca11976c535012b836b2016 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Tue, 9 Dec 2008 09:47:29 +0000 Subject: powerpc: Remove `have_of' global variable The `have_of' variable is a relic from the arch/ppc time, it isn't useful nowadays. Signed-off-by: Anton Vorontsov Acked-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/processor.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index cd7a47860e5a..d3466490104a 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -69,8 +69,6 @@ extern int _prep_type; #ifdef __KERNEL__ -extern int have_of; - struct task_struct; void start_thread(struct pt_regs *regs, unsigned long fdptr, unsigned long sp); void release_thread(struct task_struct *); -- cgit v1.2.1 From edc72ac4a0894247a6d3f1157a8ec8d603fff52d Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Thu, 11 Dec 2008 09:14:25 +0000 Subject: powerpc/pseries: Check for GIQ indicator before calling set-indicator Since "Factor out cpu joining/unjoining the GIQ" (b4963255ad5a426f04a0bb15c4315fa4bb40cde9) the WARN_ON in xics_set_cpu_giq() is being triggered during boot on JS20 because the GIQ indicator is not available on that platform. While the warning is harmless and the system runs normally, it's nicer to check for the existence of the indicator before trying to manipulate it. Implement rtas_indicator_present(), which searches the /rtas/rtas-indicators property for the given indicator token, and use this function in xics_set_cpu_giq(). Also use a WARN statement in xics_set_cpu_giq to get better information on failure. Signed-off-by: Nathan Lynch Acked-by: Milton Miller Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/rtas.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 8eaa7b28d9d0..e0175beb4462 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -168,6 +168,7 @@ extern void rtas_os_term(char *str); extern int rtas_get_sensor(int sensor, int index, int *state); extern int rtas_get_power_level(int powerdomain, int *level); extern int rtas_set_power_level(int powerdomain, int level, int *setlevel); +extern bool rtas_indicator_present(int token, int *maxindex); extern int rtas_set_indicator(int indicator, int index, int new_value); extern int rtas_set_indicator_fast(int indicator, int index, int new_value); extern void rtas_progress(char *s, unsigned short hex); -- cgit v1.2.1 From 7fe519c207e3400dea6d67e1d483a16b11608423 Mon Sep 17 00:00:00 2001 From: Josh Boyer Date: Thu, 11 Dec 2008 09:46:44 +0000 Subject: powerpc: Introduce ppc_pci_flags accessors Currently there are a number of platforms that open code access to the ppc_pci_flags global variable. However, that variable is not present if CONFIG_PCI is not set, which can lead to a build break. This introduces a number of accessor functions that are defined to be empty in the case of CONFIG_PCI being disabled. The various platform files in the kernel are updated to use these. Signed-off-by: Josh Boyer Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/pci-bridge.h | 26 +++++++++++++++++++++++++- arch/powerpc/include/asm/pci.h | 4 ++-- 2 files changed, 27 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index fa8b3b724438..84007afabdb5 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -13,7 +13,6 @@ struct device_node; -extern unsigned int ppc_pci_flags; enum { /* Force re-assigning all resources (ignore firmware * setup completely) @@ -36,6 +35,31 @@ enum { /* ... except for domain 0 */ PPC_PCI_COMPAT_DOMAIN_0 = 0x00000020, }; +#ifdef CONFIG_PCI +extern unsigned int ppc_pci_flags; + +static inline void ppc_pci_set_flags(int flags) +{ + ppc_pci_flags = flags; +} + +static inline void ppc_pci_add_flags(int flags) +{ + ppc_pci_flags |= flags; +} + +static inline int ppc_pci_has_flag(int flag) +{ + return (ppc_pci_flags & flag); +} +#else +static inline void ppc_pci_set_flags(int flags) { } +static inline void ppc_pci_add_flags(int flags) { } +static inline int ppc_pci_has_flag(int flag) +{ + return 0; +} +#endif /* diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 1c721a632d8e..3548159a1beb 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -38,8 +38,8 @@ struct pci_dev; * Set this to 1 if you want the kernel to re-assign all PCI * bus numbers (don't do that on ppc64 yet !) */ -#define pcibios_assign_all_busses() (ppc_pci_flags & \ - PPC_PCI_REASSIGN_ALL_BUS) +#define pcibios_assign_all_busses() \ + (ppc_pci_has_flag(PPC_PCI_REASSIGN_ALL_BUS)) #define pcibios_scan_all_fns(a, b) 0 static inline void pcibios_set_master(struct pci_dev *dev) -- cgit v1.2.1 From 3045b3cb0b068c9f7601786841cda1e0b4647bd9 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Sat, 13 Dec 2008 17:44:59 +0000 Subject: powerpc: Remove dead BIO_VMERGE_BOUNDARY definition The block layer dropped the virtual merge feature (b8b3e16cfe6435d961f6aaebcfd52a1ff2a988c5). BIO_VMERGE_BOUNDARY definition is meaningless now (For POWER, BIO_VMERGE_BOUNDARY has been meaningless for a long time since POWER disables the virtual merge feature). Signed-off-by: FUJITA Tomonori Acked-by: Jens Axboe Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/io.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 08266d2728b3..494cd8b0a278 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -713,13 +713,6 @@ static inline void * phys_to_virt(unsigned long address) */ #define page_to_phys(page) ((phys_addr_t)page_to_pfn(page) << PAGE_SHIFT) -/* We do NOT want virtual merging, it would put too much pressure on - * our iommu allocator. Instead, we want drivers to be smart enough - * to coalesce sglists that happen to have been mapped in a contiguous - * way by the iommu - */ -#define BIO_VMERGE_BOUNDARY 0 - /* * 32 bits still uses virt_to_bus() for it's implementation of DMA * mappings se we have to keep it defined here. We also have some old -- cgit v1.2.1 From a58f053b93e15b68e7b5f442316329f68269c8d5 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Sun, 14 Dec 2008 19:44:13 +0000 Subject: powerpc: Fix asm EMIT_BUG_ENTRY with !CONFIG_BUG Instead of not defining it at all, this defines the macro as being empty, thus avoiding ifdef's in call sites when CONFIG_BUG is not set. Also removes an extra whitespace in the existing definition. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/bug.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index e55d1f66b86f..64e1fdca233e 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -3,6 +3,7 @@ #ifdef __KERNEL__ #include + /* * Define an illegal instr to trap on the bug. * We don't use 0 because that marks the end of a function @@ -14,6 +15,7 @@ #ifdef CONFIG_BUG #ifdef __ASSEMBLY__ +#include #ifdef CONFIG_DEBUG_BUGVERBOSE .macro EMIT_BUG_ENTRY addr,file,line,flags .section __bug_table,"a" @@ -26,7 +28,7 @@ .previous .endm #else - .macro EMIT_BUG_ENTRY addr,file,line,flags +.macro EMIT_BUG_ENTRY addr,file,line,flags .section __bug_table,"a" 5001: PPC_LONG \addr .short \flags @@ -113,6 +115,13 @@ #define HAVE_ARCH_BUG_ON #define HAVE_ARCH_WARN_ON #endif /* __ASSEMBLY __ */ +#else +#ifdef __ASSEMBLY__ +.macro EMIT_BUG_ENTRY addr,file,line,flags +.endm +#else /* !__ASSEMBLY__ */ +#define _EMIT_BUG_ENTRY +#endif #endif /* CONFIG_BUG */ #include -- cgit v1.2.1 From 1a37a3fd7f12d8f9f720cceec84e23152e116668 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Sun, 14 Dec 2008 19:44:24 +0000 Subject: powerpc/mm: Add local_flush_tlb_mm() to SW loaded TLB implementations This adds a local_flush_tlb_mm() call as a pre-requisite for some SMP work for BookE processors. Signed-off-by: Benjamin Herrenschmidt Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/tlbflush.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h index 93716a9f4e16..333c24b54379 100644 --- a/arch/powerpc/include/asm/tlbflush.h +++ b/arch/powerpc/include/asm/tlbflush.h @@ -40,6 +40,11 @@ extern void _tlbil_va(unsigned long address, unsigned int pid); extern void _tlbia(void); #endif +static inline void local_flush_tlb_mm(struct mm_struct *mm) +{ + _tlbil_pid(mm->context.id); +} + static inline void flush_tlb_mm(struct mm_struct *mm) { _tlbil_pid(mm->context.id); -- cgit v1.2.1 From e523f723d69cde44e10116d7f49b277da0c6702c Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Wed, 10 Dec 2008 14:46:04 +0000 Subject: powerpc: Add of_find_next_cache_node() We have more than one piece of code that looks up cache nodes manually using the "l2-cache" property. Add a common helper routine which does this and handles ePAPR's "next-level-cache" property as well as powermac. Signed-off-by: Nathan Lynch Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/prom.