search for: larl

...ew differences, where one interesting one is that while clang stores an incremented value in each iteration, gcc waits and just stores the final value just once after the loop. The value is a global variable. I wonder if this is something clang does not do per default but can be activated, similarly to the fp-contract situation? If not, is this a deficiency in clang? What pass should handle this? IndVarSimplify? I have made a reduced test case which shows the same difference between the compilers: clang adds 1 and stores it back to 'a' in each iteration, while gcc instead figures...

...ang emits two loads. typedef struct {   double c[3][3]; } STRUCT_TY; double e = 0.0; STRUCT_TY *f; int g = 0; void h() {   int i = e;   f->c[0][i] = g;   g = e; } clang -O3-march=z13 : h:                                      # @h # %bb.0:                                # %entry         larl    %r1, e         ld      %f0, 0(%r1)        // LOAD E         lrl     %r2, g         cfdbr   %r0, 5, %f0        // CONVERT E         lgfr    %r0, %r0           // EXTEND E         cdfbr   %f0, %r2         lgrl    %r2, f         sllg    %r3, %r0, 3         std     %f0, 0(%r3,%r2)    // STOR...

...T_TY *f; > int g = 0; > void h() { >   int i = e; >   f->c[0][i] = g; >   g = e; > } > > clang -O3-march=z13 : > > h:                                      # @h > # %bb.0:                                # %entry >         larl    %r1, e >         ld      %f0, 0(%r1)        // LOAD E >         lrl     %r2, g >         cfdbr   %r0, 5, %f0        // CONVERT E >         lgfr    %r0, %r0           // EXTEND E >         cdfbr   %f0, %r2 >         lgrl    %r2, f >         sllg   ...

...ace 0000000001998c50 cccccccccccccccc cccccccccccccccc [ 0.839720] 0000000000982134 000000000058f824 0000000000a008a8 0000000000000000 [ 0.839722] 00000000000004d9 00000000007ea992 000000000015bf8a 00000000021dbc28 [ 0.839731] Krnl Code: 000000000015bf7e: c0200033e838 larl %r2,7d8fee 000000000015bf84: c0e50028cd62 brasl %r14,675a48 #000000000015bf8a: a7f40001 brc 15,15bf8c >000000000015bf8e: 9201a000 mvi 0(%r10),1 000000000015bf92: a7f4ffe2 brc 15,15bf56 000000000015bf96: 0707 bcr 0,%r7 0000000000...

...ace 0000000001998c50 cccccccccccccccc cccccccccccccccc [ 0.839720] 0000000000982134 000000000058f824 0000000000a008a8 0000000000000000 [ 0.839722] 00000000000004d9 00000000007ea992 000000000015bf8a 00000000021dbc28 [ 0.839731] Krnl Code: 000000000015bf7e: c0200033e838 larl %r2,7d8fee 000000000015bf84: c0e50028cd62 brasl %r14,675a48 #000000000015bf8a: a7f40001 brc 15,15bf8c >000000000015bf8e: 9201a000 mvi 0(%r10),1 000000000015bf92: a7f4ffe2 brc 15,15bf56 000000000015bf96: 0707 bcr 0,%r7 0000000000...

...9ce 0000000000000000 0000000000000001 00000000629e7c06 [ 33.534719] 0000000000000000 0000000000000c06 0000000000000002 000000006467f800 [ 33.534720] 0000000064673428 00000000629e7c06 00000000005869ce 00000000629e7928 [ 33.534726] Krnl Code: 00000000005869c2: c0200024ad4e larl %r2,a1c45e 00000000005869c8: c0e5ffe6d6fc brasl %r14,2617c0 #00000000005869ce: a7f40001 brc 15,5869d0 >00000000005869d2: c010003465eb larl %r1,c135a8 00000000005869d8: e31010000012 lt %r1,0(%r1) 00000000005869de: a784000a brc 8,5869f2...

