diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-19 15:38:41 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-19 15:38:41 -0700 |
commit | d5e2d00898bdfed9586472679760fc81a2ca2d02 (patch) | |
tree | 55ac781983bf7144230ad8a5a995ce02b6ac39a1 /arch/powerpc/include/asm/checksum.h | |
parent | Merge tag 'devicetree-for-4.6' of git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux (diff) | |
parent | powerpc: Fix unrecoverable SLB miss during restore_math() (diff) | |
download | linux-dev-d5e2d00898bdfed9586472679760fc81a2ca2d02.tar.xz linux-dev-d5e2d00898bdfed9586472679760fc81a2ca2d02.zip |
Merge tag 'powerpc-4.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
"This was delayed a day or two by some build-breakage on old toolchains
which we've now fixed.
There's two PCI commits both acked by Bjorn.
There's one commit to mm/hugepage.c which is (co)authored by Kirill.
Highlights:
- Restructure Linux PTE on Book3S/64 to Radix format from Paul
Mackerras
- Book3s 64 MMU cleanup in preparation for Radix MMU from Aneesh
Kumar K.V
- Add POWER9 cputable entry from Michael Neuling
- FPU/Altivec/VSX save/restore optimisations from Cyril Bur
- Add support for new ftrace ABI on ppc64le from Torsten Duwe
Various cleanups & minor fixes from:
- Adam Buchbinder, Andrew Donnellan, Balbir Singh, Christophe Leroy,
Cyril Bur, Luis Henriques, Madhavan Srinivasan, Pan Xinhui, Russell
Currey, Sukadev Bhattiprolu, Suraj Jitindar Singh.
General:
- atomics: Allow architectures to define their own __atomic_op_*
helpers from Boqun Feng
- Implement atomic{, 64}_*_return_* variants and acquire/release/
relaxed variants for (cmp)xchg from Boqun Feng
- Add powernv_defconfig from Jeremy Kerr
- Fix BUG_ON() reporting in real mode from Balbir Singh
- Add xmon command to dump OPAL msglog from Andrew Donnellan
- Add xmon command to dump process/task similar to ps(1) from Douglas
Miller
- Clean up memory hotplug failure paths from David Gibson
pci/eeh:
- Redesign SR-IOV on PowerNV to give absolute isolation between VFs
from Wei Yang.
- EEH Support for SRIOV VFs from Wei Yang and Gavin Shan.
- PCI/IOV: Rename and export virtfn_{add, remove} from Wei Yang
- PCI: Add pcibios_bus_add_device() weak function from Wei Yang
- MAINTAINERS: Update EEH details and maintainership from Russell
Currey
cxl:
- Support added to the CXL driver for running on both bare-metal and
hypervisor systems, from Christophe Lombard and Frederic Barrat.
- Ignore probes for virtual afu pci devices from Vaibhav Jain
perf:
- Export Power8 generic and cache events to sysfs from Sukadev
Bhattiprolu
- hv-24x7: Fix usage with chip events, display change in counter
values, display domain indices in sysfs, eliminate domain suffix in
event names, from Sukadev Bhattiprolu
Freescale:
- Updates from Scott: "Highlights include 8xx optimizations, 32-bit
checksum optimizations, 86xx consolidation, e5500/e6500 cpu
hotplug, more fman and other dt bits, and minor fixes/cleanup"
* tag 'powerpc-4.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (179 commits)
powerpc: Fix unrecoverable SLB miss during restore_math()
powerpc/8xx: Fix do_mtspr_cpu6() build on older compilers
powerpc/rcpm: Fix build break when SMP=n
powerpc/book3e-64: Use hardcoded mttmr opcode
powerpc/fsl/dts: Add "jedec,spi-nor" flash compatible
powerpc/T104xRDB: add tdm riser card node to device tree
powerpc32: PAGE_EXEC required for inittext
powerpc/mpc85xx: Add pcsphy nodes to FManV3 device tree
powerpc/mpc85xx: Add MDIO bus muxing support to the board device tree(s)
powerpc/86xx: Introduce and use common dtsi
powerpc/86xx: Update device tree
powerpc/86xx: Move dts files to fsl directory
powerpc/86xx: Switch to kconfig fragments approach
powerpc/86xx: Update defconfigs
powerpc/86xx: Consolidate common platform code
powerpc32: Remove one insn in mulhdu
powerpc32: small optimisation in flush_icache_range()
powerpc: Simplify test in __dma_sync()
powerpc32: move xxxxx_dcache_range() functions inline
powerpc32: Remove clear_pages() and define clear_page() inline
...