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index eb3bd2e1c7f6..6ff04185d2aa 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -253,6 +253,9 @@ extern void kdump_move_device_tree(void); /* CPU OF node matching */ struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); +/* cache lookup */ +struct device_node *of_find_next_cache_node(struct device_node *np); + /* Get the MAC address */ extern const void *of_get_mac_address(struct device_node *np); -- cgit v1.2.1 From 6d2170be4561293a6aa821c773687bd3f18e8206 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:22 +0000 Subject: powerpc/4xx: Extended DCR support v2 This adds supports to the "extended" DCR addressing via the indirect mfdcrx/mtdcrx instructions supported by some 4xx cores (440H6 and later). I enabled the feature for now only on AMCC 460 chips. Signed-off-by: Benjamin Herrenschmidt Acked-by: Josh Boyer Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/cputable.h | 7 ++-- arch/powerpc/include/asm/dcr-native.h | 63 ++++++++++++++++++++++++++++------- 2 files changed, 56 insertions(+), 14 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index f3d9d7417166..31888322d76a 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -164,6 +164,7 @@ extern const char *powerpc_base_platform; #define CPU_FTR_NEED_PAIRED_STWCX ASM_CONST(0x0000000004000000) #define CPU_FTR_LWSYNC ASM_CONST(0x0000000008000000) #define CPU_FTR_NOEXECUTE ASM_CONST(0x0000000010000000) +#define CPU_FTR_INDEXED_DCR ASM_CONST(0x0000000020000000) /* * Add the 64-bit processor unique features in the top half of the word; @@ -369,6 +370,8 @@ extern const char *powerpc_base_platform; #define CPU_FTRS_8XX (CPU_FTR_USE_TB) #define CPU_FTRS_40X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) #define CPU_FTRS_44X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) +#define CPU_FTRS_440x6 (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE | \ + CPU_FTR_INDEXED_DCR) #define CPU_FTRS_E200 (CPU_FTR_USE_TB | CPU_FTR_SPE_COMP | \ CPU_FTR_NODSISRALIGN | CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_NOEXECUTE) @@ -455,7 +458,7 @@ enum { CPU_FTRS_40X | #endif #ifdef CONFIG_44x - CPU_FTRS_44X | + CPU_FTRS_44X | CPU_FTRS_440x6 | #endif #ifdef CONFIG_E200 CPU_FTRS_E200 | @@ -495,7 +498,7 @@ enum { CPU_FTRS_40X & #endif #ifdef CONFIG_44x - CPU_FTRS_44X & + CPU_FTRS_44X & CPU_FTRS_440x6 & #endif #ifdef CONFIG_E200 CPU_FTRS_E200 & diff --git a/arch/powerpc/include/asm/dcr-native.h b/arch/powerpc/include/asm/dcr-native.h index 72d2b72c7390..7d2e6235726d 100644 --- a/arch/powerpc/include/asm/dcr-native.h +++ b/arch/powerpc/include/asm/dcr-native.h @@ -23,6 +23,7 @@ #ifndef __ASSEMBLY__ #include +#include typedef struct { unsigned int base; @@ -39,23 +40,45 @@ static inline bool dcr_map_ok_native(dcr_host_native_t host) #define dcr_read_native(host, dcr_n) mfdcr(dcr_n + host.base) #define dcr_write_native(host, dcr_n, value) mtdcr(dcr_n + host.base, value) -/* Device Control Registers */ -void __mtdcr(int reg, unsigned int val); -unsigned int __mfdcr(int reg); +/* Table based DCR accessors */ +extern void __mtdcr(unsigned int reg, unsigned int val); +extern unsigned int __mfdcr(unsigned int reg); + +/* mfdcrx/mtdcrx instruction based accessors. We hand code + * the opcodes in order not to depend on newer binutils + */ +static inline unsigned int mfdcrx(unsigned int reg) +{ + unsigned int ret; + asm volatile(".long 0x7c000206 | (%0 << 21) | (%1 << 16)" + : "=r" (ret) : "r" (reg)); + return ret; +} + +static inline void mtdcrx(unsigned int reg, unsigned int val) +{ + asm volatile(".long 0x7c000306 | (%0 << 21) | (%1 << 16)" + : : "r" (val), "r" (reg)); +} + #define mfdcr(rn) \ ({unsigned int rval; \ - if (__builtin_constant_p(rn)) \ + if (__builtin_constant_p(rn) && rn < 1024) \ asm volatile("mfdcr %0," __stringify(rn) \ : "=r" (rval)); \ + else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR))) \ + rval = mfdcrx(rn); \ else \ rval = __mfdcr(rn); \ rval;}) #define mtdcr(rn, v) \ do { \ - if (__builtin_constant_p(rn)) \ + if (__builtin_constant_p(rn) && rn < 1024) \ asm volatile("mtdcr " __stringify(rn) ",%0" \ : : "r" (v)); \ + else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR))) \ + mtdcrx(rn, v); \ else \ __mtdcr(rn, v); \ } while (0) @@ -69,8 +92,13 @@ static inline unsigned __mfdcri(int base_addr, int base_data, int reg) unsigned int val; spin_lock_irqsave(&dcr_ind_lock, flags); - __mtdcr(base_addr, reg); - val = __mfdcr(base_data); + if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) { + mtdcrx(base_addr, reg); + val = mfdcrx(base_data); + } else { + __mtdcr(base_addr, reg); + val = __mfdcr(base_data); + } spin_unlock_irqrestore(&dcr_ind_lock, flags); return val; } @@ -81,8 +109,13 @@ static inline void __mtdcri(int base_addr, int base_data, int reg, unsigned long flags; spin_lock_irqsave(&dcr_ind_lock, flags); - __mtdcr(base_addr, reg); - __mtdcr(base_data, val); + if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) { + mtdcrx(base_addr, reg); + mtdcrx(base_data, val); + } else { + __mtdcr(base_addr, reg); + __mtdcr(base_data, val); + } spin_unlock_irqrestore(&dcr_ind_lock, flags); } @@ -93,9 +126,15 @@ static inline void __dcri_clrset(int base_addr, int base_data, int reg, unsigned int val; spin_lock_irqsave(&dcr_ind_lock, flags); - __mtdcr(base_addr, reg); - val = (__mfdcr(base_data) & ~clr) | set; - __mtdcr(base_data, val); + if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) { + mtdcrx(base_addr, reg); + val = (mfdcrx(base_data) & ~clr) | set; + mtdcrx(base_data, val); + } else { + __mtdcr(base_addr, reg); + val = (__mfdcr(base_data) & ~clr) | set; + __mtdcr(base_data, val); + } spin_unlock_irqrestore(&dcr_ind_lock, flags); } -- cgit v1.2.1 From 5e696617c425eb97bd943d781f3941fb1e8f0e5b Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:24 +0000 Subject: powerpc/mm: Split mmu_context handling This splits the mmu_context handling between 32-bit hash based processors, 64-bit hash based processors and everybody else. This is preliminary work for adding SMP support for BookE processors. Signed-off-by: Benjamin Herrenschmidt Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/mmu_context.h | 260 +++++---------------------------- 1 file changed, 34 insertions(+), 226 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index b570209b71a8..ab4f19263c42 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -2,240 +2,26 @@ #define __ASM_POWERPC_MMU_CONTEXT_H #ifdef __KERNEL__ +#include +#include +#include +#include #include #include #include - -#ifndef CONFIG_PPC64 -#include -#include - -/* - * On 32-bit PowerPC 6xx/7xx/7xxx CPUs, we use a set of 16 VSIDs - * (virtual segment identifiers) for each context. Although the - * hardware supports 24-bit VSIDs, and thus >1 million contexts, - * we only use 32,768 of them. That is ample, since there can be - * at most around 30,000 tasks in the system anyway, and it means - * that we can use a bitmap to indicate which contexts are in use. - * Using a bitmap means that we entirely avoid all of the problems - * that we used to have when the context number overflowed, - * particularly on SMP systems. - * -- paulus. - */ - -/* - * This function defines the mapping from contexts to VSIDs (virtual - * segment IDs). We use a skew on both the context and the high 4 bits - * of the 32-bit virtual address (the "effective segment ID") in order - * to spread out the entries in the MMU hash table. Note, if this - * function is changed then arch/ppc/mm/hashtable.S will have to be - * changed to correspond. - */ -#define CTX_TO_VSID(ctx, va) (((ctx) * (897 * 16) + ((va) >> 28) * 0x111) \ - & 0xffffff) - -/* - The MPC8xx has only 16 contexts. We rotate through them on each - task switch. A better way would be to keep track of tasks that - own contexts, and implement an LRU usage. That way very active - tasks don't always have to pay the TLB reload overhead. The - kernel pages are mapped shared, so the kernel can run on behalf - of any task that makes a kernel entry. Shared does not mean they - are not protected, just that the ASID comparison is not performed. - -- Dan - - The IBM4xx has 256 contexts, so we can just rotate through these - as a way of "switching" contexts. If the TID of the TLB is zero, - the PID/TID comparison is disabled, so we can use a TID of zero - to represent all kernel pages as shared among all contexts. - -- Dan - */ - -static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) -{ -} - -#ifdef CONFIG_8xx -#define NO_CONTEXT 16 -#define LAST_CONTEXT 15 -#define FIRST_CONTEXT 0 - -#elif defined(CONFIG_4xx) -#define NO_CONTEXT 256 -#define LAST_CONTEXT 255 -#define FIRST_CONTEXT 1 - -#elif defined(CONFIG_E200) || defined(CONFIG_E500) -#define NO_CONTEXT 256 -#define LAST_CONTEXT 255 -#define FIRST_CONTEXT 1 - -#else - -/* PPC 6xx, 7xx CPUs */ -#define NO_CONTEXT ((unsigned long) -1) -#define LAST_CONTEXT 32767 -#define FIRST_CONTEXT 1 -#endif - -/* - * Set the current MMU context. - * On 32-bit PowerPCs (other than the 8xx embedded chips), this is done by - * loading up the segment registers for the user part of the address space. - * - * Since the PGD is immediately available, it is much faster to simply - * pass this along as a second parameter, which is required for 8xx and - * can be used for debugging on all processors (if you happen to have - * an Abatron). - */ -extern void set_context(unsigned long contextid, pgd_t *pgd); - -/* - * Bitmap of contexts in use. - * The size of this bitmap is LAST_CONTEXT + 1 bits. - */ -extern unsigned long context_map[]; - -/* - * This caches the next context number that we expect