...a7c8fffb lhi %r12,-5 > 000000000042161c: a7f4ff46 brc 15,4214a8 > 0000000000421620: a7f40001 brc 15,421622 > 0000000000421624: b9040021 lgr %r2,%r1 > 0000000000421628: c030001c3569 larl %r3,7a80fa > [ 8.644106] Call Trace: > [ 8.644110] ([<00000000004214de>] virtqueue_add_outbuf+0x1aa/0x340) > [ 8.644114] [<000003ff80174466>] start_xmit+0x1e6/0x49c [virtio_net] > [ 8.644119] [<000000000050571a>] dev_hard_start_xmit+0x346/0x600 > [...

...a7c8fffb lhi %r12,-5 > 000000000042161c: a7f4ff46 brc 15,4214a8 > 0000000000421620: a7f40001 brc 15,421622 > 0000000000421624: b9040021 lgr %r2,%r1 > 0000000000421628: c030001c3569 larl %r3,7a80fa > [ 8.644106] Call Trace: > [ 8.644110] ([<00000000004214de>] virtqueue_add_outbuf+0x1aa/0x340) > [ 8.644114] [<000003ff80174466>] start_xmit+0x1e6/0x49c [virtio_net] > [ 8.644119] [<000000000050571a>] dev_hard_start_xmit+0x346/0x600 > [...

...>>         .file   "testfun.i" >>         .machinemode zarch >>         .machine "z13" >> .text >>         .align  8 >> .globl b >>         .type   b, @function >> b: >> .LFB0: >>         .cfi_startproc >>         larl    %r1,a >>         lt      %r1,0(%r1) >>         je      .L1 >>         larl    %r1,a >>         mvhi    0(%r1),0 >> .L1: >>         br      %r14 >>         .cfi_endproc >> .LFE0: >>         .size   b, .-b >> .globl a >> .data >&...

...lhi %r12,-5 >> 000000000042161c: a7f4ff46 brc 15,4214a8 >> 0000000000421620: a7f40001 brc 15,421622 >> 0000000000421624: b9040021 lgr %r2,%r1 >> 0000000000421628: c030001c3569 larl %r3,7a80fa >> [ 8.644106] Call Trace: >> [ 8.644110] ([<00000000004214de>] virtqueue_add_outbuf+0x1aa/0x340) >> [ 8.644114] [<000003ff80174466>] start_xmit+0x1e6/0x49c [virtio_net] >> [ 8.644119] [<000000000050571a>] dev_hard_start_xmit+0x3...

...atches adds Clang support for SystemZ. The first patch adds a new common code feature that allows platform code to request minimum alignment of global symbols. The background for this is that on System Z, the most efficient way to load addresses of global symbol is the LOAD ADDRESS RELATIVE LONG (LARL) instruction. This instruction provides PC-relative addressing, but only to *even* addresses. For this reason, existing compilers will guarantee that global symbols are always aligned to at least 2. [ Since symbols would otherwise already use a default alignment based on their type, this will us...

...98c50 cccccccccccccccc cccccccccccccccc > [ 0.839720] 0000000000982134 000000000058f824 0000000000a008a8 0000000000000000 > [ 0.839722] 00000000000004d9 00000000007ea992 000000000015bf8a 00000000021dbc28 > [ 0.839731] Krnl Code: 000000000015bf7e: c0200033e838 larl %r2,7d8fee > 000000000015bf84: c0e50028cd62 brasl %r14,675a48 > #000000000015bf8a: a7f40001 brc 15,15bf8c > >000000000015bf8e: 9201a000 mvi 0(%r10),1 > 000000000015bf92: a7f4ffe2 brc 15,15bf56 > 000000000015bf96: 0707 bcr 0,...

