[backport gcc-4.8/trunk r193930 ] From: Matthew Gretton-Dann Subject: [RFA/ARM] Fix PR54974: Thumb literal pools don't handle PC rounding Date: Wed, 21 Nov 2012 19:59:05 +0000 List-Archive: All, The attached patch fixes PR54974. In Thumb when calculating the PC value for a literal load the value used is the current PC rounded down to the nearest multiple of 4. The ARM backend currently does not take this into account when calculating literal pool placement. The fix is to decrease the pool_range of all insns by 2 when generating Thumb code. There is no need to change neg_pool_range values as rounding down here will reduce the distance of the literal pool. The patch attached to the PR is not sufficient as we don't precisely know the PC when calculating literal pool ranges and so have to be conservative. Whilst going through all the code I found the following, possibly related, issues that I would like some input from the ARM maintainers on (although they have not been touched in this patch): 1) Some Thumb-2 patterns (like thumb2_movhi_insn) have a neg_pool_range of 250 for ldrh, where my reading of the ARMARM says the range is [-4095, 4095] for Thumb-2 (with appropriate rounding). What is the reason for GCC's severe pessimism here? 2) thumb1_zero_extendqisi2 (and other insns) give a Thumb-1 narrow ldrb a pool_range of 32. Surely the pool_range should be 0 (or *) as Thumb-1 doesn't have a ldrb where the base-register can be PC? Tested arm-none-linux-gnueabi cross, and with the testcase attached to the PR. No added testcase in the patch as this code is sensitive to other code generation and so it is not easy to generate a testcase which will reliably test this condition. OK for trunk, 4.7, and 4.6? Thanks, Matt gcc/ 2012-11-29 Matthew Gretton-Dann PR target/54974 * config/arm/arm.md (thumb2_pool_range, pool_range): Add comment on Thumb pool ranges. (thumb1_extendhisi2): Reduce Thumb pool range. (arm_movdi): Likewise. (thumb1_movdi_insn): Likewise. (thumb1_movsi_insn): Likewise. (pic_load_addr_unified): Likewise. (pic_load_addr_32bit): Likewise. (pic_load_addr_thumb1): Likewise. (thumb1_movhf): Likewise. (arm_movsf_soft_insn): Likewise. (thumb1_movsf_soft_insn): Likewise. (movdf_soft_insn): Likewise. (thumb1_movdf_soft_insn): Likewise. * config/arm/neon.md (*neon_mov): Likewise. (*neon_mov): Likwise. * config/arm/thumb2.md: (*thumb2_movsi_insn): Likewise. (*thumb2_movhi_insn): Likewise. (*thumb2_extendqisi_v6): Likewise. (*thumb2_zero_extendqisi_v6): Likewise. (*thumb2_zero_extendqisi2_v6): Likewise. * config/arm/vfp.md: (*thumb2_movsi_vfp): Likewise. (*movdi_vfp): Likewise. (*movdi_vfp_cortexa8): Likewise. (*thumb2_movsf_vfp): Likewise. (*thumb2_movdf_vfp): Likewise. --- gcc-4.7.2/gcc/config/arm/arm.md.