to be free. - * Its use is an optimization only, we can't rely on this context - * number to be free, but it usually will be. - */ -extern unsigned long next_mmu_context; - -/* - * If we don't have sufficient contexts to give one to every task - * that could be in the system, we need to be able to steal contexts. - * These variables support that. - */ -#if LAST_CONTEXT < 30000 -#define FEW_CONTEXTS 1 -extern atomic_t nr_free_contexts; -extern struct mm_struct *context_mm[LAST_CONTEXT+1]; -extern void steal_context(void); -#endif - -/* - * Get a new mmu context for the address space described by `mm'. - */ -static inline void get_mmu_context(struct mm_struct *mm) -{ - unsigned long ctx; - - if (mm->context.id != NO_CONTEXT) - return; -#ifdef FEW_CONTEXTS - while (atomic_dec_if_positive(&nr_free_contexts) < 0) - steal_context(); -#endif - ctx = next_mmu_context; - while (test_and_set_bit(ctx, context_map)) { - ctx = find_next_zero_bit(context_map, LAST_CONTEXT+1, ctx); - if (ctx > LAST_CONTEXT) - ctx = 0; - } - next_mmu_context = (ctx + 1) & LAST_CONTEXT; - mm->context.id = ctx; -#ifdef FEW_CONTEXTS - context_mm[ctx] = mm; -#endif -} +#include /* - * Set up the context for a new address space. + * Most if the context management is out of line */ -static inline int init_new_context(struct task_struct *t, struct mm_struct *mm) -{ - mm->context.id = NO_CONTEXT; - return 0; -} - -/* - * We're finished using the context for an address space. - */ -static inline void destroy_context(struct mm_struct *mm) -{ - preempt_disable(); - if (mm->context.id != NO_CONTEXT) { - clear_bit(mm->context.id, context_map); - mm->context.id = NO_CONTEXT; -#ifdef FEW_CONTEXTS - atomic_inc(&nr_free_contexts); -#endif - } - preempt_enable(); -} - -static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, - struct task_struct *tsk) -{ -#ifdef CONFIG_ALTIVEC - if (cpu_has_feature(CPU_FTR_ALTIVEC)) - asm volatile ("dssall;\n" -#ifndef CONFIG_POWER4 - "sync;\n" /* G4 needs a sync here, G5 apparently not */ -#endif - : : ); -#endif /* CONFIG_ALTIVEC */ - - tsk->thread.pgdir = next->pgd; - - if (!cpu_isset(smp_processor_id(), next->cpu_vm_mask)) - cpu_set(smp_processor_id(), next->cpu_vm_mask); - - /* No need to flush userspace segments if the mm doesnt change */ - if (prev == next) - return; - - /* Setup new userspace context */ - get_mmu_context(next); - set_context(next->context.id, next->pgd); -} - -#define deactivate_mm(tsk,mm) do { } while (0) - -/* - * After we have set current->mm to a new value, this activates - * the context for the new mm so we see the new mappings. - */ -#define activate_mm(active_mm, mm) switch_mm(active_mm, mm, current) - extern void mmu_context_init(void); - - -#else - -#include -#include -#include - -/* - * Copyright (C) 2001 PPC 64 Team, IBM Corp - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -static inline void enter_lazy_tlb(struct mm_struct *mm, - struct task_struct *tsk) -{ -} - -/* - * The proto-VSID space has 2^35 - 1 segments available for user mappings. - * Each segment contains 2^28 bytes. Each context maps 2^44 bytes, - * so we can support 2^19-1 contexts (19 == 35 + 28 - 44). - */ -#define NO_CONTEXT 0 -#define MAX_CONTEXT ((1UL << 19) - 1) - extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm); extern void destroy_context(struct mm_struct *mm); +extern void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next); extern void switch_stab(struct task_struct *tsk, struct mm_struct *mm); extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm); +extern void set_context(unsigned long id, pgd_t *pgd); /* * switch_mm is the entry point called from the architecture independent @@ -244,22 +30,39 @@ extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm); static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { - if (!cpu_isset(smp_processor_id(), next->cpu_vm_mask)) - cpu_set(smp_processor_id(), next->cpu_vm_mask); + /* Mark this context has been used on the new CPU */ + cpu_set(smp_processor_id(), next->cpu_vm_mask); + + /* 32-bit keeps track of the current PGDIR in the thread struct */ +#ifdef CONFIG_PPC32 + tsk->thread.pgdir = next->pgd; +#endif /* CONFIG_PPC32 */ - /* No need to flush userspace segments if the mm doesnt change */ + /* Nothing else to do if we aren't actually switching */ if (prev == next) return; + /* We must stop all altivec streams before changing the HW + * context + */ #ifdef CONFIG_ALTIVEC if (cpu_has_feature(CPU_FTR_ALTIVEC)) asm volatile ("dssall"); #endif /* CONFIG_ALTIVEC */ + /* The actual HW switching method differs between the various + * sub architectures. + */ +#ifdef CONFIG_PPC_STD_MMU_64 if (cpu_has_feature(CPU_FTR_SLB)) switch_slb(tsk, next); else switch_stab(tsk, next); +#else + /* Out of line for now */ + switch_mmu_context(prev, next); +#endif + } #define deactivate_mm(tsk,mm) do { } while (0) @@ -277,6 +80,11 @@ static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) local_irq_restore(flags); } -#endif /* CONFIG_PPC64 */ +/* We don't currently use enter_lazy_tlb() for anything */ +static inline void enter_lazy_tlb(struct mm_struct *mm, + struct task_struct *tsk) +{ +} + #endif /* __KERNEL__ */ #endif /* __ASM_POWERPC_MMU_CONTEXT_H */ -- cgit v1.2.1 From 2ca8cf738907180e7fbda90f25f32b86feda609f Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:29 +0000 Subject: powerpc/mm: Rework context management for CPUs with no hash table This reworks the context management code used by 4xx,8xx and freescale BookE. It adds support for SMP by implementing a concept of stale context map to lazily flush the TLB on processors where a context may have been invalidated. This also contains the ground work for generalizing such lazy TLB flushing by just picking up a new PID and marking the old one stale. This will be implemented later. This is a first implementation that uses a global spinlock. Ideally, we should try to get at least the fast path (context ID already assigned) lockless or limited to a per context lock, but for now this will do. I tried to keep the UP case reasonably simple to avoid adding too much overhead to 8xx which does a lot of context stealing since it effectively has only 16 PIDs available. Signed-off-by: Benjamin Herrenschmidt Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/mmu-40x.h | 5 +++-- arch/powerpc/include/asm/mmu-44x.h | 5 +++-- arch/powerpc/include/asm/mmu-8xx.h | 3 ++- arch/powerpc/include/asm/mmu-fsl-booke.h | 5 +++-- arch/powerpc/include/asm/tlbflush.h | 2 ++ 5 files changed, 13 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/mmu-40x.h b/arch/powerpc/include/asm/mmu-40x.h index 3d108676584c..776f415a36aa 100644 --- a/arch/powerpc/include/asm/mmu-40x.h +++ b/arch/powerpc/include/asm/mmu-40x.h @@ -54,8 +54,9 @@ #ifndef __ASSEMBLY__ typedef struct { - unsigned long id; - unsigned long vdso_base; + unsigned int id; + unsigned int active; + unsigned long vdso_base; } mm_context_t; #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/mmu-44x.h b/arch/powerpc/include/asm/mmu-44x.h index a825524c981a..b21af32ac6d6 100644 --- a/arch/powerpc/include/asm/mmu-44x.h +++ b/arch/powerpc/include/asm/mmu-44x.h @@ -56,8 +56,9 @@ extern unsigned int tlb_44x_hwater; typedef struct { - unsigned long id; - unsigned long vdso_base; + unsigned int id; + unsigned int active; + unsigned long vdso_base; } mm_context_t; #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h index 9db877eb88db..07865a357848 100644 --- a/arch/powerpc/include/asm/mmu-8xx.h +++ b/arch/powerpc/include/asm/mmu-8xx.h @@ -137,7 +137,8 @@ #ifndef __ASSEMBLY__ typedef struct { - unsigned long id; + unsigned int id; + unsigned int active; unsigned long vdso_base; } mm_context_t; #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/mmu-fsl-booke.h b/arch/powerpc/include/asm/mmu-fsl-booke.h index 5588a41f439c..3f941c0f7e8e 100644 --- a/arch/powerpc/include/asm/mmu-fsl-booke.h +++ b/arch/powerpc/include/asm/mmu-fsl-booke.h @@ -76,8 +76,9 @@ #ifndef __ASSEMBLY__ typedef struct { - unsigned long id; - unsigned long vdso_base; + unsigned int id; + unsigned int active; + unsigned long vdso_base; } mm_context_t; #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h index 333c24b54379..9ed363d3de44 100644 --- a/arch/powerpc/include/asm/tlbflush.h +++ b/arch/powerpc/include/asm/tlbflush.h @@ -29,6 +29,8 @@ #include +#define MMU_NO_CONTEXT ((unsigned int)-1) + extern void _tlbie(unsigned long address, unsigned int pid); extern void _tlbil_all(void); extern void _tlbil_pid(unsigned int pid); -- cgit v1.2.1 From 7c03d653cd257793dc40520c94e229b5fd0578e7 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:32 +0000 Subject: powerpc/mm: Introduce MMU features We're soon running out of CPU features and I need to add some new ones for various MMU related bits, so this patch separates the MMU features from the CPU features. I moved over the 32-bit MMU related ones, added base features for MMU type families, but didn't move over any 64-bit only feature yet. Signed-off-by: Benjamin Herrenschmidt Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/cputable.h | 85 ++++++++++++++----------------- arch/powerpc/include/asm/feature-fixups.h | 30 +++++++++++ arch/powerpc/include/asm/mmu.h | 41 +++++++++++++++ 3 files changed, 108 insertions(+), 48 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 31888322d76a..4911104791c3 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -82,6 +82,7 @@ struct cpu_spec { char *cpu_name; unsigned long cpu_features; /* Kernel features */ unsigned int cpu_user_features; /* Userland features */ + unsigned int mmu_features; /* MMU features */ /* cache line sizes */ unsigned int icache_bsize; @@ -144,17 +145,14 @@ extern const char *powerpc_base_platform; #define CPU_FTR_USE_TB ASM_CONST(0x0000000000000040) #define CPU_FTR_L2CSR ASM_CONST(0x0000000000000080) #define CPU_FTR_601 ASM_CONST(0x0000000000000100) -#define CPU_FTR_HPTE_TABLE ASM_CONST(0x0000000000000200) #define CPU_FTR_CAN_NAP ASM_CONST(0x0000000000000400) #define CPU_FTR_L3CR ASM_CONST(0x0000000000000800) #define CPU_FTR_L3_DISABLE_NAP ASM_CONST(0x0000000000001000) #define CPU_FTR_NAP_DISABLE_L2_PR ASM_CONST(0x0000000000002000) #define CPU_FTR_DUAL_PLL_750FX ASM_CONST(0x0000000000004000) #define CPU_FTR_NO_DPM ASM_CONST(0x0000000000008000) -#define CPU_FTR_HAS_HIGH_BATS ASM_CONST(0x0000000000010000) #define CPU_FTR_NEED_COHERENT ASM_CONST(0x0000000000020000) #define CPU_FTR_NO_BTIC ASM_CONST(0x0000000000040000) -#define CPU_FTR_BIG_PHYS ASM_CONST(0x0000000000080000) #define CPU_FTR_NODSISRALIGN ASM_CONST(0x0000000000100000) #define CPU_FTR_PPC_LE ASM_CONST(0x0000000000200000) #define CPU_FTR_REAL_LE ASM_CONST(0x0000000000400000) @@ -266,107 +264,99 @@ extern const char *powerpc_base_platform; !defined(CONFIG_POWER3) && !defined(CONFIG_POWER4) && \ !defined(CONFIG_BOOKE)) -#define CPU_FTRS_PPC601 (CPU_FTR_COMMON | CPU_FTR_601 | CPU_FTR_HPTE_TABLE | \ +#define CPU_FTRS_PPC601 (CPU_FTR_COMMON | CPU_FTR_601 | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_UNIFIED_ID_CACHE) #define CPU_FTRS_603 (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE) #define CPU_FTRS_604 (CPU_FTR_COMMON | \ - CPU_FTR_USE_TB | CPU_FTR_HPTE_TABLE | CPU_FTR_PPC_LE) + CPU_FTR_USE_TB | CPU_FTR_PPC_LE) #define CPU_FTRS_740_NOTAU (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE) + CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE) #define CPU_FTRS_740 (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \ - CPU_FTR_TAU | CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP | \ + CPU_FTR_TAU | CPU_FTR_MAYBE_CAN_NAP | \ CPU_FTR_PPC_LE) #define CPU_FTRS_750 (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \ - CPU_FTR_TAU | CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP | \ + CPU_FTR_TAU | CPU_FTR_MAYBE_CAN_NAP | \ CPU_FTR_PPC_LE) -#define CPU_FTRS_750CL (CPU_FTRS_750 | CPU_FTR_HAS_HIGH_BATS) +#define CPU_FTRS_750CL (CPU_FTRS_750) #define CPU_FTRS_750FX1 (CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX | CPU_FTR_NO_DPM) #define CPU_FTRS_750FX2 (CPU_FTRS_750 | CPU_FTR_NO_DPM) -#define CPU_FTRS_750FX (CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX | \ - CPU_FTR_HAS_HIGH_BATS) +#define CPU_FTRS_750FX (CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX) #define CPU_FTRS_750GX (CPU_FTRS_750FX) #define CPU_FTRS_7400_NOTAU (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \ - CPU_FTR_ALTIVEC_COMP | CPU_FTR_HPTE_TABLE | \ + CPU_FTR_ALTIVEC_COMP | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE) #define CPU_FTRS_7400 (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | CPU_FTR_L2CR | \ - CPU_FTR_TAU | CPU_FTR_ALTIVEC_COMP | CPU_FTR_HPTE_TABLE | \ + CPU_FTR_TAU | CPU_FTR_ALTIVEC_COMP | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE) #define CPU_FTRS_7450_20 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ + CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \ CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_7450_21 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ + CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \ CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_L3_DISABLE_NAP | \ CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_7450_23 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ + CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \ CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE) #define CPU_FTRS_7455_1 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \ CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | CPU_FTR_HAS_HIGH_BATS | \ - CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE) + CPU_FTR_SPEC7450 | CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE) #define CPU_FTRS_7455_20 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | CPU_FTR_NEED_PAIRED_STWCX | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ + CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \ CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_L3_DISABLE_NAP | \ - CPU_FTR_NEED_COHERENT | CPU_FTR_HAS_HIGH_BATS | CPU_FTR_PPC_LE) + CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE) #define CPU_FTRS_7455 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ - CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \ + CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \ CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_7447_10 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ - CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \ + CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \ CPU_FTR_NEED_COHERENT | CPU_FTR_NO_BTIC | CPU_FTR_PPC_LE | \ CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_7447 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_L3CR | CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ - CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \ + CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \ CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_7447A (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ - CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \ + CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \ CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_7448 (CPU_FTR_COMMON | \ CPU_FTR_USE_TB | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 | \ - CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS | \ + CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \ CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX) #define CPU_FTRS_82XX (CPU_FTR_COMMON | \ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB) #define CPU_FTRS_G2_LE (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \ - CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_HAS_HIGH_BATS) + CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP) #define CPU_FTRS_E300 (CPU_FTR_MAYBE_CAN_DOZE | \ - CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_HAS_HIGH_BATS | \ + CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | \ CPU_FTR_COMMON) #define CPU_FTRS_E300C2 (CPU_FTR_MAYBE_CAN_DOZE | \ - CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_HAS_HIGH_BATS | \ + CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | \ CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE) -#define CPU_FTRS_CLASSIC32 (CPU_FTR_COMMON | \ - CPU_FTR_USE_TB | CPU_FTR_HPTE_TABLE) +#define CPU_FTRS_CLASSIC32 (CPU_FTR_COMMON | CPU_FTR_USE_TB) #define CPU_FTRS_8XX (CPU_FTR_USE_TB) #define CPU_FTRS_40X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) #define CPU_FTRS_44X (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) @@ -379,55 +369,54 @@ extern const char *powerpc_base_platform; CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \ CPU_FTR_NOEXECUTE) #define CPU_FTRS_E500_2 (CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \ - CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_BIG_PHYS | \ + CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | \ CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) #define CPU_FTRS_E500MC (CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \ - CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_BIG_PHYS | CPU_FTR_NODSISRALIGN | \ + CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \ CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE) #define CPU_FTRS_GENERIC_32 (CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN) /* 64-bit CPUs */ #define CPU_FTRS_POWER3 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_IABR | CPU_FTR_PPC_LE) + CPU_FTR_IABR | CPU_FTR_PPC_LE) #define CPU_FTRS_RS64 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_IABR | \ + CPU_FTR_IABR | \ CPU_FTR_MMCRA | CPU_FTR_CTRL) #define CPU_FTRS_POWER4 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_CP_USE_DCBTZ) #define CPU_FTRS_PPC970 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_CAN_NAP | CPU_FTR_MMCRA | \ CPU_FTR_CP_USE_DCBTZ) #define CPU_FTRS_POWER5 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ CPU_FTR_PURR) #define CPU_FTRS_POWER6 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD) #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ CPU_FTR_DSCR | CPU_FTR_SAO) #define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ + CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_PAUSE_ZERO | CPU_FTR_CI_LARGE_PAGE | \ CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \ CPU_FTR_UNALIGNED_LD_STD) #define CPU_FTRS_PA6T (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | \ + CPU_FTR_PPCAS_ARCH_V2 | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_CI_LARGE_PAGE | \ CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_NO_SLBIE_B) -#define CPU_FTRS_COMPATIBLE (CPU_FTR_USE_TB | \ - CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2) +#define CPU_FTRS_COMPATIBLE (CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2) #ifdef __powerpc64__ #define CPU_FTRS_POSSIBLE \ diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index a1029967620b..e4094a5cb05b 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -81,6 +81,36 @@ label##5: \ #define ALT_FTR_SECTION_END_IFCLR(msk) \ ALT_FTR_SECTION_END_NESTED_IFCLR(msk, 97) +/* MMU feature dependent sections */ +#define BEGIN_MMU_FTR_SECTION_NESTED(label) START_FTR_SECTION(label) +#define BEGIN_MMU_FTR_SECTION START_FTR_SECTION(97) + +#define END_MMU_FTR_SECTION_NESTED(msk, val, label) \ + FTR_SECTION_ELSE_NESTED(label) \ + MAKE_FTR_SECTION_ENTRY(msk, val, label, __mmu_ftr_fixup) + +#define END_MMU_FTR_SECTION(msk, val) \ + END_MMU_FTR_SECTION_NESTED(msk, val, 97) + +#define END_MMU_FTR_SECTION_IFSET(msk) END_MMU_FTR_SECTION((msk), (msk)) +#define END_MMU_FTR_SECTION_IFCLR(msk) END_MMU_FTR_SECTION((msk), 0) + +/* MMU feature sections with alternatives, use BEGIN_FTR_SECTION to start */ +#define MMU_FTR_SECTION_ELSE_NESTED(label) FTR_SECTION_ELSE_NESTED(label) +#define MMU_FTR_SECTION_ELSE MMU_FTR_SECTION_ELSE_NESTED(97) +#define ALT_MMU_FTR_SECTION_END_NESTED(msk, val, label) \ + MAKE_FTR_SECTION_ENTRY(msk, val, label, __mmu_ftr_fixup) +#define ALT_MMU_FTR_SECTION_END_NESTED_IFSET(msk, label) \ + ALT_MMU_FTR_SECTION_END_NESTED(msk, msk, label) +#define ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(msk, label) \ + ALT_MMU_FTR_SECTION_END_NESTED(msk, 0, label) +#define ALT_MMU_FTR_SECTION_END(msk, val) \ + ALT_MMU_FTR_SECTION_END_NESTED(msk, val, 97) +#define ALT_MMU_FTR_SECTION_END_IFSET(msk) \ + ALT_MMU_FTR_SECTION_END_NESTED_IFSET(msk, 97) +#define ALT_MMU_FTR_SECTION_END_IFCLR(msk) \ + ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(msk, 97) + /* Firmware feature dependent sections */ #define BEGIN_FW_FTR_SECTION_NESTED(label) START_FTR_SECTION(label) #define BEGIN_FW_FTR_SECTION START_FTR_SECTION(97) diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 4c0e1b4f975c..dc8c0aef5e6c 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -2,6 +2,47 @@ #define _ASM_POWERPC_MMU_H_ #ifdef __KERNEL__ +#include +#include + +/* + * MMU features bit definitions + */ + +/* + * First half is MMU families + */ +#define MMU_FTR_HPTE_TABLE ASM_CONST(0x00000001) +#define MMU_FTR_TYPE_8xx ASM_CONST(0x00000002) +#define MMU_FTR_TYPE_40x ASM_CONST(0x00000004) +#define MMU_FTR_TYPE_44x ASM_CONST(0x00000008) +#define MMU_FTR_TYPE_FSL_E ASM_CONST(0x00000010) + +/* + * This is individual features + */ + +/* Enable use of high BAT registers */ +#define MMU_FTR_USE_HIGH_BATS ASM_CONST(0x00010000) + +/* Enable >32-bit physical addresses on 32-bit processor, only used + * by CONFIG_6xx currently as BookE supports that from day 1 + */ +#define MMU_FTR_BIG_PHYS ASM_CONST(0x00020000) + +#ifndef __ASSEMBLY__ +#include + +static inline int mmu_has_feature(unsigned long feature) +{ + return (cur_cpu_spec->mmu_features & feature); +} + +extern unsigned int __start___mmu_ftr_fixup, __stop___mmu_ftr_fixup; + +#endif /* !__ASSEMBLY__ */ + + #ifdef CONFIG_PPC64 /* 64-bit classic hash table MMU */ # include -- cgit v1.2.1 From f048aace29e007f2b642097e2da8231e0e9cce2d Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:38 +0000 Subject: powerpc/mm: Add SMP support to no-hash TLB handling This commit moves the whole no-hash TLB handling out of line into a new tlb_nohash.c file, and implements some basic SMP support using IPIs and/or broadcast tlbivax instructions. Note that I'm using local invalidations for D->I cache coherency. At worst, if another processor is trying to execute the same and has the old entry in its TLB, it will just take a fault and re-do the TLB flush locally (it won't re-do the cache flush in any case). Signed-off-by: Benjamin Herrenschmidt Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/highmem.h | 4 +- arch/powerpc/include/asm/mmu.h | 16 +++++++ arch/powerpc/include/asm/tlbflush.h | 84 +++++++++++++++++-------------------- 3 files changed, 56 insertions(+), 48 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h index 7dc52eca8b67..fd97e501aa6a 100644 --- a/arch/powerpc/include/asm/highmem.h +++ b/arch/powerpc/include/asm/highmem.h @@ -85,7 +85,7 @@ static inline void *kmap_atomic_prot(struct page *page, enum km_type type, pgpro BUG_ON(!pte_none(*(kmap_pte-idx))); #endif __set_pte_at(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot)); - local_flush_tlb_page(vaddr); + local_flush_tlb_page(NULL, vaddr); return (void*) vaddr; } @@ -113,7 +113,7 @@ static inline void kunmap_atomic(void *kvaddr, enum km_type type) * this pte without first remap it */ pte_clear(&init_mm, vaddr, kmap_pte-idx); - local_flush_tlb_page(vaddr); + local_flush_tlb_page(NULL, vaddr); #endif pagefault_enable(); } diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index dc8c0aef5e6c..6e7639911318 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -30,6 +30,22 @@ */ #define MMU_FTR_BIG_PHYS ASM_CONST(0x00020000) +/* Enable use of broadcast TLB invalidations. We don't always set it + * on processors that support it due to other constraints with the + * use of such invalidations + */ +#define MMU_FTR_USE_TLBIVAX_BCAST ASM_CONST(0x00040000) + +/* Enable use of tlbilx invalidate-by-PID variant. + */ +#define MMU_FTR_USE_TLBILX_PID ASM_CONST(0x00080000) + +/* This indicates that the processor cannot handle multiple outstanding + * broadcast tlbivax or tlbsync. This makes the code use a spinlock + * around such invalidate forms. + */ +#define MMU_FTR_LOCK_BCAST_INVAL ASM_CONST(0x00100000) + #ifndef __ASSEMBLY__ #include diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h index 9ed363d3de44..8c39b27c1ed7 100644 --- a/arch/powerpc/include/asm/tlbflush.h +++ b/arch/powerpc/include/asm/tlbflush.h @@ -6,7 +6,9 @@ * * - flush_tlb_mm(mm) flushes the specified mm context TLB's * - flush_tlb_page(vma, vmaddr) flushes one page - * - local_flush_tlb_page(vmaddr) flushes one page on the local processor + * - local_flush_tlb_mm(mm) flushes the specified mm context on + * the local processor + * - local_flush_tlb_page(vma, vmaddr) flushes one page on the local processor * - flush_tlb_page_nohash(vma, vmaddr) flushes one page if SW loaded TLB * - flush_tlb_range(vma, start, end) flushes a range of pages * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages @@ -18,7 +20,7 @@ */ #ifdef __KERNEL__ -#if defined(CONFIG_4xx) || defined(CONFIG_8xx) || defined(CONFIG_FSL_BOOKE) +#ifdef CONFIG_PPC_MMU_NOHASH /* * TLB flushing for software loaded TLB chips * @@ -31,10 +33,10 @@ #define MMU_NO_CONTEXT ((unsigned int)-1) -extern void _tlbie(unsigned long address, unsigned int pid); extern void _tlbil_all(void); extern void _tlbil_pid(unsigned int pid); extern void _tlbil_va(unsigned long address, unsigned int pid); +extern void _tlbivax_bcast(unsigned long address, unsigned int pid); #if defined(CONFIG_40x) || defined(CONFIG_8xx) #define _tlbia() asm volatile ("tlbia; sync" : : : "memory") @@ -42,48 +44,26 @@ extern void _tlbil_va(unsigned long address, unsigned int pid); extern void _tlbia(void); #endif -static inline void local_flush_tlb_mm(struct mm_struct *mm) -{ - _tlbil_pid(mm->context.id); -} - -static inline void flush_tlb_mm(struct mm_struct *mm) -{ - _tlbil_pid(mm->context.id); -} - -static inline void local_flush_tlb_page(unsigned long vmaddr) -{ - _tlbil_va(vmaddr, 0); -} - -static inline void flush_tlb_page(struct vm_area_struct *vma, - unsigned long vmaddr) -{ - _tlbil_va(vmaddr, vma ? vma->vm_mm->context.id : 0); -} +extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); +extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); -static inline void flush_tlb_page_nohash(struct vm_area_struct *vma, - unsigned long vmaddr) -{ - flush_tlb_page(vma, vmaddr); -} +extern void local_flush_tlb_mm(struct mm_struct *mm); +extern void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); -static inline void flush_tlb_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ - _tlbil_pid(vma->vm_mm->context.id); -} +#ifdef CONFIG_SMP +extern void flush_tlb_mm(struct mm_struct *mm); +extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); +#else +#define flush_tlb_mm(mm) local_flush_tlb_mm(mm) +#define flush_tlb_page(vma,addr) local_flush_tlb_page(vma,addr) +#endif +#define flush_tlb_page_nohash(vma,addr) flush_tlb_page(vma,addr) -static inline void flush_tlb_kernel_range(unsigned long start, - unsigned long end) -{ - _tlbil_pid(0); -} +#elif defined(CONFIG_PPC_STD_MMU_32) -#elif defined(CONFIG_PPC32) /* - * TLB flushing for "classic" hash-MMMU 32-bit CPUs, 