Diffstat (limited to 'arch/powerpc/include/asm/checksum.h')
-rw-r--r-- | arch/powerpc/include/asm/checksum.h | 141 |
1 files changed, 101 insertions, 40 deletions
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h index e8d9ef4755a4..ee655ed1ff1b 100644 --- a/arch/powerpc/include/asm/checksum.h +++ b/arch/powerpc/include/asm/checksum.h @@ -9,30 +9,9 @@ * 2 of the License, or (at your option) any later version. */ -/* - * This is a version of ip_compute_csum() optimized for IP headers, - * which always checksum on 4 octet boundaries. ihl is the number - * of 32-bit words and is always >= 5. - */ #ifdef CONFIG_GENERIC_CSUM #include <asm-generic/checksum.h> #else -extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl); - -/* - * computes the checksum of a memory block at buff, length len, - * and adds in "sum" (32-bit) - * - * returns a 32-bit number suitable for feeding into itself - * or csum_tcpudp_magic - * - * this function must be called with even lengths, except - * for the last fragment, which may be odd - * - * it's best to have buff aligned on a 32-bit boundary - */ -extern __wsum csum_partial(const void *buff, int len, __wsum sum); - /* * Computes the checksum of a memory block at src, length len, * and adds in "sum" (32-bit), while copying the block to dst. @@ -47,21 +26,12 @@ extern __wsum csum_partial_copy_generic(const void *src, void *dst, int len, __wsum sum, int *src_err, int *dst_err); -#ifdef __powerpc64__ #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER extern __wsum csum_and_copy_from_user(const void __user *src, void *dst, int len, __wsum sum, int *err_ptr); #define HAVE_CSUM_COPY_USER extern __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len, __wsum sum, int *err_ptr); -#else -/* - * the same as csum_partial, but copies from src to dst while it - * checksums. - */ -#define csum_partial_copy_from_user(src, dst, len, sum, errp) \ - csum_partial_copy_generic((__force const void *)(src), (dst), (len), (sum), (errp), NULL) -#endif #define csum_partial_copy_nocheck(src, dst, len, sum) \ csum_partial_copy_generic((src), (dst), (len), (sum), NULL, NULL) @@ -83,15 +53,6 @@ static inline __sum16 csum_fold(__wsum sum) return (__force __sum16)(~((__force u32)sum + tmp) >> 16); } -/* - * this routine is used for miscellaneous IP-like checksums, mainly - * in icmp.c - */ -static inline __sum16 ip_compute_csum(const void *buff, int len) -{ - return csum_fold(csum_partial(buff, len, 0)); -} - static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len, unsigned short proto, @@ -135,17 +96,117 @@ static inline __wsum csum_add(__wsum csum, __wsum addend) { #ifdef __powerpc64__ u64 res = (__force u64)csum; +#endif + if (__builtin_constant_p(csum) && csum == 0) + return addend; + if (__builtin_constant_p(addend) && addend == 0) + return csum; +#ifdef __powerpc64__ res += (__force u64)addend; return (__force __wsum)((u32)res + (res >> 32)); #else asm("addc %0,%0,%1;" "addze %0,%0;" - : "+r" (csum) : "r" (addend)); + : "+r" (csum) : "r" (addend) : "xer"); return csum; #endif } +/* + * This is a version of ip_compute_csum() optimized for IP headers, + * which always checksum on 4 octet boundaries. ihl is the number + * of 32-bit words and is always >= 5. + */ +static inline __wsum ip_fast_csum_nofold(const void *iph, unsigned int ihl) +{ + const u32 *ptr = (const u32 *)iph + 1; +#ifdef __powerpc64__ + unsigned int i; + u64 s = *(const u32 *)iph; + + for (i = 0; i < ihl - 1; i++, ptr++) + s += *ptr; + s += (s >> 32); + return (__force __wsum)s; +#else + __wsum sum, tmp; + + asm("mtctr %3;" + "addc %0,%4,%5;" + "1: lwzu %1, 4(%2);" + "adde %0,%0,%1;" + "bdnz 1b;" + "addze %0,%0;" + : "=r" (sum), "=r" (tmp), "+b" (ptr) + : "r" (ihl - 2), "r" (*(const u32 *)iph), "r" (*ptr) + : "ctr", "xer", "memory"); + + return sum; +#endif +} + +static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) +{ + return csum_fold(ip_fast_csum_nofold(iph, ihl)); +} + +/* + * computes the checksum of a memory block at buff, length len, + * and adds in "sum" (32-bit) + * + * returns a 32-bit number suitable for feeding into itself + * or csum_tcpudp_magic + * + * this function must be called with even lengths, except + * for the last fragment, which may be odd + * + * it's best to have buff aligned on a 32-bit boundary + */ +__wsum __csum_partial(const void *buff, int len, __wsum sum); + +static inline __wsum csum_partial(const void *buff, int len, __wsum sum) +{ + if (__builtin_constant_p(len) && len <= 16 && (len & 1) == 0) { + if (len == 2) + sum = csum_add(sum, (__force __wsum)*(const u16 *)buff); + if (len >= 4) + sum = csum_add(sum, (__force __wsum)*(const u32 *)buff); + if (len == 6) + sum = csum_add(sum, (__force __wsum) + *(const u16 *)(buff + 4)); + if (len >= 8) + sum = csum_add(sum, (__force __wsum) + *(const u32 *)(buff + 4)); + if (len == 10) + sum = csum_add(sum, (__force __wsum) + *(const u16 *)(buff + 8)); + if (len >= 12) + sum = csum_add(sum, (__force __wsum) + *(const u32 *)(buff + 8)); + if (len == 14) + sum = csum_add(sum, (__force __wsum) + *(const u16 *)(buff + 12)); + if (len >= 16) + sum = csum_add(sum, (__force __wsum) + *(const u32 *)(buff + 12)); + } else if (__builtin_constant_p(len) && (len & 3) == 0) { + sum = csum_add(sum, ip_fast_csum_nofold(buff, len >> 2)); + } else { + sum = __csum_partial(buff, len, sum); + } + return sum; +} + +/* + * this routine is used for miscellaneous IP-like checksums, mainly + * in icmp.c + */ +static inline __sum16 ip_compute_csum(const void *buff, int len) +{ + return csum_fold(csum_partial(buff, len, 0)); +} + #endif #endif /* __KERNEL__ */ #endif |