~1~ 2012-08-06 16:34:27.000000000 +0200 +++ gcc-4.7.2/gcc/config/arm/arm.md 2012-12-09 11:30:29.000000000 +0100 @@ -256,6 +256,9 @@ (define_attr "insn_enabled" "no,yes" ; POOL_RANGE is how far away from a constant pool entry that this insn ; can be placed. If the distance is zero, then this insn will never ; reference the pool. +; Note that for Thumb constant pools the PC value is rounded down to the +; nearest multiple of four. Therefore, THUMB2_POOL_RANGE (and POOL_RANGE for +; Thumb insns) should be set to - 2. ; NEG_POOL_RANGE is nonzero for insns that can reference a constant pool entry ; before its address. It is set to - (8 + ). (define_attr "arm_pool_range" "" (const_int 0)) @@ -4833,7 +4836,7 @@ (define_insn "thumb1_extendhisi2" (const_int 2) (const_int 4)) (const_int 4)]) (set_attr "type" "alu_shift,load_byte") - (set_attr "pool_range" "*,1020")] + (set_attr "pool_range" "*,1018")] ) ;; This pattern will only be used when ldsh is not available @@ -5239,7 +5242,7 @@ (define_insn "*arm_movdi" (set_attr "type" "*,*,*,load2,store2") (set_attr "arm_pool_range" "*,*,*,1020,*") (set_attr "arm_neg_pool_range" "*,*,*,1004,*") - (set_attr "thumb2_pool_range" "*,*,*,4096,*") + (set_attr "thumb2_pool_range" "*,*,*,4094,*") (set_attr "thumb2_neg_pool_range" "*,*,*,0,*")] ) @@ -5379,7 +5382,7 @@ (define_insn "*thumb1_movdi_insn" [(set_attr "length" "4,4,6,2,2,6,4,4") (set_attr "type" "*,*,*,load2,store2,load2,store2,*") (set_attr "insn" "*,mov,*,*,*,*,*,mov") - (set_attr "pool_range" "*,*,*,*,*,1020,*,*")] + (set_attr "pool_range" "*,*,*,*,*,1018,*,*")] ) (define_expand "movsi" @@ -5539,7 +5542,7 @@ (define_insn "*thumb1_movsi_insn" mov\\t%0, %1" [(set_attr "length" "2,2,4,4,2,2,2,2,2") (set_attr "type" "*,*,*,*,load1,store1,load1,store1,*") - (set_attr "pool_range" "*,*,*,*,*,*,1020,*,*") + (set_attr "pool_range" "*,*,*,*,*,*,1018,*,*") (set_attr "conds" "set,clob,*,*,nocond,nocond,nocond,nocond,nocond")]) (define_split @@ -5632,7 +5635,7 @@ (define_insn_and_split "pic_load_addr_un (match_dup 2)] UNSPEC_PIC_BASE))] "operands[3] = TARGET_THUMB ? GEN_INT (4) : GEN_INT (8);" [(set_attr "type" "load1,load1,load1") - (set_attr "pool_range" "4096,4096,1024") + (set_attr "pool_range" "4096,4094,1022") (set_attr "neg_pool_range" "4084,0,0") (set_attr "arch" "a,t2,t1") (set_attr "length" "8,6,4")] @@ -5648,7 +5651,10 @@ (define_insn "pic_load_addr_32bit" "TARGET_32BIT && flag_pic" "ldr%?\\t%0, %1" [(set_attr "type" "load1") - (set_attr "pool_range" "4096") + (set (attr "pool_range") + (if_then_else (eq_attr "is_thumb" "no") + (const_int 4096) + (const_int 4094))) (set (attr "neg_pool_range") (if_then_else (eq_attr "is_thumb" "no") (const_int 4084) @@ -5661,7 +5667,7 @@ (define_insn "pic_load_addr_thumb1" "TARGET_THUMB1 && flag_pic" "ldr\\t%0, %1" [(set_attr "type" "load1") - (set (attr "pool_range") (const_int 1024))] + (set (attr "pool_range") (const_int 1018))] ) (define_insn "pic_add_dot_plus_four" @@ -6456,7 +6462,7 @@ (define_insn "*thumb1_movhf" [(set_attr "length" "2") (set_attr "type" "*,load1,store1,*,*") (set_attr "insn" "mov,*,*,mov,mov") - (set_attr "pool_range" "*,1020,*,*,*") + (set_attr "pool_range" "*,1018,*,*,*") (set_attr "conds" "clob,nocond,nocond,nocond,nocond")]) (define_expand "movsf" @@ -6511,7 +6517,8 @@ (define_insn "*arm_movsf_soft_insn" [(set_attr "predicable" "yes") (set_attr "type" "*,load1,store1") (set_attr "insn" "mov,*,*") - (set_attr "pool_range" "*,4096,*") + (set_attr "arm_pool_range" "*,4096,*") + (set_attr "thumb2_pool_range" "*,4094,*") (set_attr "arm_neg_pool_range" "*,4084,*") (set_attr "thumb2_neg_pool_range" "*,0,*")] ) @@ -6533,7 +6540,7 @@ (define_insn "*thumb1_movsf_insn" mov\\t%0, %1" [(set_attr "length" "2") (set_attr "type" "*,load1,store1,load1,store1,*,*") - (set_attr "pool_range" "*,*,*,1020,*,*,*") + (set_attr "pool_range" "*,*,*,1018,*,*,*") (set_attr "insn" "*,*,*,*,*,mov,mov") (set_attr "conds" "clob,nocond,nocond,nocond,nocond,nocond,nocond")] ) @@ -6622,7 +6629,8 @@ (define_insn "*movdf_soft_insn" " [(set_attr "length" "8,12,16,8,8") (set_attr "type" "*,*,*,load2,store2") - (set_attr "pool_range" "*,*,*,1020,*") + (set_attr "arm_pool_range" "*,*,*,1020,*") + (set_attr "thumb2_pool_range" "*,*,*,1018,*") (set_attr "arm_neg_pool_range" "*,*,*,1004,*") (set_attr "thumb2_neg_pool_range" "*,*,*,0,*")] ) @@ -6665,7 +6673,7 @@ (define_insn "*thumb_movdf_insn" [(set_attr "length" "4,2,2,6,4,4") (set_attr "type" "*,load2,store2,load2,store2,*") (set_attr "insn" "*,*,*,*,*,mov") - (set_attr "pool_range" "*,*,*,1020,*,*")] + (set_attr "pool_range" "*,*,*,1018,*,*")] ) (define_expand "movxf" --- gcc-4.7.2/gcc/config/arm/neon.md.~1~ 2012-08-20 12:18:36.000000000 +0200 +++ gcc-4.7.2/gcc/config/arm/neon.md 2012-12-09 11:30:29.000000000 +0100 @@ -201,7 +201,8 @@ (define_insn "*neon_mov" (set_attr "type" "*,f_stored,*,f_loadd,*,*,alu,load2,store2") (set_attr "insn" "*,*,*,*,*,*,mov,*,*") (set_attr "length" "4,4,4,4,4,4,8,8,8") - (set_attr "pool_range" "*,*,*,1020,*,*,*,1020,*") + (set_attr "arm_pool_range" "*,*,*,1020,*,*,*,1020,*") + (set_attr "thumb2_pool_range" "*,*,*,1018,*,*,*,1018,*") (set_attr "neg_pool_range" "*,*,*,1004,*,*,*,1004,*")]) (define_insn "*neon_mov" @@ -246,7 +247,8 @@ (define_insn "*neon_mov" (set_attr "type" "*,*,*,*,*,*,alu,load4,store4") (set_attr "insn" "*,*,*,*,*,*,mov,*,*") (set_attr "length" "4,8,4,8,8,8,16,8,16") - (set_attr "pool_range" "*,*,*,1020,*,*,*,1020,*") + (set_attr "arm_pool_range" "*,*,*,1020,*,*,*,1020,*") + (set_attr "thumb2_pool_range" "*,*,*,1018,*,*,*,1018,*") (set_attr "neg_pool_range" "*,*,*,996,*,*,*,996,*")]) (define_expand "movti" --- gcc-4.7.2/gcc/config/arm/thumb2.md.~1~ 2012-02-21 16:38:35.000000000 +0100 +++ gcc-4.7.2/gcc/config/arm/thumb2.md 2012-12-09 11:30:29.000000000 +0100 @@ -182,7 +182,7 @@ (define_insn "*thumb2_movsi_insn" str%?