6xx, 7xx, 7xxx + * TLB flushing for "classic" hash-MMU 32-bit CPUs, 6xx, 7xx, 7xxx */ extern void _tlbie(unsigned long address); extern void _tlbia(void); @@ -94,14 +74,20 @@ extern void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); -static inline void local_flush_tlb_page(unsigned long vmaddr) +static inline void local_flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) { - flush_tlb_page(NULL, vmaddr); + flush_tlb_page(vma, vmaddr); +} +static inline void local_flush_tlb_mm(struct mm_struct *mm) +{ + flush_tlb_mm(mm); } -#else +#elif defined(CONFIG_PPC_STD_MMU_64) + /* - * TLB flushing for 64-bit has-MMU CPUs + * TLB flushing for 64-bit hash-MMU CPUs */ #include @@ -151,11 +137,16 @@ extern void flush_hash_page(unsigned long va, real_pte_t pte, int psize, extern void flush_hash_range(unsigned long number, int local); +static inline void local_flush_tlb_mm(struct mm_struct *mm) +{ +} + static inline void flush_tlb_mm(struct mm_struct *mm) { } -static inline void local_flush_tlb_page(unsigned long vmaddr) +static inline void local_flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) { } @@ -183,7 +174,8 @@ static inline void flush_tlb_kernel_range(unsigned long start, extern void __flush_hash_table_range(struct mm_struct *mm, unsigned long start, unsigned long end); - +#else +#error Unsupported MMU type #endif #endif /*__KERNEL__ */ -- cgit v1.2.1 From 2a4aca1144394653269720ffbb5a325a77abd5fa Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:42 +0000 Subject: powerpc/mm: Split low level tlb invalidate for nohash processors Currently, the various forms of low level TLB invalidations are all implemented in misc_32.S for 32-bit processors, in a fairly scary mess of #ifdef's and with interesting duplication such as a whole bunch of code for FSL _tlbie and _tlbia which are no longer used. This moves things around such that _tlbie is now defined in hash_low_32.S and is only used by the 32-bit hash code, and all nohash CPUs use the various _tlbil_* forms that are now moved to a new file, tlb_nohash_low.S. I moved all the definitions for that stuff out of include/asm/tlbflush.h as they are really internal mm stuff, into mm/mmu_decl.h The code should have no functional changes. I kept some variants inline for trivial forms on things like 40x and 8xx. Signed-off-by: Benjamin Herrenschmidt Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/tlbflush.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h index 8c39b27c1ed7..abbe3419d1dd 100644 --- a/arch/powerpc/include/asm/tlbflush.h +++ b/arch/powerpc/include/asm/tlbflush.h @@ -33,17 +33,6 @@ #define MMU_NO_CONTEXT ((unsigned int)-1) -extern void _tlbil_all(void); -extern void _tlbil_pid(unsigned int pid); -extern void _tlbil_va(unsigned long address, unsigned int pid); -extern void _tlbivax_bcast(unsigned long address, unsigned int pid); - -#if defined(CONFIG_40x) || defined(CONFIG_8xx) -#define _tlbia() asm volatile ("tlbia; sync" : : : "memory") -#else /* CONFIG_44x || CONFIG_FSL_BOOKE */ -extern void _tlbia(void); -#endif - extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); @@ -65,9 +54,6 @@ extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); /* * TLB flushing for "classic" hash-MMU 32-bit CPUs, 6xx, 7xx, 7xxx */ -extern void _tlbie(unsigned long address); -extern void _tlbia(void); - extern void flush_tlb_mm(struct mm_struct *mm); extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); extern void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr); -- cgit v1.2.1 From 64b3d0e8122b422e879b23d42f9e0e8efbbf9744 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Thu, 18 Dec 2008 19:13:51 +0000 Subject: powerpc/mm: Rework usage of _PAGE_COHERENT/NO_CACHE/GUARDED Currently, we never set _PAGE_COHERENT in the PTEs, we just OR it in in the hash code based on some CPU feature bit. We also manipulate _PAGE_NO_CACHE and _PAGE_GUARDED by hand in all sorts of places. This changes the logic so that instead, the PTE now contains _PAGE_COHERENT for all normal RAM pages thay have I = 0 on platforms that need it. The hash code clears it if the feature bit is not set. It also adds some clean accessors to setup various valid combinations of access flags and change various bits of code to use them instead. This should help having the PTE actually containing the bit combinations that we really want. I also removed _PAGE_GUARDED from _PAGE_BASE on 44x and instead set it explicitely from the TLB miss. I will ultimately remove it completely as it appears that it might not be needed after all but in the meantime, having it in the TLB miss makes things a lot easier. Signed-off-by: Benjamin Herrenschmidt Acked-by: Kumar Gala Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/pgtable-ppc32.h | 42 +++++++++++++------------------- arch/powerpc/include/asm/pgtable-ppc64.h | 13 ---------- arch/powerpc/include/asm/pgtable.h | 26 ++++++++++++++++++++ 3 files changed, 43 insertions(+), 38 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/pgtable-ppc32.h b/arch/powerpc/include/asm/pgtable-ppc32.h index 6ab7c67cb5ab..f69a4d977729 100644 --- a/arch/powerpc/include/asm/pgtable-ppc32.h +++ b/arch/powerpc/include/asm/pgtable-ppc32.h @@ -228,9 +228,10 @@ extern int icache_44x_need_flush; * - FILE *must* be in the bottom three bits because swap cache * entries use the top 29 bits for TLB2. * - * - CACHE COHERENT bit (M) has no effect on PPC440 core, because it - * doesn't support SMP. So we can use this as software bit, like - * DIRTY. + * - CACHE COHERENT bit (M) has no effect on original PPC440 cores, + * because it doesn't support SMP. However, some later 460 variants + * have -some- form of SMP support and so I keep the bit there for + * future use * * With the PPC 44x Linux implementation, the 0-11th LSBs of the PTE are used * for memory protection related functions (see PTE structure in @@ -436,20 +437,23 @@ extern int icache_44x_need_flush; _PAGE_USER | _PAGE_ACCESSED | \ _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | \ _PAGE_EXEC | _PAGE_HWEXEC) + /* - * Note: the _PAGE_COHERENT bit automatically gets set in the hardware - * PTE if CONFIG_SMP is defined (hash_page does this); there is no need - * to have it in the Linux PTE, and in fact the bit could be reused for - * another purpose. -- paulus. + * We define 2 sets of base prot bits, one for basic pages (ie, + * cacheable kernel and user pages) and one for non cacheable + * pages. We always set _PAGE_COHERENT when SMP is enabled or + * the processor might need it for DMA coherency. */ - -#ifdef CONFIG_44x -#define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_GUARDED) +#if defined(CONFIG_SMP) || defined(CONFIG_PPC_STD_MMU) +#define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_COHERENT) #else #define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED) #endif +#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_NO_CACHE) + #define _PAGE_WRENABLE (_PAGE_RW | _PAGE_DIRTY | _PAGE_HWWRITE) #define _PAGE_KERNEL (_PAGE_BASE | _PAGE_SHARED | _PAGE_WRENABLE) +#define _PAGE_KERNEL_NC (_PAGE_BASE_NC | _PAGE_SHARED | _PAGE_WRENABLE) #ifdef CONFIG_PPC_STD_MMU /* On standard PPC MMU, no user access implies kernel read/write access, @@ -459,7 +463,7 @@ extern int icache_44x_need_flush; #define _PAGE_KERNEL_RO (_PAGE_BASE | _PAGE_SHARED) #endif -#define _PAGE_IO (_PAGE_KERNEL | _PAGE_NO_CACHE | _PAGE_GUARDED) +#define _PAGE_IO (_PAGE_KERNEL_NC | _PAGE_GUARDED) #define _PAGE_RAM (_PAGE_KERNEL | _PAGE_HWEXEC) #if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\ @@ -552,9 +556,6 @@ static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; } static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } -static inline void pte_uncache(pte_t pte) { pte_val(pte) |= _PAGE_NO_CACHE; } -static inline void pte_cache(pte_t pte) { pte_val(pte) &= ~_PAGE_NO_CACHE; } - static inline pte_t pte_wrprotect(pte_t pte) { pte_val(pte) &= ~(_PAGE_RW | _PAGE_HWWRITE); return pte; } static inline pte_t pte_mkclean(pte_t pte) { @@ -693,10 +694,11 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, #endif } + static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { -#if defined(CONFIG_PTE_64BIT) && defined(CONFIG_SMP) +#if defined(CONFIG_PTE_64BIT) && defined(CONFIG_SMP) && defined(CONFIG_DEBUG_VM) WARN_ON(pte_present(*ptep)); #endif __set_pte_at(mm, addr, ptep, pte); @@ -760,16 +762,6 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry, int dirty) __changed; \ }) -/* - * Macro to mark a page protection value as "uncacheable". - */ -#define pgprot_noncached(prot) (__pgprot(pgprot_val(prot) | _PAGE_NO_CACHE | _PAGE_GUARDED)) - -struct file; -extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot); -#define __HAVE_PHYS_MEM_ACCESS_PROT - #define __HAVE_ARCH_PTE_SAME #define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0) diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index 1f0a330f03f4..b0f18be81d9f 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -245,9 +245,6 @@ static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED;} static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE;} static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } -static inline void pte_uncache(pte_t pte) { pte_val(pte) |= _PAGE_NO_CACHE; } -static inline void pte_cache(pte_t pte) { pte_val(pte) &= ~_PAGE_NO_CACHE; } - static inline pte_t pte_wrprotect(pte_t pte) { pte_val(pte) &= ~(_PAGE_RW); return pte; } static inline pte_t pte_mkclean(pte_t pte) { @@ -405,16 +402,6 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry, int dirty) __changed; \ }) -/* - * Macro to mark a page protection value as "uncacheable". - */ -#define pgprot_noncached(prot) (__pgprot(pgprot_val(prot) | _PAGE_NO_CACHE | _PAGE_GUARDED)) - -struct file; -extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, - unsigned long size, pgprot_t vma_prot); -#define __HAVE_PHYS_MEM_ACCESS_PROT - #define __HAVE_ARCH_PTE_SAME #define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0) diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index dbb8ca172e44..07f55e601696 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -16,6 +16,32 @@ struct mm_struct; #endif #ifndef __ASSEMBLY__ + +/* + * Macro to mark a page protection value as "uncacheable". + */ + +#define _PAGE_CACHE_CTL (_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \ + _PAGE_WRITETHRU) + +#define pgprot_noncached(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_NO_CACHE | _PAGE_GUARDED)) + +#define pgprot_noncached_wc(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_NO_CACHE)) + +#define pgprot_cached(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_COHERENT)) + +#define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ + _PAGE_COHERENT | _PAGE_WRITETHRU)) + + +struct file; +extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot); +#define __HAVE_PHYS_MEM_ACCESS_PROT + /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. -- cgit v1.2.1 From e14d77490d3e1da833cff4fee52674c52684ce77 Mon Sep 17 00:00:00 2001 From: Grant Erickson Date: Fri, 19 Dec 2008 08:17:54 +0000 Subject: powerpc: Const-qualify Device Node Argument to DCR Resource Extent API Add const qualifier to device_node argument for dcr_resource_{start,len} as of_get_property also const-qualifies this argument. Signed-off-by: Grant Erickson Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/dcr.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/dcr.h b/arch/powerpc/include/asm/dcr.h index d13fb68bb5c0..9d6851cfb841 100644 --- a/arch/powerpc/include/asm/dcr.h +++ b/arch/powerpc/include/asm/dcr.h @@ -68,9 +68,9 @@ typedef dcr_host_mmio_t dcr_host_t; * additional helpers to read the DCR * base from the device-tree */ struct device_node; -extern unsigned int dcr_resource_start(struct device_node *np, +extern unsigned int dcr_resource_start(const struct device_node *np, unsigned int index); -extern unsigned int dcr_resource_len(struct device_node *np, +extern unsigned int dcr_resource_len(const struct device_node *np, unsigned int index); #endif /* CONFIG_PPC_DCR */ #endif /* __ASSEMBLY__ */ -- cgit v1.2.1 From bcb73f5611c1946db768a1c219d205b3bf90f4a5 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Sun, 21 Dec 2008 02:54:26 -0700 Subject: powerpc/mpc5200: Document and tidy irq driver This patch adds documentation to the mpc5200 interrupt controller driver and cleans up some minor coding conventions. It also moves the contents of mpc52xx_pic.h into the driver proper (except for a small common bit that is moved to the common mpc52xx.h) because the information encoded there is not required by any other part of kernel code. Finally for code readability sake, the L2_OFFSET shift value is removed because the code using it resolves to a noop. Signed-off-by: Grant Likely --- arch/powerpc/include/asm/mpc52xx.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/mpc52xx.h b/arch/powerpc/include/asm/mpc52xx.h index 81ef10b6b672..81a23932a160 100644 --- a/arch/powerpc/include/asm/mpc52xx.h +++ b/arch/powerpc/include/asm/mpc52xx.h @@ -239,6 +239,25 @@ struct mpc52xx_cdm { u16 mclken_div_psc6; /* CDM + 0x36 reg13 byte2,3 */ }; +/* Interrupt controller Register set */ +struct mpc52xx_intr { + u32 per_mask; /* INTR + 0x00 */ + u32 per_pri1; /* INTR + 0x04 */ + u32 per_pri2; /* INTR + 0x08 */ + u32 per_pri3; /* INTR + 0x0c */ + u32 ctrl; /* INTR + 0x10 */ + u32 main_mask; /* INTR + 0x14 */ + u32 main_pri1; /* INTR + 0x18 */ + u32 main_pri2; /* INTR + 0x1c */ + u32 reserved1; /* INTR + 0x20 */ + u32 enc_status; /* INTR + 0x24 */ + u32 crit_status; /* INTR + 0x28 */ + u32 main_status; /* INTR + 0x2c */ + u32 per_status; /* INTR + 0x30 */ + u32 reserved2; /* INTR + 0x34 */ + u32 per_error; /* INTR + 0x38 */ +}; + #endif /* __ASSEMBLY__ */ -- cgit v1.2.1 From aec739e010f8163eac225f4e331ac7fbd59ac5c8 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sun, 21 Dec 2008 02:54:32 -0700 Subject: powerpc/mpc5200: add rts/cts handling in PSC UART driver Add RTS/CTS-support for the PSC of the MPC5200B. Tested with a Phytec MPC5200B-IO. Signed-off-by: Wolfram Sang Signed-off-by: Grant Likely --- arch/powerpc/include/asm/mpc52xx_psc.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/mpc52xx_psc.h b/arch/powerpc/include/asm/mpc52xx_psc.h index 8917ed630565..a218da6bec7c 100644 --- a/arch/powerpc/include/asm/mpc52xx_psc.h +++ b/arch/powerpc/include/asm/mpc52xx_psc.h @@ -68,12 +68,20 @@ #define MPC52xx_PSC_IMR_ORERR 0x1000 #define MPC52xx_PSC_IMR_IPC 0x8000 -/* PSC input port change bit */ +/* PSC input port change bits */ #define MPC52xx_PSC_CTS 0x01 #define MPC52xx_PSC_DCD 0x02 #define MPC52xx_PSC_D_CTS 0x10 #define MPC52xx_PSC_D_DCD 0x20 +/* PSC acr bits */ +#define MPC52xx_PSC_IEC_CTS 0x01 +#define MPC52xx_PSC_IEC_DCD 0x02 + +/* PSC output port bits */ +#define MPC52xx_PSC_OP_RTS 0x01 +#define MPC52xx_PSC_OP_RES 0x02 + /* PSC mode fields */ #define MPC52xx_PSC_MODE_5_BITS 0x00 #define MPC52xx_PSC_MODE_6_BITS 0x01 @@ -91,6 +99,7 @@ #define MPC52xx_PSC_MODE_ONE_STOP_5_BITS 0x00 #define MPC52xx_PSC_MODE_ONE_STOP 0x07 #define MPC52xx_PSC_MODE_TWO_STOP 0x0f +#define MPC52xx_PSC_MODE_TXCTS 0x10 #define MPC52xx_PSC_RFNUM_MASK 0x01ff -- cgit v1.2.1 From 322b439455ea62e6480e300c77b258e872896381 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Wed, 17 Dec 2008 10:08:55 +0000 Subject: powerpc: Prepare xmon_save_regs for use with kdump Today the arch/powerpc/xmon/setjmp.S file contains only the xmon_save_regs function. We want to use it for kdump purposes, so let's move the file into arch/powerpc/kernel/ and give the function a more generic name (ppc_save_regs). Signed-off-by: Anton Vorontsov Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/reg.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index c6d1ab650778..f484a343efba 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -783,6 +783,10 @@ extern void scom970_write(unsigned int address, unsigned long value); #define __get_SP() ({unsigned long sp; \ asm volatile("mr %0,1": "=r" (sp)); sp;}) +struct pt_regs; + +extern void ppc_save_regs(struct pt_regs *regs); + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_REG_H */ -- cgit v1.2.1 From 73753313884e8d063d9bf9d3e36325743ca006ba Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Wed, 17 Dec 2008 10:09:01 +0000 Subject: powerpc/32/kdump: Implement crash_setup_regs() using ppc_save_regs() This replaces the dummy crash_setup_regs function with full-fledged crash_setup_regs implementation. On PPC32 we simply use the new ppc_save_regs function to dump the registers. Signed-off-by: Anton Vorontsov Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/kexec.h | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 3736d9b33289..6dbffc981702 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -33,12 +33,12 @@ #ifndef __ASSEMBLY__ #include +#include typedef void (*crash_shutdown_t)(void); #ifdef CONFIG_KEXEC -#ifdef __powerpc64__ /* * This function is responsible for capturing register states if coming * via panic or invoking dump using sysrq-trigger. @@ -48,6 +48,7 @@ static inline void crash_setup_regs(struct pt_regs *newregs, { if (oldregs) memcpy(newregs, oldregs, sizeof(*newregs)); +#ifdef __powerpc64__ else { /* FIXME Merge this with xmon_save_regs ?? */ unsigned long tmp1, tmp2; @@ -100,15 +101,11 @@ static inline void crash_setup_regs(struct pt_regs *newregs, : "b" (newregs) : "memory"); } -} #else -/* - * Provide a dummy definition to avoid build failures. Will remain - * empty till crash dump support is enabled. - */ -static inline void crash_setup_regs(struct pt_regs *newregs, - struct pt_regs *oldregs) { } -#endif /* !