...98c50 cccccccccccccccc cccccccccccccccc > [ 0.839720] 0000000000982134 000000000058f824 0000000000a008a8 0000000000000000 > [ 0.839722] 00000000000004d9 00000000007ea992 000000000015bf8a 00000000021dbc28 > [ 0.839731] Krnl Code: 000000000015bf7e: c0200033e838 larl %r2,7d8fee > 000000000015bf84: c0e50028cd62 brasl %r14,675a48 > #000000000015bf8a: a7f40001 brc 15,15bf8c > >000000000015bf8e: 9201a000 mvi 0(%r10),1 > 000000000015bf92: a7f4ffe2 brc 15,15bf56 > 000000000015bf96: 0707 bcr 0,...

...#0000000000421614: a7f40001 brc 15,421616 >0000000000421618: a7c8fffb lhi %r12,-5 000000000042161c: a7f4ff46 brc 15,4214a8 0000000000421620: a7f40001 brc 15,421622 0000000000421624: b9040021 lgr %r2,%r1 0000000000421628: c030001c3569 larl %r3,7a80fa [ 8.644106] Call Trace: [ 8.644110] ([<00000000004214de>] virtqueue_add_outbuf+0x1aa/0x340) [ 8.644114] [<000003ff80174466>] start_xmit+0x1e6/0x49c [virtio_net] [ 8.644119] [<000000000050571a>] dev_hard_start_xmit+0x346/0x600 [ 8.644123] [<000000000...

...22) & 1)) - addr &= 0xffff; - addr += base; - up(&child->mm->context.sem); + /* Check the segment exists, is within the current LDT/GDT size, + that kernel/user (ring 0..3) has the appropriate privilege, + that it's a code segment, and get the limit. */ + asm ("larl %3,%0; lsll %3,%1" + : "=&r" (seg_ar), "=r" (seg_limit) : "0" (0), "rm" (seg)); + if ((~seg_ar & 0x9800) || eip > seg_limit) { + if (eip_limit) + *eip_limit = 0; + eip = 1; /* So that returned eip > *eip_limit. */ + base = 0; + } el...

...22) & 1)) - addr &= 0xffff; - addr += base; - up(&child->mm->context.sem); + /* Check the segment exists, is within the current LDT/GDT size, + that kernel/user (ring 0..3) has the appropriate privilege, + that it's a code segment, and get the limit. */ + asm ("larl %3,%0; lsll %3,%1" + : "=&r" (seg_ar), "=r" (seg_limit) : "0" (0), "rm" (seg)); + if ((~seg_ar & 0x9800) || eip > seg_limit) { + if (eip_limit) + *eip_limit = 0; + eip = 1; /* So that returned eip > *eip_limit. */ + base = 0; + } el...

This fixes virtio on Xen guests as well as on any other platform that uses virtio_pci on which physical addresses don't match bus addresses. This can be tested with: virtme-run --xen xen --kimg arch/x86/boot/bzImage --console using virtme from here: https://git.kernel.org/cgit/utils/kernel/virtme/virtme.git Without these patches, the guest hangs forever. With these patches,

This fixes virtio on Xen guests as well as on any other platform that uses virtio_pci on which physical addresses don't match bus addresses. This can be tested with: virtme-run --xen xen --kimg arch/x86/boot/bzImage --console using virtme from here: https://git.kernel.org/cgit/utils/kernel/virtme/virtme.git Without these patches, the guest hangs forever. With these patches,

This switches virtio to use the DMA API unconditionally. I'm sure it breaks things, but it seems to work on x86 using virtio-pci, with and without Xen, and using both the modern 1.0 variant and the legacy variant. This appears to work on native and Xen x86_64 using both modern and legacy virtio-pci. It also appears to work on arm and arm64. It definitely won't work as-is on s390x, and

This switches virtio to use the DMA API unconditionally. I'm sure it breaks things, but it seems to work on x86 using virtio-pci, with and without Xen, and using both the modern 1.0 variant and the legacy variant. This appears to work on native and Xen x86_64 using both modern and legacy virtio-pci. It also appears to work on arm and arm64. It definitely won't work as-is on s390x, and