\\t%1, %0" [(set_attr "type" "*,*,*,*,load1,load1,store1,store1") (set_attr "predicable" "yes") - (set_attr "pool_range" "*,*,*,*,1020,4096,*,*") + (set_attr "pool_range" "*,*,*,*,1018,4094,*,*") (set_attr "neg_pool_range" "*,*,*,*,0,0,*,*")] ) @@ -217,7 +217,7 @@ (define_insn "*thumb2_movhi_insn" ldr%(h%)\\t%0, %1\\t%@ movhi" [(set_attr "type" "*,*,store1,load1") (set_attr "predicable" "yes") - (set_attr "pool_range" "*,*,*,4096") + (set_attr "pool_range" "*,*,*,4094") (set_attr "neg_pool_range" "*,*,*,250")] ) @@ -570,7 +570,7 @@ (define_insn "*thumb2_extendqisi_v6" ldr%(sb%)\\t%0, %1" [(set_attr "type" "alu_shift,load_byte") (set_attr "predicable" "yes") - (set_attr "pool_range" "*,4096") + (set_attr "pool_range" "*,4094") (set_attr "neg_pool_range" "*,250")] ) @@ -583,7 +583,7 @@ (define_insn "*thumb2_zero_extendhisi2_v ldr%(h%)\\t%0, %1" [(set_attr "type" "alu_shift,load_byte") (set_attr "predicable" "yes") - (set_attr "pool_range" "*,4096") + (set_attr "pool_range" "*,4094") (set_attr "neg_pool_range" "*,250")] ) @@ -596,7 +596,7 @@ (define_insn "thumb2_zero_extendqisi2_v6 ldr%(b%)\\t%0, %1\\t%@ zero_extendqisi2" [(set_attr "type" "alu_shift,load_byte") (set_attr "predicable" "yes") - (set_attr "pool_range" "*,4096") + (set_attr "pool_range" "*,4094") (set_attr "neg_pool_range" "*,250")] ) --- gcc-4.7.2/gcc/config/arm/vfp.md.~1~ 2011-12-06 02:03:04.000000000 +0100 +++ gcc-4.7.2/gcc/config/arm/vfp.md 2012-12-09 11:30:29.000000000 +0100 @@ -126,7 +126,7 @@ (define_insn "*thumb2_movsi_vfp" [(set_attr "predicable" "yes") (set_attr "type" "*,*,*,*,load1,load1,store1,store1,r_2_f,f_2_r,fcpys,f_loads,f_stores") (set_attr "insn" "mov,mov,mvn,mov,*,*,*,*,*,*,*,*,*") - (set_attr "pool_range" "*,*,*,*,1020,4096,*,*,*,*,*,1020,*") + (set_attr "pool_range" "*,*,*,*,1018,4094,*,*,*,*,*,1018,*") (set_attr "neg_pool_range" "*,*,*,*, 0, 0,*,*,*,*,*,1008,*")] ) @@ -177,7 +177,8 @@ (define_insn "*movdi_vfp" (const_int 8) (const_int 4))] (const_int 4))) - (set_attr "pool_range" "*,*,*,*,1020,4096,*,*,*,*,1020,*") + (set_attr "arm_pool_range" "*,*,*,*,1020,4096,*,*,*,*,1020,*") + (set_attr "thumb2_pool_range" "*,*,*,*,1018,4094,*,*,*,*,1018,*") (set_attr "neg_pool_range" "*,*,*,*,1004,0,*,*,*,*,1004,*") (set_attr "arch" "t2,any,any,any,a,t2,any,any,any,any,any,any")] ) @@ -222,7 +223,8 @@ (define_insn "*movdi_vfp_cortexa8" * 4")] (const_int 4))) (set_attr "predicable" "yes") - (set_attr "pool_range" "*,*,*,*,1020,4096,*,*,*,*,1020,*") + (set_attr "arm_pool_range" "*,*,*,*,1018,4094,*,*,*,*,1018,*") + (set_attr "thumb2_pool_range" "*,*,*,*,1018,4094,*,*,*,*,1018,*") (set_attr "neg_pool_range" "*,*,*,*,1004,0,*,*,*,*,1004,*") (set (attr "ce_count") (symbol_ref "get_attr_length (insn) / 4")) @@ -409,7 +411,7 @@ (define_insn "*thumb2_movsf_vfp" (set_attr "type" "r_2_f,f_2_r,fconsts,f_loads,f_stores,load1,store1,fcpys,*") (set_attr "insn" "*,*,*,*,*,*,*,*,mov") - (set_attr "pool_range" "*,*,*,1020,*,4092,*,*,*") + (set_attr "pool_range" "*,*,*,1018,*,4090,*,*,*") (set_attr "neg_pool_range" "*,*,*,1008,*,0,*,*,*")] ) @@ -501,7 +503,7 @@ (define_insn "*thumb2_movdf_vfp" (const_int 8) (const_int 4))] (const_int 4))) - (set_attr "pool_range" "*,*,*,1020,*,4096,*,*,*") + (set_attr "pool_range" "*,*,*,1018,*,4094,*,*,*") (set_attr "neg_pool_range" "*,*,*,1008,*,0,*,*,*")] )