__powerpc64 __ */ + else + ppc_save_regs(newregs); +#endif /* __powerpc64__ */ +} extern void kexec_smp_wait(void); /* get and clear naca physid, wait for master to copy new code to 0 */ -- cgit v1.2.1 From ccdcef72c249c289898b164eada89a61855b9287 Mon Sep 17 00:00:00 2001 From: Dale Farnsworth Date: Wed, 17 Dec 2008 10:09:13 +0000 Subject: powerpc/32: Add the ability for a classic ppc kernel to be loaded at 32M Add the ability for a classic ppc kernel to be loaded at an address of 32MB. This done by fixing a few places that assume we are loaded at address 0, and by changing several uses of KERNELBASE to use PAGE_OFFSET, instead. Signed-off-by: Dale Farnsworth Signed-off-by: Anton Vorontsov Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/ppc_asm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index c4a029ccb4d3..1a0d628eb114 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -425,14 +425,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) #define fromreal(rd) tovirt(rd,rd) #define tophys(rd,rs) \ -0: addis rd,rs,-KERNELBASE@h; \ +0: addis rd,rs,-PAGE_OFFSET@h; \ .section ".vtop_fixup","aw"; \ .align 1; \ .long 0b; \ .previous #define tovirt(rd,rs) \ -0: addis rd,rs,KERNELBASE@h; \ +0: addis rd,rs,PAGE_OFFSET@h; \ .section ".ptov_fixup","aw"; \ .align 1; \ .long 0b; \ -- cgit v1.2.1 From f8f50b1bddd49eb171398cfc543c957884dc6e35 Mon Sep 17 00:00:00 2001 From: Dale Farnsworth Date: Wed, 17 Dec 2008 10:09:26 +0000 Subject: powerpc/32: Wire up the trampoline code for kdump Wire up the trampoline code for ppc32 to relay exceptions from the vectors at address 0 to vectors at address 32MB, and modify Kconfig to enable Kdump support for all classic powerpcs. Signed-off-by: Dale Farnsworth Signed-off-by: Anton Vorontsov Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/kdump.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/kdump.h b/arch/powerpc/include/asm/kdump.h index b07ebb9784d3..5ebfe5d3c61f 100644 --- a/arch/powerpc/include/asm/kdump.h +++ b/arch/powerpc/include/asm/kdump.h @@ -1,6 +1,8 @@ #ifndef _PPC64_KDUMP_H #define _PPC64_KDUMP_H +#include + /* Kdump kernel runs at 32 MB, change at your peril. */ #define KDUMP_KERNELBASE 0x2000000 @@ -11,8 +13,19 @@ #ifdef CONFIG_CRASH_DUMP +/* + * On PPC64 translation is disabled during trampoline setup, so we use + * physical addresses. Though on PPC32 translation is already enabled, + * so we can't do the same. Luckily create_trampoline() creates relative + * branches, so we can just add the PAGE_OFFSET and don't worry about it. + */ +#ifdef __powerpc64__ #define KDUMP_TRAMPOLINE_START 0x0100 #define KDUMP_TRAMPOLINE_END 0x3000 +#else +#define KDUMP_TRAMPOLINE_START (0x0100 + PAGE_OFFSET) +#define KDUMP_TRAMPOLINE_END (0x3000 + PAGE_OFFSET) +#endif /* __powerpc64__ */ #define KDUMP_MIN_TCE_ENTRIES 2048 -- cgit v1.2.1 From fc5243d98ac2575ad14a974b3c097e9ba874c03d Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Thu, 25 Dec 2008 13:38:35 +0100 Subject: [S390] arch_setup_additional_pages arguments arch_setup_additional_pages currently gets two arguments, the binary format descripton and an indication if the process uses an executable stack or not. The second argument is not used by anybody, it could be removed without replacement. What actually does make sense is to pass an indication if the process uses the elf interpreter or not. The glibc code will not use anything from the vdso if the process does not use the dynamic linker, so for statically linked binaries the architecture backend can choose not to map the vdso. Acked-by: Ingo Molnar Signed-off-by: Martin Schwidefsky --- arch/powerpc/include/asm/elf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index d812929390e4..cd46f023ec6d 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -267,7 +267,7 @@ extern int ucache_bsize; #define ARCH_HAS_SETUP_ADDITIONAL_PAGES struct linux_binprm; extern int arch_setup_additional_pages(struct linux_binprm *bprm, - int executable_stack); + int uses_interp); #define VDSO_AUX_ENT(a,b) NEW_AUX_ENT(a,b); #endif /* __KERNEL__ */ -- cgit v1.2.1 From ca9153a3a2a7556d091dfe080e42b0e67881fff6 Mon Sep 17 00:00:00 2001 From: Ilya Yanok Date: Thu, 11 Dec 2008 04:55:41 +0300 Subject: powerpc/44x: Support 16K/64K base page sizes on 44x This adds support for 16k and 64k page sizes on PowerPC 44x processors. The PGDIR table is much smaller than a page when using 16k or 64k pages (512 and 32 bytes respectively) so we allocate the PGDIR with kzalloc() instead of __get_free_pages(). One PTE table covers rather a large memory area when using 16k or 64k pages (32MB or 512MB respectively), so we can easily put FIXMAP and PKMAP in the area covered by one PTE table. Signed-off-by: Yuri Tikhonov Signed-off-by: Vladimir Panfilov Signed-off-by: Ilya Yanok Acked-by: Josh Boyer Signed-off-by: Paul Mackerras --- arch/powerpc/include/asm/highmem.h | 19 +++++++++++++++++-- arch/powerpc/include/asm/mmu-44x.h | 17 +++++++++++++++++ arch/powerpc/include/asm/page.h | 13 ++++++++----- arch/powerpc/include/asm/page_32.h | 7 +++++-- 4 files changed, 47 insertions(+), 9 deletions(-) (limited to 'arch/powerpc/include/asm') diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h index fd97e501aa6a..04e4a620952e 100644 --- a/arch/powerpc/include/asm/highmem.h +++ b/arch/powerpc/include/asm/highmem.h @@ -38,9 +38,24 @@ extern pte_t *pkmap_page_table; * easily, subsequent pte tables have to be allocated in one physical * chunk of RAM. */ -#define LAST_PKMAP (1 << PTE_SHIFT) -#define LAST_PKMAP_MASK (LAST_PKMAP-1) +/* + * We use one full pte table with 4K pages. And with 16K/64K pages pte + * table covers enough memory (32MB and 512MB resp.) that both FIXMAP + * and PKMAP can be placed in single pte table. We use 1024 pages for + * PKMAP in case of 16K/64K pages. + */ +#ifdef CONFIG_PPC_4K_PAGES +#define PKMAP_ORDER PTE_SHIFT +#else +#define PKMAP_ORDER 10 +#endif +#define LAST_PKMAP (1 << PKMAP_ORDER) +#ifndef CONFIG_PPC_4K_PAGES +#define PKMAP_BASE (FIXADDR_START - PAGE_SIZE*(LAST_PKMAP + 1)) +#else #define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE*(LAST_PKMAP + 1)) & PMD_MASK) +#endif +#define LAST_PKMAP_MASK (LAST_PKMAP-1) #define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT) #define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT)) diff --git a/arch/powerpc/include/asm/mmu-44x.h b/arch/powerpc/include/asm/mmu-44x.h index b21af32ac6d6..8a97cfb08b7e 100644 --- a/arch/powerpc/include/asm/mmu-44x.h +++ b/arch/powerpc/include/asm/mmu-44x.h @@ -4,6 +4,8 @@ * PPC440 support */ +#include + #define PPC44x_MMUCR_TID 0x000000ff #define PPC44x_MMUCR_STS 0x00010000 @@ -74,4 +76,19 @@ typedef struct { /* Size of the TLBs used for pinning in lowmem */ #define PPC_PIN_SIZE (1 << 28) /* 256M */ +#if (PAGE_SHIFT == 12) +#define PPC44x_TLBE_SIZE PPC44x_TLB_4K +#elif (PAGE_SHIFT == 14) +#define PPC44x_TLBE_SIZE PPC44x_TLB_16K +#elif (PAGE_SHIFT == 16) +#define PPC44x_TLBE_SIZE PPC44x_TLB_64K +#else +#error "Unsupported PAGE_SIZE" +#endif + +#define PPC44x_PGD_OFF_SHIFT (32 - PGDIR_SHIFT + PGD_T_LOG2) +#define PPC44x_PGD_OFF_MASK_BIT (PGDIR_SHIFT - PGD_T_LOG2) +#define PPC44x_PTE_ADD_SHIFT (32 - PGDIR_SHIFT + PTE_SHIFT + PTE_T_LOG2) +#define PPC44x_PTE_ADD_MASK_BIT (32 - PTE_T_LOG2 - PTE_SHIFT) + #endif /* _ASM_POWERPC_MMU_44X_H_ */ diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index c0b8d4a29a91..197d569f5bd3 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -19,12 +19,15 @@ #include /* - * On PPC32 page size is 4K. For PPC64 we support either 4K or 64K software + * On regular PPC32 page size is 4K (but we support 4K/16K/64K pages + * on PPC44x). For PPC64 we support either 4K or 64K software * page size. When using 64K pages however, whether we are really supporting * 64K pages in HW or not is irrelevant to those definitions. */ -#ifdef CONFIG_PPC_64K_PAGES +#if defined(CONFIG_PPC_64K_PAGES) #define PAGE_SHIFT 16 +#elif defined(CONFIG_PPC_16K_PAGES) +#define PAGE_SHIFT 14 #else #define PAGE_SHIFT 12 #endif @@ -151,7 +154,7 @@ typedef struct { pte_basic_t pte; } pte_t; /* 64k pages additionally define a bigger "real PTE" type that gathers * the "second half" part of the PTE for pseudo 64k pages */ -#ifdef CONFIG_PPC_64K_PAGES +#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64) typedef struct { pte_t pte; unsigned long hidx; } real_pte_t; #else typedef struct { pte_t pte; } real_pte_t; @@ -191,10 +194,10 @@ typedef pte_basic_t pte_t; #define pte_val(x) (x) #define __pte(x) (x) -#ifdef CONFIG_PPC_64K_PAGES +#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_STD_MMU_64) typedef struct { pte_t pte; unsigned long hidx; } real_pte_t; #else -typedef unsigned long real_pte_t; +typedef pte_t real_pte_t; #endif diff --git a/arch/powerpc/include/asm/page_32.h b/arch/powerpc/include/asm/page_32.h index d77072a32cc6..1458d9500381 100644 --- a/arch/powerpc/include/asm/page_32.h +++ b/arch/powerpc/include/asm/page_32.h @@ -19,6 +19,8 @@ #define PTE_FLAGS_OFFSET 0 #endif +#define PTE_SHIFT (PAGE_SHIFT - PTE_T_LOG2) /* full page */ + #ifndef __ASSEMBLY__ /* * The basic type of a PTE - 64 bits for those CPUs with > 32 bit @@ -26,10 +28,8 @@ */ #ifdef CONFIG_PTE_64BIT typedef unsigned long long pte_basic_t; -#define PTE_SHIFT (PAGE_SHIFT - 3) /* 512 ptes per page */ #else typedef unsigned long pte_basic_t; -#define PTE_SHIFT (PAGE_SHIFT - 2) /* 1024 ptes per page */ #endif struct page; @@ -39,6 +39,9 @@ extern void copy_page(void *to, void *from); #include +#define PGD_T_LOG2 (__builtin_ffs(sizeof(pgd_t)) - 1) +#define PTE_T_LOG2 (__builtin_ffs(sizeof(pte_t)) - 1) + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_PAGE_32_H */ -- cgit v1.2.1